Table of Contents

• Phonological processing in the auditory system: a new class of stimuli and advances in fmri techniquesRoy D. Patterson, Stefan Uppenkamp, Dennis Norris, William D. Marslen-Wilson, Ingrid Johnsrude, Emma Williams. 1-4 [doi]
• Data collection and performance evaluation of spoken dialogue systems: the MIT experienceJames R. Glass, Joseph Polifroni, Stephanie Seneff, Victor Zue. 1-4 [doi]
• Multimodal interface research: a science without bordersSharon L. Oviatt. 1-6 [doi]
• Subglottal pressure and prosody in SwedishJohan Liljencrants, Gunnar Fant, Anita Kruckenberg. 1-4 [doi]
• Considerations in the design and evaluation of spoken language dialog systemsLori Lamel, Sophie Rosset, Jean-Luc Gauvain. 5-8 [doi]
• Observation of laryngeal control for voicing and pitch change by magnetic resonance imaging techniqueKiyoshi Honda, Shinobu Masaki, Yasuhiro Shimada. 5-8 [doi]
• Brain regions responsible for word retrieval, speech production and deficient word fluency in elderly people: a PET activation studyItaru F. Tatsumi, Michio Senda, Kenji Ishii, Masahiro Mishina, Masashi Oyama, Hinako Toyama, Keiichi Oda, Masayuki Tanaka, Yasuyuki Gondo. 5-10 [doi]
• Studies of audiovisual speech perception using production-based animationKevin G. Munhall, Christian Kroos, Takaaki Kuratate, J. Lucero, Michel Pitermann, Eric Vatikiotis-Bateson, Hani Yehia. 7-10 [doi]
• Physiological mechanisms for fundamental frequency control in standard ChineseHiroya Fujisaki, Ryou Tomana, Shuichi Narusawa, Sumio Ohno, Changfu Wang. 9-12 [doi]
• Labeling audio-visual speech corpora and training an ANN/HMM audio-visual speech recognition systemMartin Heckmann, Frédéric Berthommier, Christophe Savario, Kristian Kroschel. 9-12 [doi]
• MEG-measurements of brain activity reveal the link between human speech production and perceptionPaavo Alku, Hannu Tiitinen, Kalle J. Palomäki, Päivi Sivonen. 11-14 [doi]
• Perceptual interfaces for information interaction: joint processing of audio and visual information for human-computer interactionChalapathy Neti, Giridharan Iyengar, Gerasimos Potamianos, Andrew W. Senior, Benoît Maison. 11-14 [doi]
• On vocal tract asymmetry/symmetryRené Carré. 13-16 [doi]
• Speech corpus of Chinese discourse and the phonetic researchAijun Li, Maocan Lin, Xiaoxia Chen, Yiqing Zu, Guohua Sun, Wu Hua, Zhigang Yin, Jingzhu Yan. 13-18 [doi]
• Normal and impaired processing in quasi-regular domains of language: the case of English past-tense verbsKaralyn Patterson, Matthew A. Lambon-Ralph, Helen Bird, John R. Hodges, James L. McClelland. 15-19 [doi]
• Towards robust lipreadingWen Gao, Jiyong Ma, Rui Wang, Hongxun Yao. 15-19 [doi]
• Are static MRI measurements representative of dynamic speech? results from a comparative study using MRI, EPG and EMAOlov Engwall. 17-20 [doi]
• Results of the 1999 topic detection and tracking evaluation in Mandarin and EnglishJonathan G. Fiscus, George R. Doddington. 19-24 [doi]
• Neuropsychological and computational evidence for a model of lexical processing, verbal short-term memory and learningNadine Martin, Eleanor M. Saffran, Gary S. Dell, Myrna F. Schwartz, Prahlad Gupta. 20-25 [doi]
• Stream weight optimization of speech and lip image sequence for audio-visual speech recognitionSatoshi Nakamura, Hidetoshi Ito, Kiyohiro Shikano. 20-24 [doi]
• Prosodic control in Chinese TTS systemShinan Lu, Lin He, Yufang Yang, Jianfen Cao. 21-24 [doi]
• Multimodal corpora for human-machine interaction researchSatoshi Nakamura, Keiko Watanuki, Toshiyuki Takezawa, Satoru Hayamizu. 25-28 [doi]
• HMM-based text-to-audio-visual speech synthesisShinji Sako, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura. 25-28 [doi]
• Multistage coarticulation model combining articulatory, formant and cepstral featuresYuqing Gao, Raimo Bakis, Jing Huang, Bing Xiang. 25-28 [doi]
• Normal and impaired reading of Japanese kanji and kanaTakao Fushimi, Mutsuo Ijuin, Naoko Sakuma, Masayuki Tanaka, Tadahisa Kondo, Shigeaki Amano, Karalyn Patterson, Itaru F. Tatsumi. 26-31 [doi]
• Rhythmic organization and signal characteristics of speechOsamu Fujimura. 29-35 [doi]
• The aurora experimental framework for the performance evaluation of speech recognition systems under noisy conditionsDavid Pearce, Hans-Gnter Hirsch. 29-32 [doi]
• Real-time speech-generated subtitles: problems and solutionsJill A. Hewitt, Andi Bateman, Andrew Lambourne, Aladdin M. Ariyaeeinia, P. Sivakumaran. 29-32 [doi]
• A connectionist approach to naming disorders of Japanese in dyslexic patientsMutsuo Ijuin, Takao Fushimi, Karalyn Patterson, Naoko Sakuma, Masayuki Tanaka, Itaru F. Tatsumi, Tadahisa Kondo, Shigeaki Amano. 32-37 [doi]
• Mipad: a next generation PDA prototypeXuedong Huang, Alex Acero, Ciprian Chelba, Li Deng, D. Duchene, Joshua Goodman, H. Hon, D. Jacoby, Li Jiang, R. Loynd, Milind Mahajan, Peter Mau, S. Meredith, S. Mughal, S. Neto, Mike Plumpe, Kuansan Wang, Y. Wang. 33-36 [doi]
• The bavarian archive for speech signals - serving the speech communityHans G. Tillmann, Florian Schiel, Christoph Draxler, Phil Hoole. 33-36 [doi]
• Dialogue management for multimodal user registrationFei Huang, Jie Yang, Alex Waibel. 37-40 [doi]
• The development of spoken language resources in oceaniaJ. Bruce Millar. 37-40 [doi]
• Impaired pronunciations of kanji words by Japanese CVA patientsTaeko Nakayama Wydell, Takako Shinkai. 38-41 [doi]
• Hands-free human-machine dialogue - corpora, technology and evaluationFrank K. Soong, Eric A. Woudenberg. 41-44 [doi]
• On the correlation between facial movements, tongue movements and speech acousticsJintao Jiang, Abeer Alwan, Lynne E. Bernstein, Patricia A. Keating, Edward T. Auer. 42-45 [doi]
• Disability of phonological versus visual information processes in Japanese dyslexic childrenAkira Uno, M. Kaneko, N. Haruhara, M. Kaga. 42-44 [doi]
• Segmental optical phonetics for human and machine speech processingLynne E. Bernstein. 43-46 [doi]
• On-line learning of acoustic and lexical units for domain-independent ASRGiuseppe Riccardi. 45-48 [doi]
• Lexical tone in the spoken word recognition of ChineseXiaolin Zhou, Yanxuan Qu. 45-50 [doi]
• Coarticulation patterns in identical twins: an acoustic case studySandra P. Whiteside, E. Rixon. 46-49 [doi]
• Classification of Thai consonant naming using Thai toneUmavasee Thathong, Somchai Jitapunkul, Visarut Ahkuputra, Ekkarit Maneenoi, Boonchai Thampanitchawong. 47-50 [doi]
• Semi-automatic language model acquisition without large corporaTomoyosi Akiba, Katsunobu Itou. 49-52 [doi]
• Improved lexicon formation through removal of co-articulation and acoustic recognition errorsPhilip Hanna, Darryl Stewart, Ji Ming, F. Jack Smith. 50-53 [doi]
• A high-performance auditory feature for robust speech recognitionQi Li, Frank K. Soong, Olivier Siohan. 51-54 [doi]
• Lexical tone in the speech production of Chinese wordsXiaolin Zhou, Jie Zhuang. 51-54 [doi]
• Detecting acoustic morphemes in lattices for spoken language understandingDijana Petrovska-Delacrétaz, Allen L. Gorin, Jerry H. Wright, Giuseppe Riccardi. 53-56 [doi]
• A two-level approach to the handling of foreign items in Swedish speech technology applicationsAnders Lindström, Anna Kasaty. 54-57 [doi]
• Prosody generation in Chinese synthesis using the template of quantified prosodic unit and base intonation contourYu Hu, Qingfeng Liu, Ren-Hua Wang. 55-58 [doi]
• A new strategy of formant tracking based on dynamic programmingKun Xia, Carol Y. Espy-Wilson. 55-58 [doi]
• Design of robust subtractive beamformer for noisy speech recognitionMitsunori Mizumachi, Masato Akagi, Satoshi Nakamura. 57-60 [doi]
• Word repetitions in Japanese spontaneous speechYasuharu Den, Herbert H. Clark. 58-61 [doi]
• Dominant subspace analysis for auditory spectrumXugang Lu, Gang Li, Lipo Wang. 59-62 [doi]
• Multi-strategy data mining on Mandarin prosodic patternsYiqiang Chen, Wen Gao, Tingshao Zhu, Jiyong Ma. 59-62 [doi]
• Objective long-term assessment of speech quality changes in pre-lingual cochlear implant childrenHamid Sheikhzadeh, Rassoul Amirfattahi. 61-64 [doi]
• The role of language experience in speaker and rate normalization processesAllard Jongman, Corinne B. Moore. 62-65 [doi]
• A unified view on synchronized overlap-add methods for prosodic modifications of speechWerner Verhelst, Dirk Van Compernolle, Patrick Wambacq. 63-66 [doi]
• Spectral and cepstral projection bases constructed by independent component analysisIlyas Potamitis, Nikos Fakotakis, George Kokkinakis. 63-66 [doi]
• Automatic stuttering recognition using hidden Markov modelsElmar Nöth, Heinrich Niemann, Tino Haderlein, M. Decher, Uwe Eysholdt, Frank Rosanowski, Thomas Wittenberg. 65-68 [doi]
• Data-driven importance analysis of linguistic and phonetic informationAchim F. Müller, Jianhua Tao, Rüdiger Hoffmann. 66-69 [doi]
• Chinese tone modeling with stem-MLChilin Shih, Greg Kochanski. 67-70 [doi]
• Relating LPC modeling to a factor-based articulatory modelSacha Krstulovic. 67-70 [doi]
• Grounded speech communicationDeb Roy. 69-72 [doi]
• Overview of an intelligent system for information retrieval based on human-machine dialogue through spoken languageHiroya Fujisaki, Katsuhiko Shirai, Shuji Doshita, Seiichi Nakagawa, Keikichi Hirose, Shuichi Itahashi, Tatsuya Kawahara, Sumio Ohno, Hideaki Kikuchi, Kenji Abe, Shinya Kiriyama. 70-73 [doi]
• On data-derived temporal processing in speech feature extractionMichael L. Shire, Barry Y. Chen. 71-74 [doi]
• Perceptually based automatic prosody labeling and prosodically enriched unit selection improve concatenative text-to-speech synthesisColin W. Wightman, Ann K. Syrdal, Georg Stemmer, Alistair Conkie, Mark C. Beutnagel. 71-74 [doi]
• Acquisition of second language intonationSun-Ah Jun, Mira Oh. 73-76 [doi]
• The expression and recognition of emotions through prosodyLi-chiung Yang. 74-77 [doi]
• Minimum Bayes error feature selectionGeorge Saon, Mukund Padmanabhan. 75-78 [doi]
• Data-driven importance analysis of linguistic and phonetic informationAchim F. Müller, Jianhua Tao, Rüdiger Hoffmann. 75-78 [doi]
• Computer-aided Mandarin pronunciation learning systemMan-Hung Siu, Ka-Ming Wong, Man-Yan Ching, Mei-Sum Lau. 77-80 [doi]
• Prosodic marking of information status in tokyo JapaneseMarc Swerts, Miki Taniguchi, Yasuhiro Katagiri. 78-81 [doi]
• Tonal structure of yes-no question intonation in chahaZhiqiang Li, Degif Petros Banksira. 79-82 [doi]
• Using mutual information to design feature combinationsDaniel P. W. Ellis, Jeff A. Bilmes. 79-82 [doi]
• Speech recognition software: a tool for people with dyslexiaMichael F. McTear, Norma Conn, Nicola Phillips. 81-84 [doi]
• Influence of duration on static and dynamic properties of German vowels in spontaneous speechBritta Wrede, Gernot A. Fink, Gerhard Sagerer. 82-85 [doi]
• Improved tone recognition by normalizing for coarticulation and intonation effectsChao Wang, Stephanie Seneff. 83-86 [doi]
• Multichannel signal separation for cocktail party speech recognition: a dynamic recurrent networkSeungjin Choi, Heonseok Hong, Hervé Glotin, Frédéric Berthommier. 83-86 [doi]
• STAR: articulation training for young childrenH. Timothy Bunnell, Debra Yarrington, James B. Polikoff. 85-88 [doi]
• The regular accent in Chinese sentencesBo Zheng, Bei Wang, Yufang Yang, Shinan Lu, Jianfen Cao. 86-89 [doi]
• Discriminating Chinese lexical tones by anchoring F0 featuresJin-Song Zhang, Satoshi Nakamura, Keikichi Hirose. 87-90 [doi]
• An automatic algorithm for segmenting and labelling a connected digit sequenceV. Kamakshi Prasad, Hema A. Murthy. 87-90 [doi]
• Sound pressure distributions and propagation paths in the vocal tract with the pyriform fossa and the larynxTakayoshi Nakai, Keizo Ishida, Hisayoshi Suzuki. 89-92 [doi]
• A tool for the synchronization of speech and mouth shapes: LIPSOdile Mella, Dominique Fohr, Laurent Martin, Andreas J. Carlen. 90-93 [doi]
• The signal reconstruction of speech by KPCAHui Yan, Xuegong Zhang, Yanda Li, Liqin Shen, Weibin Zhu. 91-93 [doi]
• Universal and language-specific effects in the perception of question intonationCarlos Gussenhoven, Aoju Chen. 91-94 [doi]
• Lip representation by image ellipseLászló Czap. 93-96 [doi]
• Blind source separation based on subband ICA and beamformingHiroshi Saruwatari, Satoshi Kurita, Kazuya Takeda, Fumitada Itakura, Kiyohiro Shikano. 94-97 [doi]
• The interplay and interaction between prosody and syntax: evidence from Mandarin ChineseChiu-yu Tseng, Da-De Chen. 95-97 [doi]
• An acoustic profile of speech efficiencyR. J. J. H. van Son, Barbertje M. Streefkerk, Louis C. W. Pols. 97-100 [doi]
• A quantitative description of German prosody offering symbolic labels as a by-productHansjörg Mixdorff, Hiroya Fujisaki. 98-101 [doi]
• A synchrony front-end using phase-locked-loop techniquesClaudio Estienne, Patricia A. Pelle. 98-101 [doi]
• Identification of utterance intention in Japanese spontaneous spoken dialogue by use of prosody and keyword informationAkira Kurematsu, Yousuke Shionoya. 98-101 [doi]
• Multi-scale audio indexing for Chinese spoken document retrievalHelen M. Meng, Wai Kit Lo, Yuk-Chi Li, P. C. Ching. 101-104 [doi]
• Towards a universal speech interfaceRoni Rosenfeld, Xiaojin Zhu, Arthur R. Toth, Stefanie Shriver, Kevin A. Lenzo, Alan W. Black. 102-105 [doi]
• Improved speech understanding using dialogue expectation in sentence parsingSherif Abdou, Michael S. Scordilis. 102-105 [doi]
• On the use of filter-bank energies driven from the autocorrelation sequence for noisy speech recognitionJavier Hernando. 102-105 [doi]
• Phone dependent modeling of hyperarticulated effects#Hagen Soltau, Alex Waibel. 105-108 [doi]
• The use of belief networks for mixed-initiative dialog modelingHelen M. Meng, Carmen Wai, Roberto Pieraccini. 106-109 [doi]
• A domain model centered approach to spoken language dialog systemsDale Russell. 106-109 [doi]
• Vocabulary-based acoustic model trim down and task adaptationQing Guo, YongHong Yan, Baosheng Yuan, Xiangdong Zhang, Ying Jia, Xiaoxing Liu. 109-112 [doi]
• From multilingual multimodal spoken language acquisition towards on-line assistance to intermittent human interpreting: SIM*, a versatile environment for SLPGeorges Fafiotte, Jianshe Zhai. 110-113 [doi]
• Language model size reduction by pruning and clusteringJoshua Goodman, Jianfeng Gao. 110-113 [doi]
• Integrating flexibility into a structured dialogue model: some design considerationsMichael F. McTear, Susan Allen, Laura Clatworthy, Noelle Ellison, Colin Lavelle, Helen McCaffery. 110-113 [doi]
• Place of articulation cues for voiced and voiceless plosives and fricatives in syllable-initial positionWilla S. Chen, Abeer Alwan. 113-116 [doi]
• Efficient training methods for maximum entropy language modelingJun Wu, Sanjeev Khudanpur. 114-118 [doi]
• A task-independent dialogue controller based on the extended frame-driven methodYasuhisa Niimi, Tomoki Oku, Takuya Nishimoto, Masahiro Araki. 114-117 [doi]
• Informational characterization of dialogue statesMatthias Denecke. 114-117 [doi]
• A block cosine transform and its application in speech recognitionJingdong Chen, Kuldip K. Paliwal, Satoshi Nakamura. 117-120 [doi]
• A new method for dialogue management in an intelligent system for information retrievalKenji Abe, Kazushige Kurokawa, Kazunari Taketa, Sumio Ohno, Hiroya Fujisaki. 118-121 [doi]
• Language modeling for dialog systemWei Xu, Alex Rudnicky. 118-121 [doi]
• Statistical language modeling with a class based ::::n::::-multigram modelSabine Deligne. 119-122 [doi]
• Automatic metric-based speech segmentation for broadcast news via principal component analysisJeih-Weih Hung, Hsin-Min Wang, Lin-Shan Lee. 121-124 [doi]
• The AT&t-DARPA communicator mixed-initiative spoken dialog systemEsther Levin, Shrikanth Narayanan, Roberto Pieraccini, Konstantin Biatov, Enrico Bocchieri, Giuseppe Di Fabbrizio, Wieland Eckert, S. Lee, A. Pokrovsky, Mazin G. Rahim, P. Ruscitti, Marilyn A. Walker. 122-125 [doi]
• Building stochastic language model networks based on simultaneous word/phrase clusteringKallirroi Georgila, Nikos Fakotakis, George Kokkinakis. 122-125 [doi]
• A hierarchical language model incorporating class-dependent word models for OOV words recognitionKoichi Tanigaki, Hirofumi Yamamoto, Yoshinori Sagisaka. 123-126 [doi]
• Maximal rank likelihood as an optimization function for speech recognitionYuqing Gao, Yongxin Li, Michael Picheny. 125-128 [doi]
• Integrating multimodal language processing with speech recognitionSrinivas Bangalore, Michael Johnston. 126-129 [doi]
• Prosody and topic structuring in spoken dialogueLi-chiung Yang, Richard Esposito. 126-129 [doi]
• Input Chinese sentences using digitsFang Zheng, Jian Wu, Wenhu Wu. 127-130 [doi]
• The effects of room acoustics on MFCC speech parameterYue Pan, Alex Waibel. 129-132 [doi]
• Task and domain specific modelling in the Carnegie Mellon communicator systemAlexander I. Rudnicky, Christina L. Bennett, Alan W. Black, Ananlada Chotimongkol, Kevin A. Lenzo, Alice Oh, Rita Singh. 130-134 [doi]
• Elements of conversational computing - a paradigm shiftStéphane H. Maes. 130-133 [doi]
• Hidden-articulator Markov models: performance improvements and robustness to noiseMatthew Richardson, Jeff Bilmes, Chris Diorio. 131-134 [doi]
• Time-frequency distribution of partial phonetic information measured using mutual informationMark Hasegawa-Johnson. 133-136 [doi]
• Rejection and key-phrase spottin techniques using a mumble model in a czech telephone dialog systemLudek Müller, Filip Jurcícek, Lubos Smídl. 134-137 [doi]
• Adapt - a multimodal conversational dialogue system in an apartment domainJoakim Gustafson, Linda Bell, Jonas Beskow, Johan Boye, Rolf Carlson, Jens Edlund, Björn Granström, David House, Mats Wirén. 134-137 [doi]
• Keyword-based discriminative training of acoustic modelsEric D. Sandness, I. Lee Hetherington. 135-138 [doi]
• Subword-dependent speaker clustering for improved speech recognitionLi Jiang, Xuedong Huang. 137-140 [doi]
• Continuous listening for unconstrained spoken dialogTim Paek, Eric Horvitz, Eric K. Ringger. 138-141 [doi]
• Implementation of a multimodal dialog system using extended markup languagesKuansan Wang. 138-141 [doi]
• Segmental minimum Bayes-risk ASR voting strategiesVaibhava Goel, Shankar Kumar, William Byrne. 139-142 [doi]
• An equivalent-class based MMI learning method for MGCPMChunhua Luo, Fang Zheng, Mingxing Xu. 141-144 [doi]
• ORION: from on-line interaction to off-line delegationStephanie Seneff, Chian Chuu, D. Scott Cyphers. 142-145 [doi]
• Audio signals in speech interfacesStefanie Shriver, Alan W. Black, Ronald Rosenfeld. 142-145 [doi]
• Loosely coupled HMMs for ASRHarriet J. Nock, Steve J. Young. 143-146 [doi]
• Continuous speech recognition using articulatory dataAlan Wrench, Korin Richmond. 145-148 [doi]
• Visualisation of spoken dialoguesPéter Pál Boda. 146-149 [doi]
• Practical spoken language translation using compiled feature structure grammarsLei Duan, Alexander Franz, Keiko Horiguchi. 146-149 [doi]
• HMM2- a novel approach to HMM emission probability estimationKatrin Weber, Samy Bengio, Hervé Bourlard. 147-150 [doi]
• Asynchrony with trained transition probabilities improves performance in multi-band speech recognitionBrian Kan-Wing Mak, Yik-Cheung Tam. 149-152 [doi]
• ISIS: A multilingual spoken dialog system developed with CORBA and KQML agentsHelen M. Meng, Shuk Fong Chan, Yee Fong Wong, Tien Ying Fung, Wai Ching Tsui, Tin Hang Lo, Cheong Chat Chan, Ke Chen 0001, Lan Wang, Ting-Yao Wu, Xiaolong Li, Tan Lee, Wing Nin Choi, Yiu Wing Wong, P. C. Ching, Huisheng Chi. 150-153 [doi]
• The construction of speech output to support elderly visually impaired users starting to use the internetMary Zajicek. 150-153 [doi]
• Structured redefinition of sound units by merging and splitting for improved speech recognitionRita Singh, Bhiksha Raj, Richard M. Stern. 151-154 [doi]
• Discriminative MLPs in HMM-based recognition of speech in cellular telephonySunil Sivadas, Pratibha Jain, Hynek Hermansky. 153-156 [doi]
• New feature parameters for detecting misunderstandings in a spoken dialogue systemJun-ichi Hirasawa, Noboru Miyazaki, Mikio Nakano, Kiyoaki Aikawa. 154-157 [doi]
• Effects of word string language models on noisy broadcast news speech recognitionKazuyuki Takagi, Rei Oguro, Kazuhiko Ozeki. 154-157 [doi]
• Speech modeling with state constrained Markov fields over frequency bandsVincent Arsigny, Gérard Chollet, Guillaume Gravier, Marc Sigelle. 155-158 [doi]
• Acoustic modeling for spontaneous speech recognition using syllable dependent modelsToshiyuki Hanazawa, Jun Ishii, Yohei Okato, Kunio Nakajima. 157-160 [doi]
• Semantic tokenization of verbalized numbers in language modelingXiaoqiang Luo, Martin Franz. 158-161 [doi]
• Toward an acoustic-articulatory model of inter-speaker variabilityParham Mokhtari, Frantz Clermont, Kazuyo Tanaka. 158-161 [doi]
• Duration modeling for Chinese synthesis from C-toBI labeled corpusWeibin Zhu, Liqin Shen, Xiaochuan Miu. 159-162 [doi]
• A robust training strategy against extraneous acoustic variations for spontaneous speech recognitionHui Jiang, Li Deng. 161-164 [doi]
• Automatic transcription of lecture speech using topic-independent language modelingKazuomi Kato, Hiroaki Nanjo, Tatsuya Kawahara. 162-165 [doi]
• Degrees of freedom of tongue movements in speech may be constrained by biomechanicsPascal Perrier, Joseph S. Perkell, Yohan Payan, Majid Zandipour, Frank Guenther, Ali Khalighi. 162-165 [doi]
• The pitch movement of word stress in ChineseBei Wang, Bo Zheng, Shinan Lu, Jianfen Cao, Yufang Yang. 163-166 [doi]
• Improved performance and generalization of minimum classification error training for continuous speech recognitionDarryl W. Purnell, Elizabeth C. Botha. 165-168 [doi]
• Extending grammars based on similar-word recognitionRocio Guillén, Randal Erman. 166-169 [doi]
• Gestural overlap, place of articulation and speech rate - an x-ray investigationBéatrice Vaxelaire, Rudolph Sock, Pascal Perrier. 166-169 [doi]
• The distribution of fillers in lectures in the Japanese languageMichiko Watanabe, Carlos Toshinori Ishi. 167-170 [doi]
• Dynamic threshold setting via Bayesian information criterion (BIC) in HMM trainingYing Jia, YongHong Yan, Baosheng Yuan. 169-171 [doi]
• Articulatory compensation and adaptation for unexpected palate shape perturbationMasaaki Honda, Akinori Fujino. 170-173 [doi]
• Particle-based language modellingEdward W. D. Whittaker, Philip C. Woodland. 170-173 [doi]
• Research on stress in bisyllsblic words of MongolianHuhe Harnud, Yuling Zheng, Jiayou Chen. 171-174 [doi]
• Modelling sub-phone insertions and deletions in continuous speech recognitionThomas Hain, Philip C. Woodland. 172-175 [doi]
• Lexical tree decoding with a class-based language model for Chinese speech recognitionWing Nin Choi, Yiu Wing Wong, Tan Lee, P. C. Ching. 174-177 [doi]
• Modeling of a speech production system based on MRI measurement of three-dimensional vocal tract shapes during fricative consonant phonationTakuya Niikawa, Masafumi Matsumura, Takashi Tachimura, Takeshi Wada. 174-177 [doi]
• Modelling of the perception of English sentence stress for computer-assisted language learningKazunori Imoto, Masatake Dantsuji, Tatsuya Kawahara. 175-178 [doi]
• Improved acoustics modeling for speech recognition using transformation techniquesCarrson C. Fung, Oscar C. Au, Wanggen Wan, Chi H. Yim, Cyan L. Keung. 176-179 [doi]
• Impact of bucketing on performance of linearly interpolated language modelsKarthik Visweswariah, Harry Printz, Michael Picheny. 178-181 [doi]
• Improving acoustic-to-articulatory inversion by using hypercube codebooksSlim Ouni, Yves Laprie. 178-181 [doi]
• Data driven intonation modelling of 6 languagesJeska Buhmann, Halewijn Vereecken, Justin Fackrell, Jean-Pierre Martens, Bert Van Coile. 179-182 [doi]
• Concatenative arabic speech synthesis using large speech databaseWael Hamza, Mohsen Rashwan. 182-185 [doi]
• An embedded knowledge integration for hybrid language modellingShuwu Zhang, Hirofumi Yamamoto, Yoshinori Sagisaka. 182-195 [doi]
• Prosody prediction using a tree-structure similarity metricLaurent Blin, Mike Edgington. 183-186 [doi]
• Discriminative training of tied-mixture HMM by deterministic annealingLiang Gu, Jayanth Nayak, Kenneth Rose. 183-186 [doi]
• Hierarchical statistical language models: experiments on in-domain adaptationLucian Galescu, James F. Allen. 186-189 [doi]
• A new speech classifier based on Yinyang compensatory soft computing theoryDong Chen, Jingming Kuang, Yan Zhang. 186-189 [doi]
• Discriminative training in natural language call routingHong-Kwang Jeff Kuo, Chin-Hui Lee. 187-190 [doi]
• Prosodic features for automatic text-independent evaluation of degree of nativeness for language learnersCarlos Teixeira, Horacio Franco, Elizabeth Shriberg, Kristin Precoda, M. Kemal Sönmez. 187-190 [doi]
• New models predicting conversational effects of telephone transmission on speech communication qualitySebastian Möller, Ute Jekosch, Alexander Raake. 190-193 [doi]
• A language model for conversational speech recognition using information designed for speech translationHirofumi Yamamoto, Kouichi Tanigaki, Yoshinori Sagisaka. 190-193 [doi]
• Instantaneous estimation of prosodic pronunciation habits for Japanese students to learn English pronunciationNobuaki Minematsu, Seiichi Nakagawa. 191-194 [doi]
• A speech recognition method with a language-independent intermediate phonetic codeKazuyo Tanaka, Hiroaki Kojima. 191-194 [doi]
• A novel search algorithm for LSF VQJinyu Li, Xin Luo, Ren-Hua Wang. 194-197 [doi]
• Optimizing BNF grammars through source transformationsBob Carpenter, Sol Lerner, Roberto Pieraccini. 194-197 [doi]
• Synthesis of fundamental FDrequency contours of standard Chinese sentences from tone sandhi and focus conditionsJinfu Ni, Keikichi Hirose. 195-198 [doi]
• Confidence measures based on the k-nn probability estimatorFabrice Lefèvre. 195-197 [doi]
• On enhancing katz-smoothing based back-off language modelJian Wu, Fang Zheng. 198-201 [doi]
• On deriving a phoneme model for a new languageNiloy Mukherjee, Nitendra Rajput, L. Venkata Subramaniam, Ashish Verma. 198-201 [doi]
• Conversational networking: conversational protocols for transport, coding, and controlStéphane H. Maes, Dan Chazan, Gilad Cohen, Ron Hoory. 198-201 [doi]
• Syllable duration and its functions in standard Chinese discourseYiqing Zu, Xiaoxia Chan, Aijun Li, Wu Hua, Guohua Sun. 199-202 [doi]
• Can artificial neural networks learn language models?Wei Xu, Alex Rudnicky. 202-205 [doi]
• Estimation of semantic case of Japanese dialogue by use of distance derived from statistics of dependencyTomonobu Saito, Kiyoshi Hashimoto. 202-205 [doi]
• A low bit rate speech coding method using a formant-articulatory parameter nomogramHiroshi Ohmura, Akira Sasou, Kazuyo Tanaka. 202-205 [doi]
• Generating prosody by superposing multi-parametric overlapping contoursBleicke Holm, Gérard Bailly. 203-206 [doi]
• A semantically-based confidence measure for speech recognitionStephen Cox, Srinandan Dasmahapatra. 206-209 [doi]
• Improving language model perplexity and recognition accuracy for medical dictations via within-domain interpolation with literal and semi-literal corporaGuergana Savova, Michael Schonwetter, Sergey V. Pakhomov. 206-209 [doi]
• Variable bit-rate sinusoidal transform coding using variable order spectral estimationNing Li, Derek J. Molyneux, Meau Shin Ho, Barry M. G. Cheetham. 206-209 [doi]
• Consistent pitch markingRaymond N. J. Veldhuis. 207-210 [doi]
• Support vector machines for automatic data cleanupAravind Ganapathiraju, Joseph Picone. 210-213 [doi]
• Efficient harmonic-CELP based hybrid coding of speech at low bit ratesYong-Soo Choi, Sueng-Kyun Ryu, Young-Cheol Park, Dae Hee Youn. 210-213 [doi]
• Placing structuring elements in a word sequence for generating new statistical language modelsKarl Weilhammer, Günther Ruske. 210-213 [doi]
• Labeler agreement in transcribing korean intonation with K-toBISun-Ah Jun, Sook-Hyang Lee, Keeho Kim, Yong-Ju Lee. 211-214 [doi]
• Dynamic selection of language models in a dialogue systemYannick Estève, Frédéric Béchet, Renato de Mori. 214-217 [doi]
• Speech enhancement based on a constrained sinusoidal modelJesper Jensen, John H. L. Hansen. 214-217 [doi]
• Competition-based score analysis for utterance verification in name recognitionYong Gu, Trevor Thomas. 214-217 [doi]
• Effectiveness of prosodic features in syntactic analysis of read Japanese sentencesYukiyoshi Hirose, Kazuhiko Ozeki, Kazuyuki Takagi. 215-218 [doi]
• A bark coherence function for perceived speech quality estimationSang Wook Park, Seung-Kyun Ryu, Young-Cheol Park, Dae Hee Youn. 218-221 [doi]
• Stochastic modeling of semantic content for use IN a spoken dialogue systemMagne Hallstein Johnsen, Trym Holter, Torbjørn Svendsen, Erik Harborg. 218-221 [doi]
• Utterance verification/rejection for speaker-dependent and speaker-independent speech recognitionYaxin Zhang. 218-221 [doi]
• A high-efficiency scheme for secure speech transmission using spatiotemporal chaos synchronizationJinyu Kiang, Kun Deng, Ronghuai Huang. 222-225 [doi]
• Spoken word recognition using the artificial evolution of a set of vocabularyTomio Takara, Eiji Nagaki. 222-225 [doi]
• Emotion recognition in speech signal: experimental study, development, and applicationValery A. Petrushin. 222-225 [doi]
• Data-driven intonation modeling using a neural network and a command response modelAtsuhiro Sakurai, Nobuaki Minematsu, Keikichi Hirose. 223-226 [doi]
• Deeplistener: harnessing expected utility to guide clarification dialog in spoken language systemsEric Horvitz, Tim Paek. 226-229 [doi]
• A bi-lingual Mandarin/taiwanese (min-nan), large vocabulary, continuous speech recognition system based on the tong-yong phonetic alphabet (TYPA)Ren-Yuan Lyu, Chi-yu Chen, Yuang-Chin Chiang, Min-shung Liang. 226-229 [doi]
• Application of speaker authentication technology to a telephone dialogue systemLeandro Rodríguez Liñares, Carmen García-Mateo. 226-229 [doi]
• Natural F0 contours with a new neural-network-hybrid approachCaglayan Erdem, Martin Holzapfel, Rüdiger Hoffmann. 227-230 [doi]
• Chinese spoken language understanding across domainYunbin Deng, Bo Xu, Taiyi Huang. 230-233 [doi]
• Language recognition using time-frequency principal component analysis and acoustic modelingMichel Dutat, Ivan Magrin-Chagnolleau, Frédéric Bimbot. 230-233 [doi]
• A data-driven methodology for the production of multilingual conversational systemsOssama Emam, Jorge Gonzalez, Carsten Günther, Eric Janke, Siegfried Kunzmann, Giulio Maltese, Claire Waast-Richard. 230-233 [doi]
• Prosodic variation with text typeJustin Fackrell, Halewijn Vereecken, Jeska Buhmann, Jean-Pierre Martens, Bert Van Coile. 231-234 [doi]
• Multi-path, context dependent SC-HMM architectures for improved connected word recognitionTzur Vaich, Arnon Cohen. 234-237 [doi]
• Interpolation of stochastic grammar and word bigram models in natural language understandingSven C. Martin, Andreas Kellner, Thomas Portele. 234-237 [doi]
• Comparative study of GMM, DTW, and ANN on Thai speaker identification systemChularat Tanprasert, Varin Achariyakulporn. 234-237 [doi]
• Inter-transcriber reliability of toBI prosodic labelingAnn K. Syrdal, Julia Tevis McGory. 235-238 [doi]
• Efficient mixed-order hidden Markov model inferenceLudwig Schwardt, Johan A. du Preez. 238-241 [doi]
• Robust recognition using multiple utterancesYoram Meron, Keikichi Hirose. 238-241 [doi]
• A portable development tool for spoken dialogue systemsSatoru Kogure, Seiichi Nakagawa. 238-241 [doi]
• Stem-ML: language-independent prosody descriptionGreg Kochanski, Chilin Shih. 239-242 [doi]
• High performance Italian continuous digit recognitionPiero Cosi, John-Paul Hosom, Fabio Tesser. 242-245 [doi]
• Speaker identification and verification using eigenvoicesOlivier Thyes, Roland Kuhn, Patrick Nguyen, Jean-Claude Junqua. 242-245 [doi]
• Error-tolerant language understanding for spoken dialogue systemsYi-Chung Lin, Huei-Ming Wang. 242-245 [doi]
• Using prosody database in Chinese speech synthesisMinghui Dong, Kim-Teng Lua. 243-246 [doi]
• Language modeling by stochastic dependency grammar for Japanese speech recognitionAkinori Ito, Chiori Hori, Masaharu Katoh, Masaki Kohda. 246-249 [doi]
• A priori threshold selection for fixed vocabulary speaker verification systemsArun C. Surendran, Chin-Hui Lee. 246-249 [doi]
• The automatic speech recognition engine ESPERE: experiments on telephone speechDominique Fohr, Odile Mella, Christophe Antoine. 246-249 [doi]
• Some articulatory and acoustic changes associated with emphasis in spoken EnglishDonna Erickson, Kikuo Maekawa, Michiko Hashi, Jianwu Dang. 247-250 [doi]
• A tagger-aided language model with a stack decoderRuiqiang Zhang, Ezra Black, Andrew M. Finch, Yoshinori Sagisaka. 250-253 [doi]
• A comparison of distributed and network speech recognition for mobile communication systemsImre Kiss. 250-253 [doi]
• Application of LDA to speaker recognitionQin Jin, Alex Waibel. 250-253 [doi]
• Fast speech timing in Dutch: durational correlates of lexical stress and pitch accentEsther Janse, Anke Sennema, Anneke Slis. 251-254 [doi]
• An automatic speech recognition system using neural networks and linear dynamic models to recover and model articulatory tracesJoe Frankel, Korin Richmond, Simon King, Paul Taylor. 254-257 [doi]
• Generalizing prosodic prediction of speech recognition errorsJulia Hirschberg, Diane J. Litman, Marc Swerts. 254-257 [doi]
• Automatic language identification using mixed-order HMMs and untranscribed corporaLudwig Schwardt, Johan A. du Preez. 254-257 [doi]
• On perception of word-based local speech rate in Japanese without focusing attentionMakoto Hiroshige, Kantaro Suzuki, Kenji Araki, Koji Tochinai. 255-258 [doi]
• On the potential threat of using large speech corpora for impostor selection in speaker verificationJohan Lindberg, Mats Blomberg. 258-261 [doi]
• The OGI kids² speech corpus and recognizersKhaldoun Shobaki, John-Paul Hosom, Ronald A. Cole. 258-261 [doi]
• Toward unconstrained command and control: data-driven semantic inferenceJerome R. Bellegarda, Kim E. A. Silverman. 258-261 [doi]
• Modeling and generation of accentual phrase F0 contours based on discrete HMMs synchronized at mora-unit transitionsAtsuhiro Sakurai, Koji Iwano, Keikichi Hirose. 259-262 [doi]
• Reducing time-synchronous beam search effort using stage based look-ahead and language model rank based pruningJian Wu, Fang Zheng. 262-265 [doi]
• Continuous speech recognition with parse filteringKen Hanazawa, Shinsuke Sakai. 262-265 [doi]
• Phonetic consistency in Spanish for pin-based speaker verification systemJavier Ortega-Garcia, J. G. Rodriguez, Daniel Tapias Merino. 262-265 [doi]
• Synthesizing prosody for commands in a Xhosa TTS systemPhilippa H. Louw, Justus C. Roux, Elizabeth C. Botha. 263-266 [doi]
• An auditory feature extraction method based on forward-masking and its application in robust speaker identification and speech recognitionZhimin Liu, Xihong Wu, Bin Zhen, Huisheng Chi. 266-269 [doi]
• Investigating text normalization and pronunciation variants for German broadcast transcriptionMartine Adda-Decker, Gilles Adda, Lori Lamel. 266-269 [doi]
• A three-stage solution for flexible vocabulary speech understandingGrace Chung. 266-269 [doi]
• Design and implementation of a Greek text-to-speech system based on concatenative synthesisCostas Christogiannis, Yiannis Stavroulas, Yiannis Vamvakoulas, Theodora A. Varvarigou, Agatha Zappa, Chilin Shih, Amalia Arvaniti. 267-270 [doi]
• Decoding speech in the presence of other sound sourcesJon Barker, Martin Cooke, Daniel P. W. Ellis. 270-273 [doi]
• A comparison of data-derived and knowledge-based modeling of pronunciation variationMirjam Wester, Eric Fosler-Lussier. 270-273 [doi]
• Transition-oriented hidden Markov models for speaker verificationS. Douglas Peters, Matthieu Hébert, Daniel Boies. 270-273 [doi]
• GENESIS-II: a versatile system for language generation in conversational system applicationsLauren Baptist, Stephanie Seneff. 271-274 [doi]
• Efficient search strategy in large vocabulary continuous speech recognition using prosodic boundary informationShi-wook Lee, Keikichi Hirose, Nobuaki Minematsu. 274-277 [doi]
• An LLR-based technique for frame selection for GMM-based text-independent speaker identificationPang Kuen Tsoi, Pascale Fung. 274-277 [doi]
• A bottom-up method for obtaining information about pronunciation variationJudith M. Kessens, Helmer Strik, Catia Cucchiarini. 274-277 [doi]
• New analysis method for harmonic plus noise model based on time-domain periodicity scoreEun-Kyoung Kim, Yung-Hwan Oh. 275-278 [doi]
• Robust speaker recognition based on high order cumulantJiyong Ma, Wen Gao. 278-281 [doi]
• Large vocabulary Korean continuous speech recognition using a one-pass algorithmHa-Jin Yu, Hoon Kim, Joon-Mo Hong, Min-Seong Kim, Jong-Seok Lee. 278-281 [doi]
• Semi-continuous segmental probability modeling for continuous speech recognitionJiyong Zhang, Fang Zheng, Mingxing Xu, Ditang Fang. 278-281 [doi]
• Straight-based voice conversion algorithm based on Gaussian mixture modelTomoki Toda, Jinlin Lu, Hiroshi Saruwatari, Kiyohiro Shikano. 279-282 [doi]
• A tree-trellis n-best decoder for stochastic context-free grammarsAlexander Seward. 282-285 [doi]
• Acoustic modelling using modular/ensemble combinations of heterogeneous neural networksChristos A. Antoniou, T. Jeff Reynolds. 282-285 [doi]
• Two-stage speaker identification system based on VQ and NBDGMMLuo Si, Qixiu Hu. 282-285 [doi]
• Syllable-based text-to-phoneme conversion for GermanMarion Libossek, Florian Schiel. 283-286 [doi]
• A MAP approach, with synchronous decoding and unit-based normalization for text-dependent speaker verificationJohnny Mariéthoz, Johan Lindberg, Frédéric Bimbot. 286-289 [doi]
• Unifying HMM and phone-pair segment modelsHsiao-Wuen Hon, Shankar Kumar, Kuansan Wang. 286-289 [doi]
• EWAVES: an efficient decoding algorithm for lexical tree based speech recognitionPatrick Nguyen, Luca Rigazio, Jean-Claude Junqua. 286-289 [doi]
• Multi-group mixture weight HMMMing Li, Tiecheng Yu. 290-292 [doi]
• Novel two-pass search strategy using time-asynchronous shortest-first second-pass beam searchAtsunori Ogawa, Yoshiaki Noda, Shoichi Matsunaga. 290-293 [doi]
• A fast search method of speaker identification for large population using pre-selection and hierarchical matchingZhibin Pan, Koji Kotani, Tadahiro Ohmi. 290-293 [doi]
• A hybrid approach for grapheme-to-phoneme conversion based on a combination of partial string matching and a neural networkHorst-Udo Hain. 291-294 [doi]
• Application of pattern recognition neural network model to hearing system for continuous speechTetsuro Kitazoe, Tomoyuki Ichiki, Makoto Funamori. 293-296 [doi]
• Optimal fusion of diverse feature sets for speaker identification: an alternative methodLan Wang, Ke Chen, Huisheng Chi. 294-297 [doi]
• Pruning of state-tying tree using bayesian information criterion with multiple mixturesYu-Chung Chan, Man-Hung Siu, Brian Kan-Wing Mak. 294-297 [doi]
• Parametric high definition (PHD) speech synthesis-by-analysis: the development of a fundamentally new system creating connected speech by modifying lexically-represented language unitsHans G. Tillmann, Hartmut R. Pfitzinger. 295-297 [doi]
• Data-dependent kernels in svm classification of speech patternsNathan Smith, Mahesan Niranjan. 297-300 [doi]
• A new synthesis algorithm using phase information for TTS systemsChul Hong Kwon, Minkyu Lee, Joseph P. Olive. 298-301 [doi]
• Improvements of the Philips 2000 Taiwan Mandarin benchmark systemYuan-Fu Liao, Nick Wang, Max Huang, Hank Huang, Frank Seide. 298-301 [doi]
• Transformation enhanced multi-grained modeling for text-independent speaker recognitionUpendra V. Chaudhari, Jiri Navratil, Stéphane H. Maes, Ramesh A. Gopinath. 298-301 [doi]
• Exploiting frequency-scaling invariance properties of the scale transform for automatic speech recognitionS. Umesh, Richard C. Rose, S. Parthasarathy. 301-304 [doi]
• Imposture using synthetic speech against speaker verification based on spectrum and pitchTakashi Masuko, Keiichi Tokuda, Takao Kobayashi. 302-305 [doi]
• Extending the generation of word graphs for a cross-word m-gram decoderChristoph Neukirchen, Xavier L. Aubert, Hans Dolfing. 302-305 [doi]
• Unit fusion for concatenative speech synthesisJohan Wouters, Michael W. Macon. 302-305 [doi]
• Large vocabulary continuous speech recognition under real environments using adaptive sub-band spectral subtractionMasahiro Fujimoto, Jun Ogata, Yasuo Ariki. 305-308 [doi]
• Improvements in search algorithm for large vocabulary continuous speech recognitionQingWei Zhao, Zhiwei Lin, Baosheng Yuan, YongHong Yan. 306-309 [doi]
• Diphone collection and synthesisKevin A. Lenzo, Alan W. Black. 306-309 [doi]
• Speaker recognition with recurrent neural networksShahla Parveen, Abdul Qadeer, Phil Green. 306-309 [doi]
• Perceptual harmonic cepstral coefficients as the front-end for speech recognitionLiang Gu, Kenneth Rose. 309-312 [doi]
• Speaker feature extraction from pitch information based on spectral subtraction for speaker identificationYoshiroh Itoh, Jun Toyama, Masaru Shimbo. 310-313 [doi]
• Natural language generation for spoken dialogueThomas Portele. 310-313 [doi]
• New developments in automatic meeting transcriptionHua Yu, Takashi Tomokiyo, Zhirong Wang, Alex Waibel. 310-313 [doi]
• Optimization of sub-band weights using simulated noisy speech in multi-band speech recognitionYik-Cheung Tam, Brian Kan-Wing Mak. 313-316 [doi]
• Preselection of candidate units in a unit selection-based text-to-speech synthesis systemAlistair Conkie, Mark C. Beutnagel, Ann K. Syrdal, Philip E. Brown. 314-317 [doi]
• Text-independent speaker identification using Gaussian mixture bigram modelsWei-Ho Tsai, Chiwei Che, Wen-Whei Chang. 314-317 [doi]
• On the use of speaking rate as a generalized feature to improve decision treesRobert Faltlhauser, Thilo Pfau, Günther Ruske. 317-320 [doi]
• Comparison of MFCC and pitch synchronous AM, FM parameters for speaker identificationHassan Ezzaidi, Jean Rouat. 318-321 [doi]
• Self-organizing letter code-book for text-to-phoneme neural network modelKåre Jean Jensen, Søren Riis. 318-321 [doi]
• Effective vector quantization for a highly compact acoustic model for LVCSRJielin Pan, Baosheng Yuan, YongHong Yan. 318-321 [doi]
• Syllable recognition using glides based on a non-linear transformationJun Toyama, Masaru Shimbo. 321-324 [doi]
• Effective lexical tree search for large vocabulary continuous speech recognitionHiroki Yamamoto, Toshiaki Fukada, Yasuhiro Komori. 322-325 [doi]
• A flexible, scalable finite-state transducer architecture for corpus-based concatenative speech synthesisJon R. W. Yi, James R. Glass, I. Lee Hetherington. 322-325 [doi]
• Consonant discrimination in elicited and spontaneous speech: a case for signal-adaptive front ends in ASRM. Kemal Sönmez, Madelaine Plauché, Elizabeth Shriberg, Horacio Franco. 325-328 [doi]
• Determination of threshold for speaker verification using speaker adaptation gain in likelihood during trainingToshiaki Uchibe, Shingo Kuroiwa, Norio Higuchi. 326-329 [doi]
• Analysis of fundamental frequency contours of standard Chinese in terms of the command-response model and its application to synthesis by rule of intonationChangfu Wang, Hiroya Fujisaki, Ryou Tomana, Sumio Ohno. 326-329 [doi]
• Improvements in automatic speech summarization and evaluation methodsChiori Hori, Sadaoki Furui. 326-329 [doi]
• A new approach for multi-band speech recognition based on probabilistic graphical modelsKhalid Daoudi, Dominique Fohr, Christophe Antoine. 329-332 [doi]
• Manipulating speech pitch periods according to optimal insertion/deletion position in residual signal for intonation control in speech synthesisToshio Hirai, Seiichi Tenpaku, Kiyohiro Shikano. 330-333 [doi]
• Accent-specific Mandarin adaptation based on pronunciation modeling technologyMingkuan Liu, Bo Xu. 330-333 [doi]
• Automatic phonetic transcription of spontaneous speech (american English)Shuangyu Chang, Lokendra Shastri, Steven Greenberg. 330-333 [doi]
• Test of several external posterior weighting functions for multiband full combination ASRHervé Glotin, Frédéric Berthommier. 333-336 [doi]
• Speed improvement of the tree-based time asynchronous searchMiroslav Novak, Michael Picheny. 334-337 [doi]
• Improving naturalness of Thai text-to-speech synthesis by prosodic rulePradit Mittrapiyanuruk, Chatchawarn Hansakunbuntheung, Virongrong Tesprasit, Virach Sornlertlamvanich. 334-337 [doi]
• Using the modulation wavelet transform for feature extraction in automatic speech recognitionKenji Okada, Takayuki Arai, Noburu Kanederu, Yasunori Momomura, Yuji Murahara. 337-340 [doi]
• Word-level F0 range in Mandarin Chinese and its application to inserting words into a sentenceDawei Xu, Hiroki Mori, Hideki Kasuya. 338-341 [doi]
• Recent improvements in speech recognition performance on large vocabulary conversational speech (voicemail and switchboard)Jing Huang, Brian Kingsbury, Lidia Mangu, Mukund Padmanabhan, George Saon, Geoffrey Zweig. 338-341 [doi]
• AM-demodulation of speech spectra and its application io noise robust speech recognitionQifeng Zhu, Abeer Alwan. 341-344 [doi]
• A prominence based model of Swedish intonationGunnar Fant, Anita Kruckenberg. 341-344 [doi]
• Speaker normalization training and adaptation for speech recognitionLei He, Ditang Fang, Wenhu Wu. 342-345 [doi]
• A new Japanese TTS system based on speech-prosody database and speech modificationMitsuaki Isogai, Kimihito Tanaka, Satoshi Takano, Hideyuki Mizuno, Masanobu Abe, Shin ya Nakajima. 342-345 [doi]
• Comparison of HMM experts with MLP experts in the full combination multi-band approach to robust ASRAstrid Hagen, Andrew C. Morris. 345-348 [doi]
• Roles of voice source dynamics as a conveyer of paralinguistic featuresHideki Kasuya, Masanori Yoshizawa, Kikuo Maekawa. 345-348 [doi]
• Lexical and acoustic modeling of non-native speech in LVSCRLaura Mayfield Tomokiyo. 346-349 [doi]
• Stress assignment in Spanish proper namesRubén San Segundo, Juan Manuel Montero, Ricardo de Córdoba, Juana M. Gutiérrez-Arriola. 346-349 [doi]
• Influence of paralinguistic information on segmental articulationKikuo Maekawa, Takayuki Kagomiya. 349-352 [doi]
• Using multiple time scales in the framework of multi-stream speech recognitionAstrid Hagen, Hervé Bourlard. 349-352 [doi]
• Modeling phone correlation for speaker adaptive speech recognitionBaojie Li, Keikichi Hirose, Nobuaki Minematsu. 350-353 [doi]
• Segmentation of prosodic phrases for improving the naturalness of synthesized Mandarin Chinese speechZhengyu Niu, Peiqi Chai. 350-353 [doi]
• Analysis and modeling of the effect of paralinguistic information upon the local speech rateSumio Ohno, Yoshimitsu Sugiyama, Hiroya Fujisaki. 353-356 [doi]
• Streamlining the front end of a speech recognizerHua Yu, Alex Waibel. 353-356 [doi]
• Practical language modeling: an interpolating methodXiaohu Liu, Douglas D. O Shaughnessy. 354-357 [doi]
• Very fast adaptation for large vocabulary continuous speech recognition using eigenvoicesHenrik Botterweck. 354-357 [doi]
• Rhythm of spoken Chinese - linguistic and paralinguistic evidences -Jianfen Cao. 357-360 [doi]
• Reconstruction of damaged spectrographic features for robust speech recognitionBhiksha Raj, Michael L. Seltzer, Richard M. Stern. 357-360 [doi]
• Efficiently using speaker adaptation dataChengyi Zheng, YongHong Yan. 358-361 [doi]
• Combination of different n-grams based on their different assumptionsGongjun Li, Na Dong, Toshiro Ishikawa. 358-361 [doi]
• Impact of speaking style and speaking task on acoustic modelsJanienke Sturm, Hans Kamperman, Lou Boves, Els den Os. 361-364 [doi]
• A combination of speaker normalization and speech rate normalization for automatic speech recognitionThilo Pfau, Robert Faltlhauser, Günther Ruske. 362-365 [doi]
• Construction of speech corpus in moving car environmentNobuo Kawaguchi, Shigeki Matsubara, Hiroyuki Iwa, Shoji Kajita, Kazuya Takeda, Fumitada Itakura, Yasuyoshi Inagaki. 362-365 [doi]
• Articulatory characteristics of emotional utterances in spoken EnglishDonna Erickson, Arthur Abramson, Kikuo Maekawa, Tokihiko Kaburagi. 365-368 [doi]
• Encoded speech recognition accuracy improvement in adverse environments by enhancing formant spectral bandsShubha Kadambe, Ron Burns. 365-368 [doi]
• Parsing spoken dialoguesYue-Shi Lee, Hsin-Hsi Chen. 366-369 [doi]
• Speech model compensation with direct adaptation of cepstral variance to noisy environmentTai-Hwei Hwang, Kuo-Hwei Yuo, Hsiao-Chuan Wang. 366-369 [doi]
• Analytical and perceptual study on the role of acoustic features in realizing emotional speechKeikichi Hirose, Nobuaki Minematsu, Hiromichi Kawanami. 369-372 [doi]
• A Noise Robust Multilingual Reference Recogniser Based on Speechdat(II)Børge Lindberg, Finn Tore Johansen, Narada D. Warakagoda, Gunnar Lehtinen, Zdravko Kacic, Andrej Zgank, Kjell Elenius, Giampiero Salvi. 370-373 [doi]
• Gaussian similarity analysis and its application in speaker adaptationJi Wu, Zuoying Wang. 370-373 [doi]
• Expression of emotion and attitude through temporal speech variationsSylvie J. L. Mozziconacci, Dik J. Hermes. 373-378 [doi]
• Soft decisions in missing data techniques for robust automatic speech recognitionJon Barker, Ljubomir Josifovski, Martin Cooke, Phil D. Green. 373-376 [doi]
• A method for style adaptation to spontaneous speech by using a semi-linear interpolation techniqueNobuyasu Itoh, Masafumi Nishimura, Shinsuke Mori. 374-377 [doi]
• New tone recognition methods for Chinese continuous speechJian Liu, Tiecheng Yu. 377-380 [doi]
• VODIS - voice-operated driver information systems: a usability study on advanced speech technologies for car environmentsPetra Geutner, Luis Arévalo, Joerg Breuninger. 378-382 [doi]
• The design and application of a speech database for Chinese TTS systemMuhua Lv, Lianhong Cai. 378-381 [doi]
• A cross-cultural investigation of emotion inferences from voice and speech: implications for speech technologyKlaus R. Scherer. 379-382 [doi]
• Reliable bands guided similarity measure for noise-robust speech recognitionBo Zhang, Gang Peng, William S.-Y. Wang. 381-384 [doi]
• Use of multiple classifiers for speech recognition in wireless CDMA network environmentsRathinavelu Chengalvarayan. 382-385 [doi]
• Natural language call steering for service applicationsWu Chou, Qiru Zhou, Hong-Kwang Jeff Kuo, Antoine Saad, David Attwater, Peter J. Durston, Mark Farrell, Frank Scahill. 382-385 [doi]
• Speaker dependent emotion recognition using speech signalsBong Seok Kang, Chul-Hee Han, Sang-Tae Lee, Dae Hee Youn, Chungyong Lee. 383-386 [doi]
• A novel feature extraction using multiple acoustic feature planes for HMM-based speech recognitionTsuneo Nitta, Masashi Takigawa, Takashi Fukuda. 385-388 [doi]
• An imperative programming language for spoken language translationAlexander Franz, Keiko Horiguchi, Lei Duan. 386-389 [doi]
• A single-stage top-down probabilistic approach towards understanding spoken and handwritten mathematical formulasJörg Hunsinger, Manfred Lang. 386-389 [doi]
• Concatenative text-to-speech synthesis based on prototype waveform interpolation (a time frequency approach)Edmilson Morais, Paul Taylor, Fábio Violaro. 387-390 [doi]
• Integrating the energy information into MFCCFang Zheng, Guoliang Zhang. 389-392 [doi]
• Low complexity connected digit recognition for mobile applicationsPrabhu Raghavan, Sunil K. Gupta. 390-393 [doi]
• Fine keyword clustering using a thesaurus and example sentences for speech translationYumi Wakita, Kenji Matsui, Yoshinori Sagisaka. 390-393 [doi]
• A corpus-based Chinese speech synthesis with contextual dependent unit selectionRen-Hua Wang, Zhongke Ma, Wei Li, Donglai Zhu. 391-394 [doi]
• Speaker independent phoneme recognition by MLP using wavelet featuresOmar Farooq, Sekharjit Datta. 393-396 [doi]
• Telephone speech recognition from large lists of Czech wordsJan Nouza. 394-397 [doi]
• Segment selection in the L&h Realspeak laboratory TTS systemGeert Coorman, Justin Fackrell, Peter Rutten, Bert Van Coile. 395-398 [doi]
• A corpus-based approach for robust ASR in reverberant environmentsLaurent Couvreur, Christophe Couvreur, Christophe Ris. 397-400 [doi]
• Spoken language corpus for machine interpretation researchYasuyuki Aizawa, Shigeki Matsubara, Nobuo Kawaguchi, Katsuhiko Toyama, Yasuyoshi Inagaki. 398-401 [doi]
• Speech and word detection algorithms for hands-free applicationsDuanpei Wu, Xavier Menéndez-Pidal, Lex Olorenshaw, Ruxin Chen, Mick Tanaka, Mariscela Amador. 398-401 [doi]
• A Taiwanese (min-nan) text-to-speech (TTS) system based on automatically generated synthetic unitsRen-Yuan Lyu, Zhen-hong Fu, Yuang-Chin Chiang, Hui-mei Liu. 399-402 [doi]
• Modeling out-of-vocabulary words for robust speech recognitionIssam Bazzi, James R. Glass. 401-404 [doi]
• Large vocabulary continuous speech recognition of read speech over cellular and landline networksAshwin Rao, Bob Roth, Venkatesh Nagesha, Don McAllaster, Natalie Liberman, Larry Gillick. 402-405 [doi]
• When will synthetic speech sound human: role of rules and dataJan P. H. van Santen, Michael W. Macon, Andrew Cronk, John-Paul Hosom, Alexander Kain, Vincent Pagel, Johan Wouters. 402-409 [doi]
• Puretalk: a high quality Japanese text-to-speech systemMasayuki Yamada, Yasuo Okutani, Toshiaki Fukada, Takashi Aso, Yasuhiro Komori. 403-406 [doi]
• Hidden Markov model environmental compensation for automatic speech recognition on hand-held mobile devicesBojana Gajic, Richard C. Rose. 405-408 [doi]
• Toward speech communications beyond language barrier - research of spoken language translation technologies at ATR -Seiichi Yamamoto. 406-411 [doi]
• Using cross-syllable units for Cantonese speech synthesisKa Man Law, Tan Lee. 407-410 [doi]
• A neural network for classification with incomplete data: application to robust ASRAndrew C. Morris, Ljubomir Josifovski, Hervé Bourlard, Martin Cooke, Phil D. Green. 409-412 [doi]
• Corpus-based techniques in the AT&t nextgen synthesis systemAnn K. Syrdal, Colin W. Wightman, Alistair Conkie, Yannis Stylianou, Marc C. Beutnagel, Juergen Schroeter, Volker Strom, Ki-Seung Lee, Matthew J. Makashay. 410-415 [doi]
• Limited domain synthesisAlan W. Black, Kevin A. Lenzo. 411-414 [doi]
• Speech translation for French within the c-STAR II consortium and future perspectivesHervé Blanchon, Christian Boitet. 412-417 [doi]
• Feature-dependent allophone clusteringShigeki Matsuda, Mitsuru Nakai, Hiroshi Shimodaira, Shigeki Sagayama. 413-416 [doi]
• Coupling dialogue and prosody computation in spoken dialogue generationChristine H. Nakatani, Jennifer Chu-Carroll. 415-418 [doi]
• Limitations to concatenative speech synthesisNick Campbell. 416-419 [doi]
• Data-driven lexical modeling of pronunciation variations for ASRQian Yang, Jean-Pierre Martens. 417-420 [doi]
• Japanese-to-Chinese spoken language translation based on the simple expressionChengqing Zong, Yumi Wakita, Bo Xu, Zhenbiao Chen, Kenji Matsui. 418-421 [doi]
• A study on the pitch pattern of a singing voice synthesis system based on the cepstral methodTomio Takara, Kazuto Izumi, Keiichi Funaki. 419-422 [doi]
• A design method of speech corpus for text-to-speech synthesis taking account of prosodyHisashi Kawai, Seiichi Yamamoto, Norio Higuchi, Tohru Shimizu. 420-425 [doi]
• Fuzzy entropy hidden Markov models for speech recognitionDat Tran, Michael Wagner. 421-424 [doi]
• Finite-state models for lexical reordering in spoken language translationSrinivas Bangalore, Giuseppe Riccardi. 422-425 [doi]
• Automatic methods for lexical stress assignment and syllabificationSteve Pearson, Roland Kuhn, Steven Fincke, Nick Kibre. 423-426 [doi]
• Adjacent node continuous-state HMM’sCarl Quillen. 425-428 [doi]
• Corpus-based methods and hand-built methodsRichard Sproat. 426-428 [doi]
• CHUNKY: an example based machine translation system for spoken dialogsRalf Engel. 426-429 [doi]
• Using bayesian belief networks for model duration in text-to-speech systemsOlga Goubanova, Paul Taylor. 427-430 [doi]
• Modelling phonetic context using head-body-tail models for connected digit recognitionJanienke Sturm, Eric Sanders. 429-432 [doi]
• Heredity and environment in speech recognition: the role of a priori information vs. dataMichael A. Picheny. 429-433 [doi]
• Spoken translation: challenges and opportunitiesGianni Lazzari. 430-435 [doi]
• Using support vector machines for spoken digit recognitionIssam Bazzi, Dina Katabi. 433-436 [doi]
• Comparing static and dynamic features for segmental cost function calculation in concatenative speech synthesisDiane Hirschfeld. 435-438 [doi]
• Analysis into a formal task-oriented pivot without clear abstract - semantics is best handled as usual translationChristian Boitet, Jean-Philippe Guilbaud. 436-439 [doi]
• Data-driven model construction for continuous speech recognition using overlapping articulatory featuresJiping Sun, Xing Jing, Li Deng. 437-440 [doi]
• A constraint-based analysis of compound accent in JapaneseHaruo Kubozono. 438-441 [doi]
• Temporal patterns of critical-band spectrum for text-to-speechPratibha Jain, Hynek Hermansky. 439-441 [doi]
• An improved template-based approach to spoken language translationChengqing Zong, Taiyi Huang, Bo Xu. 440-443 [doi]
• Speech recognition using HMMs with quantized parametersMarcel Vasilache. 441-444 [doi]
• Language acquisition through a human-robot interfaceNaoto Iwahashi. 442-447 [doi]
• Successive cohort selection (SCS) for text-independent speaker verificationEric H. C. Choi, Jianming Song. 442-445 [doi]
• An automatic interpretation system for travel conversationTakao Watanabe, Akitoshi Okumura, Shinsuke Sakai, Kiyoshi Yamabana, Shinichi Doi, Ken Hanazawa. 444-447 [doi]
• A perception and PDE based nonlinear transformation for processing spoken wordsYingyong Qi, Jack Xin. 445-448 [doi]
• Fuzzy normalisation methods for speaker verificationDat Tran, Michael Wagner. 446-449 [doi]
• Rules, but what for? - rule description as efficient and robust abstraction of corpora and optimal fitting to applications -Yoshinori Sagisaka, Hirofumi Yamamoto, Minoru Tsuzaki, Hiroaki Kato. 448-451 [doi]
• Cellular-phone based speech-to-speech translation system ATR-MATRIXRainer Gruhn, Harald Singer, Hajime Tsukada, Masaki Naito, Atsushi Nishino, Atsushi Nakamura, Yoshinori Sagisaka, Satoshi Nakamura. 448-451 [doi]
• Training of isolated word recognizers with continuous speechReinhard Blasig, Georg Rose, Carsten Meyer. 449-452 [doi]
• Speaker verification in operational environments - monitoring for improved service operationYong Gu, Hans Jongebloed, Dorota J. Iskra, Els den Os, Lou Boves. 450-453 [doi]
• Generation of pronunciation rule sets for automatic segmentation of American English and JapaneseNicole Beringer, Tsuyoshi Ito, Marcia Neff. 452-455 [doi]
• Cross-linguistic aspects of intonation perceptionVeronika Makarova. 452-453 [doi]
• Repair patterns in spontaneous Chinese dialogs: morphemes, words, and phrasesShu-Chuan Tseng. 453-456 [doi]
• On-line unsupervised adaptation in speaker verificationLarry P. Heck, Nikki Mirghafori. 454-457 [doi]
• Visual information and the perception of prosodyHaruo Kubozono, Shosuke Haraguchi. 454-457 [doi]
• Hindi speech databaseK. Samudravijaya, P. V. S. Rao, S. S. Agrawal. 456-459 [doi]
• Improvement of a physiological articulatory model for synthesis of vowel sequencesJianwu Dang, Kiyoshi Honda. 457-460 [doi]
• Multiple sub-band systems for speaker verificationP. Sivakumaran, Aladdin M. Ariyaeeinia, Jill A. Hewitt. 458-461 [doi]
• Perception of synthesized singing voices with fine fluctuations in their fundamental frequency contoursMasato Akagi, Hironori Kitakaze. 458-461 [doi]
• MAT-2000 - design, collection, and validation of a Mandarin 2000-speaker telephone speech databaseHsiao-Chuan Wang, Frank Seide, Chiu-yu Tseng, Lin-Shan Lee. 460-463 [doi]
• Computation of 3-d vocal tract acoustics based on mode-matching techniqueKunitoshi Motoki, Xavier Pelorson, Pierre Badin, Hiroki Matsuzaki. 461-464 [doi]
• Neuromagnetic study on localization of speech soundsKalle J. Palomäki, Paavo Alku, Ville Mäkinen, Patrick J. C. May, Hannu Tiitinen. 462-465 [doi]
• An orthogonal GMM based speaker verification systemXiaoxing Liu, Baosheng Yuan, YongHong Yan. 462-465 [doi]
• Wavesurfer - an open source speech toolKåre Sjölander, Jonas Beskow. 464-467 [doi]
• Exploring vowel production strategies from infant to adult by means of articulatory inversion of formant dataLucie Ménard, Louis-Jean Boë. 465-468 [doi]
• Perception of identical vowel sequences in Japanese conversational speechYukiyoshi Hirose, Kazuhiko Kakehi. 466-469 [doi]
• A na ve de-lambing method for speaker identificationQin Jin, Alex Waibel. 466-469 [doi]
• Automatic labelling of voice-quality in speech databases for synthesisNick Campbell, Toru Marumoto. 468-471 [doi]
• Segmentation of a speech waveform according to glottal open and closed phases using an autoregressive-HMMGavin Smith, Tony Robinson. 469-472 [doi]
• Acoustic cues to perception of vowel qualitySantiago Fernández, Sergio Feijóo. 470-473 [doi]
• The lincoln speaker recognition system: NIST eval2000Douglas A. Reynolds, Robert B. Dunn, Jack McLaughlin. 470-473 [doi]
• Speech quality evaluation based on AM-FM time-frequency representationsJoe Timoney, J. Brian Foley. 472-475 [doi]
• Comparison of inverse filtering of the flow signal and microphone signalRosemary Orr, Bert Cranen, Felix de Jong, Lou Boves. 473-476 [doi]
• Foldering voicemail messages by caller using text independent speaker recognitionAaron E. Rosenberg, S. Parthasarathy, Julia Hirschberg, Stephen Whittaker. 474-478 [doi]
• A solution to the reduction of concatenation artefacts in speech synthesisEsther Klabbers, Raymond N. J. Veldhuis, Kim Koppen. 474-477 [doi]
• Free software toolkit for Japanese large vocabulary continuous speech recognitionTatsuya Kawahara, Akinobu Lee, Tetsunori Kobayashi, Kazuya Takeda, Nobuaki Minematsu, Shigeki Sagayama, Katsunobu Itou, Akinori Ito, Mikio Yamamoto, Atsushi Yamada, Takehito Utsuro, Kiyohiro Shikano. 476-479 [doi]
• Inter- and intra-speaker variability of glottal flow derivative using the LF modelMarkus Iseli, Abeer Alwan. 477-480 [doi]
• Domain-unconstrained language understanding based on CKIP-auto tag, how-net, and ARTJhing-Fa Wang, Hsien-Chang Wang, Kin-Nan Lee, Chieh-Yi Huang. 478-481 [doi]
• Structural framework for combining speaker recognition methodsClaude Montacié, Marie-José Caraty. 479-482 [doi]
• Robust speech recognition based on off-line elicitation of multiple priors and on-line adaptive prior fusionQiang Huo, Bin Ma. 480-483 [doi]
• Multi-level annotation for spoken language corporaPhilippe Blache, Daniel Hirst. 481-484 [doi]
• The generation of representations of word meanings from dictionariesChris Powell, Mary Zajicek, David Duce. 482-485 [doi]
• Bootstrapping for speaker recognitionWalter D. Andrews, Joseph P. Campbell, Douglas A. Reynolds. 483-486 [doi]
• Robust speech recognition via modeling spectral coefficients with HMM s with complex Gaussian componentsWilliam J. J. Roberts, Sadaoki Furui. 484-487 [doi]
• CASS: a phonetically transcribed corpus of mandarin spontaneous speechAijun Li, Fang Zheng, William Byrne, Pascale Fung, Terri Kamm, Yi Liu, Zhanjiang Song, Umar Ruhi, Veera Venkataramani, Xiaoxia Chen. 485-488 [doi]
• Grammar partitioning and parser composition for natural language understandingPo-Chui Luk, Helen M. Meng, Filung Wang. 486-489 [doi]
• On the importance of components of the MFCC in speech and speaker recognitionBin Zhen, Xihong Wu, Zhimin Liu, Huisheng Chi. 487-490 [doi]
• Pronunciation variation in ASR: which variation to model?Mirjam Wester, Judith M. Kessens, Helmer Strik. 488-491 [doi]
• Multiple decision-tree strategy for input-error robustness: a simulation of tree combinationsKazuhide Yamamoto, Eiichiro Sumita. 489-492 [doi]
• Comprehension of synthesized speech while driving and in the labJennifer Lai, Omer Tsimhoni, Paul Green. 490-493 [doi]
• On the influence of rate, pitch, and spectrum on automatic speaker recognition performanceThomas F. Quatieri, Robert B. Dunn, Douglas A. Reynolds. 491-494 [doi]
• The use of dynamic reliability scoring in speech recognitionXiaolong Mou, Victor Zue. 492-495 [doi]
• Discriminative training on language modelZheng Chen, Kai-Fu Lee, Mingjing Li. 493-496 [doi]
• Orthographic influences on initial phoneme addition and deletion tasks: the effect of lexical statusMichael D. Tyler, Denis K. Burnham. 494-497 [doi]
• A model-based transformational approach to robust speaker recognitionRemco Teunen, Ben Shahshahani, Larry P. Heck. 495-498 [doi]
• Acoustical and lexical based confidence measures for a very large vocabulary telephone speech hypothesis-verification systemJavier Macías Guarasa, Javier Ferreiros, Rubén San Segundo, Juan Manuel Montero, Juan Manuel Pardo. 496-499 [doi]
• N-gram distribution based language model adaptationJianfeng Gao, Mingjing Li, Kai-Fu Lee. 497-500 [doi]
• Investigation of analysis and synthesis parameters of straight by subjective evaluationParham Zolfaghari, Yoshinori Atake, Kiyohiro Shikano, Hideki Kawahara. 498-501 [doi]
• Contrastive lateral clicks and variation in click typesAmanda Miller-Ockhuizen, Bonny E. Sands. 499-502 [doi]
• Phone-duration-based confidence measures for embedded applicationsSilke Goronzy, Krzysztof Marasek, Ralf Kompe, Andreas Haag. 500-503 [doi]
• Towards a common phone alphabet for multilingual speech recognitionFrancisco Palou, P. Bravetti, O. Emam, Volker Fischer, Eric Janke. 501-504 [doi]
• Cross-domain classification using generalized domain actsAndrew N. Pargellis, Alexandros Potamianos. 502-505 [doi]
• Analysis of acoustic models trained on a large-scale Japanese speech databaseTomoko Matsui, Masaki Naito, Yoshinori Sagisaka, Kozo Okuda, Satoshi Nakamura. 503-506 [doi]
• Hybrid SVM/HMM architectures for speech recognitionAravind Ganapathiraju, Jonathan Hamaker, Joseph Picone. 504-507 [doi]
• What²s next: a case study in the multidimensionality of a dialog systemRobert Belvin, Ron Burns, Cheryl Hein. 504-507 [doi]
• Hierarchical feature-based translation for scalable natural language understandingGanesh N. Ramaswamy, Jan Kleindienst. 506-509 [doi]
• Farsi vowel compensatory lengthening: an experimental approachMahmood Bijankhan. 507-510 [doi]
• Rapid adaptation of n-gram language models using inter-word correlation for speech recognitionKoki Sasaki, Hui Jiang, Keikichi Hirose. 508-511 [doi]
• A new dialogue control method based on human listening process to construct an interface for ascertaining a user²s inputsMasanobu Higashida, Kumiko Ohmori. 508-511 [doi]
• Statistical recursive finite state machine parsing for speech understandingAlexandros Potamianos, Hong-Kwang Jeff Kuo. 510-513 [doi]
• Cortical reorganization associated with the acquisition of Mandarin tones by american learners: an FMRI studyYue Wang, Joan A. Sereno, Allard Jongman, Joy Hirsch. 511-514 [doi]
• Class-based language model adaptation using mixtures of word-class weightsGareth Moore, Steve Young. 512-515 [doi]
• Speaker change detection using minimum message length criterionChaojun Liu, YongHong Yan. 514-517 [doi]
• The production of real and non-words in adult stutterers and non-stutterers: an acoustic studySandra P. Whiteside, Rosemary A. Varley, T. Phillips, H. Garety. 515-518 [doi]
• Statistical methods for topic segmentationSatya Dharanipragada, Martin Franz, J. Scott McCarley, Kishore Papineni, Salim Roukos, Todd Ward, Wei-Jing Zhu. 516-519 [doi]
• A language model adaptation approach based on text classificationJiasong Sun, Xiaodong Cui, Zuoying Wang, Yang Liu. 516-519 [doi]
• Toward the realization of spontaneous speech recognition - introduction of a Japanese priority program and preliminary results -Sadaoki Furui, Kikuo Maekawa, Hitoshi Isahara, Takahiro Shinozaki, Takashi Ohdaira. 518-521 [doi]
• A new proposal of laryngeal features for the tonal system of VietnameseMasaaki Shimizu, Masatake Dantsuji. 519-522 [doi]
• Automatically incorporating unknown words in JUPITERGrace Chung. 520-523 [doi]
• Retrieval of mandarin broadcast news using spoken queriesBerlin Chen, Hsin-Min Wang, Lin-Shan Lee. 520-523 [doi]
• A comparative study on acoustic and linguistic characteristics using speech from human-to-human and human-to-machine conversationsToshiyuki Takezawa, Fumiaki Sugaya, Masaki Naito, Seiichi Yamamoto. 522-525 [doi]
• How to choose training set for language modelingHong Zhang, Bo Xu, Taiyi Huang. 523-526 [doi]
• CU-move : robust speech processing for in-vehicle speech systemsJohn H. L. Hansen, Jay P. Plucienkowski, Stephen Gallant, Bryan L. Pellom, Wayne Ward. 524-527 [doi]
• Look-ahead sequential feature vector normalization for noisy speech recognitionRathinavelu Chengalvarayan. 524-527 [doi]
• Speaker dependent temporal constraints combined with speaker independent HMM for speech recognition in noiseNéstor Becerra Yoma. 526-529 [doi]
• High performance general purpose phonetic recognition for ItalianPiero Cosi, John-Paul Hosom. 527-530 [doi]
• A rule-based named entity recognition system for speech inputJi-Hwan Kim, Philip C. Woodland. 528-531 [doi]
• Speaker adaptation in noisy environments based on parameter estimation using uncertain dataNaoto Iwahashi, Akihiko Kawasaki. 528-531 [doi]
• Forward masking on a generalized logarithmic scale for robust speech recognitionYoshihiro Ito, Hiroshi Matsumoto, Kazumasa Yamamoto. 530-533 [doi]
• First approach to the selection of lexical units for continuous speech recognition of BasqueMiren Karmele López de Ipiña, Inés Torres, Lourdes Oñederra, Amparo Varona, N. Ezeiza, Mikel Peñagarikano, M. Hernandez, Luis Javier Rodríguez. 531-534 [doi]
• A rule-based approach to farsi language text-to-phoneme conversionMohammad Reza Sadigh, Hamid Sheikhzadeh, M. R. Jahangir, Arash Farzan. 532-535 [doi]
• Speech/noise separation using two microphones and a VQ model of speech signalsAlex Acero, Steven Altschuler, Lani Wu. 532-535 [doi]
• Noise robustness of heterogeneous features employing minimum classification error feature space transformationsHeidi Christensen, Børge Lindberg, Ove Andersen. 534-537 [doi]
• Assimilation, ambiguity, and the feature parsing problemDavid W. Gow Jr.. 535-538 [doi]
• Using maximum likelihood linear regression for segment clustering and speaker identificationMichiel Bacchiani. 536-539 [doi]
• Acoustic and perceptual properties of English fricativesAllard Jongman, Yue Wang, Joan Sereno. 536-539 [doi]
• Classifier-based mask estimation for missing feature methods of robust speech recognitionMichael L. Seltzer, Bhiksha Raj, Richard M. Stern. 538-541 [doi]
• Optimization of units for continuous-digit recognition taskSachin S. Kajarekar, Hynek Hermansky. 539-542 [doi]
• Structural maximum a-posteriori linear regression for unsupervised speaker adaptationTor André Myrvoll, Olivier Siohan, Chin-Hui Lee, Wu Chou. 540-543 [doi]
• The special phonological characteristics of monosyllabic function words in EnglishStefanie Shattuck-Hufnagel, Nanette Veilleux. 540-543 [doi]
• Optimized subspace weighting for robust speech recognition in additive noise environmentsKris Hermus, Werner Verhelst, Patrick Wambacq. 542-545 [doi]
• Perceptual features for the identification of Romance languagesIoana Vasilescu, François Pellegrino, Jean-Marie Hombert. 543-546 [doi]
• Selection of sublexical units for continuous speech recognition of basqueKarmele López de Ipiña, Inés Torres, Lourdes Oñederra, Amparo Varona, Luis Javier Rodríguez. 544-547 [doi]
• Transformation-based Bayesian predictive classification for online environmental learning and robust speech recognitionJen-Tzung Chien, Guo-Hong Liao. 544-547 [doi]
• Robust feature selection using probabilistic union modelsJi Ming, Peter Jancovic, Philip Hanna, Darryl Stewart, F. Jack Smith. 546-549 [doi]
• Perception of Swedish vowel quantity: tracing late stages of developmentDawn M. Behne, Peter E. Czigler, Kirk P. H. Sullivan. 547-550 [doi]
• Machine learning techniques for the identification of cues for stop placeMadelaine Plauché, M. Kemal Sönmez. 548-551 [doi]
• Improved MLLR speaker adaptation using confidence measures for conversational speech recognitionMichael Pitz, Frank Wessel, Hermann Ney. 548-551 [doi]
• Multi-resolution front-end for noise robust speech recognitionRamalingam Hariharan, Imre Kiss, Olli Viikki, Jilei Tian. 550-553 [doi]
• Statistically trained orthographic to sound models for ThaiAnanlada Chotimongkol, Alan W. Black. 551-554 [doi]
• Strategies of vowel reduction - a speaker-dependent phenomenonChristina Widera. 552-555 [doi]
• Unified acoustic modeling for continuous speech recognitionRathinavelu Chengalvarayan. 552-555 [doi]
• Recognition of digit strings in noisy speech with limited resourcesDouglas D. O Shaughnessy, Marcel Gabrea. 554-557 [doi]
• Speech timing patterning as an indicator of discourse and syntactic boundariesJanice Fon, Keith Johnson. 555-558 [doi]
• A nonlinear unsupervised adaptation technique for speech recognitionSatya Dharanipragada, Mukund Padmanabhan. 556-559 [doi]
• Factors affecting native Japanese speakers production of intrusive (epenthetic) vowels in English wordsKeiichi Tajima, Donna Erickson, Kyoko Nagao. 558-561 [doi]
• On the phonetics of geminates: evidence from Cypriot GreekAmalia Arvaniti, Georgios Tserdanelis. 559-562 [doi]
• Using class weighting in inter-class MLLRSam-joo Doh, Richard M. Stern. 560-563 [doi]
• Meaning extraction based on frame representation for Japanese spoken dialogueAkira Kurematsu, Takeaki Nakazaki. 560-563 [doi]
• Beyond the conventional statistical language models: the variable-length sequences approachImed Zitouni, Kamel Smaïli, Jean-Paul Haton. 562-565 [doi]
• A simple procedure to clarify the relation between text and prosodyHanny den Ouden, Carel van Wijk, Marc Swerts. 563-566 [doi]
• Burst detection based on measurements of intensity discriminationJohn-Paul Hosom, Ronald A. Cole. 564-567 [doi]
• Pitch accents, boundary tones and turn-taking in dutch map task dialoguesJohanneke Caspers. 565-568 [doi]
• Computer-assisted English vowel learning system for Japanese speakers using cross language formant structuresYasushi Tsubota, Masatake Dantsuji, Tatsuya Kawahara. 566-569 [doi]
• Effects of consonantal voicing on English diphthongs: a comparison of L1 and L2 productionKimiko Tsukada. 567-570 [doi]
• Using acoustic condition clustering to improve acoustic change detection on broadcast newsJavier Ferreiros López, Daniel P. W. Ellis. 568-571 [doi]
• An annotation scheme of spoken dialogues with topic break indexesYoichi Yamashita, Michiyo Murai. 569-572 [doi]
• ASR-based subtitling of live TV-programs for the hearing impairedTrym Holter, Erik Harborg, Magne Hallstein Johnsen, Torbjørn Svendsen. 570-573 [doi]
• The challenge of non-lexical speech soundsNigel Ward. 571-574 [doi]
• Phone transition acoustic modeling: application to speaker independent and spontaneous speech systemsJon P. Nedel, Rita Singh, Richard M. Stern. 572-575 [doi]
• Application of the centering framework in spontaneous dialoguesNanette Veilleux. 573-576 [doi]
• Natural language processing for Taiwanese sign language to speech conversionChung-Hsien Wu, Yu-Hsien Chiu, Chi-Shiang Guo. 574-577 [doi]
• A method to synthesize Arabic from short phoneticYousif A. El-Imam. 575-578 [doi]
• The measurement of acoustic similarity and its applicationsLiqin Shen, Guokang Fu, Haixin Chai, Yong Qin. 576-579 [doi]
• Automatic lexicon generation and dialogue modeling for spontaneous speechHiroki Mori, Hideki Kasuya. 577-580 [doi]
• Japanese spoken language learning system using java information technologyJouji Miwa, Hiroshi Sasaki, Kazunori Tanno. 578-581 [doi]
• A brazilian portuguese language corpus developmentMauricio C. Schramm, Luis Felipe R. Freitas, Adriano Zanuz, Dante Barone. 579-582 [doi]
• Glottal parameters contributing to the perceotion of loud voicesSopae Yi, Hyung Soon Kim, One Good Lee. 580-583 [doi]
• Evaluating radio news intonation - autosegmental versus superpositional modellingMaria Wolters, Hansjörg Mixdorff. 581-584 [doi]
• L2 pronunciation quality in read and spontaneous speechHelmer Strik, Catia Cucchiarini, Diana Binnenpoorte. 582-585 [doi]
• Visual lipreading of voicing for French stop consonantsC. Colin, Monique Radeau, Didier Demolin, Alain Soquet. 583-586 [doi]
• Grapheme based speech recognition for large vocabulariesChristoph Schillo, Gernot A. Fink, Franz Kummert. 584-587 [doi]
• A mixed language model for a dialogue system over ihe telephoneDaniele Falavigna, Roberto Gretter, Marco Orlandi. 585-588 [doi]
• Designing modulation filters for improving speech intelligibility in reverberant environmentsTomoko Kitamura, Keisuke Kinoshita, Takayuki Arai, Akiko Kusumoto, Yuji Murahara. 586-589 [doi]
• Acoustic features of vowel production in Mandarin speakers of EnglishYang Chen, Michael Robb. 587-590 [doi]
• Automatic subword unit refinement for spontaneous speech recognition via phone splittingJon P. Nedel, Rita Singh, Richard M. Stern. 588-591 [doi]
• Positive and negative user feedback in a spoken dialogue corpusLinda Bell, Joakim Gustafson. 589-592 [doi]
• An environment model-based robust speech recognitionLei Zhang, Jiqing Han, Chengguo Lv, Chengfa Wang. 590-593 [doi]
• Spoken language navigation systems for driversRobert Belvin, Ron Burns, Cheryl Hein. 591-594 [doi]
• Stress and lexical activation in dutchAnne Cutler, Mariëtte Koster. 593-596 [doi]
• Particle filtering for non-stationary speech modelling and enhancementJaco Vermaak, Christophe Andrieu, Arnaud Doucet. 594-597 [doi]
• An approach to intelligent Chinese dialogue systemFang Chen, Baozong Yuan. 595-598 [doi]
• A vocal tract area ratio estimation from spectral parameter extracted by straightMamoru Iwaki. 596-599 [doi]
• Automatic modeling and implementation of intonation for the arabic language in TTS systemsSafa Nasser Eldin, Hanna Abdel Nour, Rajouani Abdenbi. 597-600 [doi]
• Maximum likelihood noise HMMm estimation in model-based robust speech recognitionMartin Graciarena. 598-601 [doi]
• Goal-oriented table-driven design for dialogue managerHuei-Ming Wang, Yi-Chung Lin. 599-602 [doi]
• Decision tree based rate of speech modeling for speech recognitionBhuvana Ramabhadran, Yuqing Gao. 600-603 [doi]
• Modeling word durationsVenkata Ramana Rao Gadde. 601-604 [doi]
• Microphone array within a handset or face mask for speech enhancementQingsheng Zeng, Douglas D. O Shaughnessy. 602-605 [doi]
• Dialogue management in the Bell Labs communicator systemAlexandros Potamianos, Egbert Ammicht, Hong-Kwang Jeff Kuo. 603-606 [doi]
• Spectral peak tracking and its use in speech recognitionMukund Padmanabhan. 604-607 [doi]
• Japanese intonation synthesis using superposition and linear alignment modelsJennifer J. Venditti, Jan P. H. van Santen. 605-608 [doi]
• Embedding visually recognizable watermarks into digital audio signalsChengfa Wang, Qiusheng Wang. 606-609 [doi]
• Dialogue management based on a hierarchical task structureJiang Han, Yong Wang. 607-610 [doi]
• Weighted pairwise scatter to improve linear discriminant analysisYongxin Li, Yuqing Gao, Hakan Erdogan. 608-611 [doi]
• Improving the naturalness of synthetic speech by utilizing the prosody of natural speechToshimitsu Minowa, Ryo Mochizuki, Hirofumi Nishimura. 609-612 [doi]
• Auditory perception of amplitude modulated sinusoid using a pure tone and band-limited noises as modulation signalsMamoru Iwaki. 610-613 [doi]
• Melodic characteristics of backchannels in Dutch map task dialoguesJohanneke Caspers. 611-614 [doi]
• ARTIC: a new Czech text-to-speech system using statistical approach to speech segment database constructionJindrich Matousek, Josef Psutka. 612-615 [doi]
• A hybrid statistical/RNN approach to prosody synthesis for taiwanese TTSSin-Horng Chen, Chen-Chung Ho. 613-616 [doi]
• Spectral voice conversion based on unsupervised clustering of acoustic spaceMasoud Geravanchizadeh. 614-617 [doi]
• Corrections in spoken dialogue systemsMarc Swerts, Diane J. Litman, Julia Hirschberg. 615-618 [doi]
• Extended maximum a posterior linear regression (EMAPLR) model adaptation for speech recognitionWu Chou, Olivier Siohan, Tor André Myrvoll, Chin-Hui Lee. 616-619 [doi]
• Performance comparison among HMM, DTW, and human abilities in terms of identifying stress patterns of word utterancesNobuaki Minematsu, Yukiko Fujisawa, Seiichi Nakagawa. 617-620 [doi]
• Removing hum from spoken language resourcesHartmut R. Pfitzinger. 618-621 [doi]
• F::0:: correlates of topic and subject in spontaneous Japanese speechJohn Fry. 619-622 [doi]
• Thai monophthong recognition using continuous density hidden Markov model and LPC cepstral coefficientsEkkarit Maneenoi, Somchai Jitapunkul, Visarut Ahkuputra, Umavasee Thathong, Boonchai Thampanitchawong, Sudaporn Luksaneeyanawin. 620-623 [doi]
• Restricted-domain female-voice synthesis in Spanish: from database design to ANN prosodic modelingJuan Manuel Montero, Ricardo de Córdoba, José A. Vallejo, Juana M. Gutiérrez-Arriola, Emilia Enríquez, Juan Manuel Pardo. 621-624 [doi]
• Joint pronunciation modelling of non-native speakers using data-driven methodsIngunn Amdal, Filipp Korkmazskiy, Arun C. Surendran. 622-625 [doi]
• Specification of communicative acts of utterances based on dialogue corpus analysisMutsuko Tomokiyo, Solange Hollard. 623-627 [doi]
• Error recovery and sentence verification using statistical partial pattern tree for conversational speechChung-Hsien Wu, Yeou-Jiunn Chen, Cher-Yao Yang. 624-627 [doi]
• A hierarchical intonation model for synthesising F0 contours in galician languageXavier Fernández Salgado, Eduardo Rodríguez Banga. 625-628 [doi]
• A comparison of disfluency distribution in a unimodal and a multimodal speech interfaceLinda Bell, Robert Eklund, Joakim Gustafson. 626-629 [doi]
• An experimental verification of the prosodic/lexical effects on the occurrence of backchannelsHiroaki Noguchi, Yasuhiro Katagiri, Yasuharu Den. 628-631 [doi]
• Features for F0 contour predictionTed H. Applebaum, Nick Kibre, Steve Pearson. 629-632 [doi]
• Modelling pronunciation variations in spontaneous Mandarin speechYi Liu, Pascale Fung. 630-633 [doi]
• The acoustic characteristics of Japanese identical vowel sequences in connected speechTsutomu Sato, John A. Maidment. 632-635 [doi]
• Rival training: efficient use of data in discriminative trainingCarsten Meyer, Georg Rose. 632-635 [doi]
• Prosodic variation of focused syllables of disyllabic word in Mandarin ChineseZhenglai Gu, Hiroki Mori, Hideki Kasuya. 633-636 [doi]
• A method of generating English pronunciation dictionary for Japanese English recognition systemsTadashi Suzuki, Jun Ishii, Kunio Nakajima. 634-637 [doi]
• Effects of dialog initiative and multi-modal presentation strategies on large directory information accessShrikanth Narayanan, Giuseppe Di Fabbrizio, Candace A. Kamm, James Hubbell, Bruce Buntschuh, P. Ruscitti, Jerry H. Wright. 636-639 [doi]
• Nasal detection module for a knowledge-based speech recognition systemMarilyn Y. Chen. 636-639 [doi]
• Automatic head gesture learning and synthesis from prosodic cuesStephen M. Chu, Thomas S. Huang. 637-640 [doi]
• A framework for evaluating contextual understandingHélène Bonneau-Maynard, Laurence Devillers. 638-641 [doi]
• Semi-continuous segmental probability model for speech signalsJun Liu, Xiaoyan Zhu, Bin Jia. 640-643 [doi]
• A declarative framework for building compositional dialog modulesWilliam Thompson, Harry Bliss. 640-643 [doi]
• Measuring the importance of morphological information for finnish speech synthesisMartti Vainio, Toomas Altosaar, Stefan Werner. 641-644 [doi]
• Towards high performance continuous Mandarin digit string recognitionYonggang Deng, Taiyi Huang, Bo Xu. 642-645 [doi]
• A plan-based dialog system with probabilistic inferencesKuansan Wang. 644-647 [doi]
• Cross-domain robust acoustic trainingEa-Ee Jan, Jaime Botella Ordinas. 644-647 [doi]
• Learning the parameters of quantitative prosody modelsOliver Jokisch, Hansjörg Mixdorff, Hans Kruschke, Ulrich Kordon. 645-648 [doi]
• Stochastic suprasegmentals: relationships between redundancy, prosodic structure and care of articulation in spontaneous speechMatthew P. Aylett. 646-649 [doi]
• Generating effective confirmation and guidance using two-level confidence measures for dialogue systemsKazunori Komatani, Tatsuya Kawahara. 648 [doi]
• A c/v segmentation method for Mandarin speech based on multiscale fractal dimensionFan Wang, Fang Zheng, Wenhu Wu. 648-651 [doi]
• A method for automatic extraction of parameters of the fundamental frequency contourShuichi Narusawa, Hiroya Fujisaki, Sumio Ohno. 649-652 [doi]
• An automatic pitch-marking method using wavelet transformMasaharu Sakamoto, Takashi Saitoh. 650-653 [doi]
• Intelligent barge-in in conversational systemsNikko Ström, Stephanie Seneff. 652-655 [doi]
• An application of SAMPA-c for standard ChineseXiaoxia Chen, Aijun Li, Guohua Sun, Wu Hua, Zhigang Yu. 652-655 [doi]
• Recognition of emotional states using voice, face image and thermal image of faceTetsuro Kitazoe, Sung-Ill Kim, Yasunari Yoshitomi, Tatsuhiko Ikeda. 653-656 [doi]
• A proposal of a model to extract Japanese voluntary speech rate controlKeiichi Takamaru, Makoto Hiroshige, Kenji Araki, Koji Tochinai. 654-657 [doi]
• A system for the research into multi-modal man-machine communication within a virtual environmentAndrew P. Breen, Barry Eggleton, Gavin Churcher, Paul Deans, Simon Downey. 656-659 [doi]
• Joint speech signal enhancement based on spectral subtraction and SVD filterWenkai Lu, Xuegong Zhang, Yanda Li, Shen Liqin, Zhu Weibin. 656-659 [doi]
• Turn taking and multimodal information in two-people dialogKeiko Watanuki, Susumu Seki, Hideo Miyoshi. 657-660 [doi]
• Acoustic characteristics of surprise in Russian questionsVeronika Makarova. 658-661 [doi]
• Advances in automatic transcription of Italian broadcast newsFabio Brugnara, Mauro Cettolo, Marcello Federico, Diego Giuliani. 660-663 [doi]
• Inverse lattice filtering of speech with adapted non-uniform delaysSacha Krstulovic, Frédéric Bimbot. 660-663 [doi]
• Implementation of a text-to-speech system for farsi languageHamid Reza Abutalebi, Mahmood Bijankhan. 661-664 [doi]
• Neural network based integration of multiple confidence measures for OOV detectionYonggang Deng, Yang Cao, Bo Xu. 662-665 [doi]
• Live thesaurus construction for interactive voice-based web searchShui-Lung Chuang, Hsiao-Tieh Pu, Wen-Hsiang Lu, Lee-Feng Chien. 664-667 [doi]
• Accurate vocal event detection method based on a fixed-point analysis of mapping from time to weighted average group delayHideki Kawahara, Yoshinori Atake, Parham Zolfaghari. 664-667 [doi]
• Recognition of emotion in a realistic dialogue scenarioRichard Huber, Anton Batliner, Jan Buckow, Elmar Nöth, Volker Warnke, Heinrich Niemann. 665-668 [doi]
• How fast can we really change pitch? maximum speed of pitch change revisitedYi Xu, Xuejing Sun. 666-669 [doi]
• Filterbank-based feature extraction for speech recognition and its application to voice mail transcriptionJun Huang, Mukund Padmanabhan. 668-671 [doi]
• Selecting TV news stories and newswire articles related to a target article of newswire using SVMYoshimi Suzuki, Fumiyo Fukumoto, Yoshihiro Sekiguchi. 668-671 [doi]
• Differentiation in tone production in cantonese-speaking hearing-impaired childrenJohanna Barry, Peter J. Blamey, Kathy Lee, Dilys Cheung. 669-672 [doi]
• Predicting segmental durations for Dutch using the sums-of-products approachEsther Klabbers, Jan P. H. van Santen. 670-673 [doi]
• A cepstrum-based harmonics-to-noise ratio in voice signalsPeter J. Murphy. 672-675 [doi]
• Towards an integrated approach for spoken document retrievalKenney Ng. 672-675 [doi]
• Learning effects for phonetic properties of synthetic speechMartine van Zundert, Jacques M. B. Terken. 673-676 [doi]
• A stochastic polynomial tone model for continuous Mandarin speechYang Cao, Taiyi Huang, Bo Xu, Chengrong Li. 674-677 [doi]
• An experimental study of an audio indexing system for the webBeth Logan, Pedro J. Moreno, Jean-Manuel Van Thong, Edward W. D. Whittaker. 676-679 [doi]
• A pitch determination algorithm based on subharmonic-to-harmonic ratioXuejing Sun. 676-679 [doi]
• An empirical study of the effectiveness of speech-recognition-based pronunciation trainingLaura Mayfield Tomokiyo, Le Wang, Maxine Eskenazi. 677-680 [doi]
• Detection of filled pauses in spontaneous conversational speechMarcel Gabrea, Douglas D. O Shaughnessy. 678-681 [doi]
• Source separation techniques applied to speech linear predictionJordi Solé i Casals, Enric Monte-Moreno, Christian Jutten, Anisse Taleb. 680-683 [doi]
• Title generation for spoken broadcast news using a training corpusRong Jin, Alexander G. Hauptmann. 680-683 [doi]
• Automatic detection of mispronounced phonemes for language learning toolsOlivier Deroo, Christophe Ris, Sofie Gielen, Johan Vanparys. 681-684 [doi]
• Some observations on different strategies for the timing of fundamental frequency eventsBertil Lyberg, Sonia Sangarig. 682-685 [doi]
• Model based voice decomposition methodMasahide Sugiyama. 684-687 [doi]
• Evaluating different information retrieval algorithms on real-world dataManfred Weber, Thomas Kemp. 684-687 [doi]
• Estimation of duration models for phonemes in m exican speech synthesisHoracio Meza Escalona, Ingrid Kirschning, Ofelia Cervantes Villagómez. 685-688 [doi]
• Research on dynamic characters of Chinese pitch contoursZhiyong Wu, Lianhong Cai, Tongchun Zhou. 686-689 [doi]
• A time-varying complex speech analysis based on IV methodKeiichi Funaki. 688-691 [doi]
• Transcription and summarization of voicemail speechKonstantinos Koumpis, Steve Renals. 688-691 [doi]
• Special text processing based external descriptor ruleXiaoru Wu, Ren-Hua Wang, Guoping Hu. 689-692 [doi]
• Incorporating HMM-state sequence confusion for rapid MLLR adaptation to new speakersBing Zhao, Bo Xu. 690-693 [doi]
• Robust rejection for embedded systemsW. C. Tsai, Y. C. Chu. 692-695 [doi]
• A sinusoidal model based on frequency-to-instantaneous frequency mappingParham Zolfaghari, Hideki Kawahara. 692-695 [doi]
• Articulatory synthesis using a vocal-tract model of variable lengthZhenli Yu, Shangcui Zeng. 693-696 [doi]
• An online incremental speaker adaptation method using speaker-clustered initial modelsZhipeng Zhang, Sadaoki Furui. 694-697 [doi]
• Multimodal signal processing in naturalistic noisy environmentsSharon L. Oviatt. 696-699 [doi]
• Dynamic feature extraction by wavelet analysisOmar Farooq, Sekharjit Datta. 696-699 [doi]
• Linguistic-prosodic processing for text-to-speech synthesis in italianPhilippe Boula de Mareüil. 697-700 [doi]
• Prior parameter transformation for unsupervised speaker adaptationGuoqiang Li, Limin Du, Ziqiang Hou. 698-701 [doi]
• A multi-modal dialog system for business transactionsJoyce Yue Chai, Sylvie Levesque, Malgorzata Budzikowska, Veronika Horvath, Nanda Kambhatla, Nicolas Nicolov, Wlodek Zadrozny. 700-703 [doi]
• An investigation of variable block length methods for calculation of spectral/temporal features for automatic speech recognitionMontri Karnjanadecha, Stephen A. Zahorian. 700-703 [doi]
• A unified approach for speech synthesis and speech recognition using stochastic Markov graphsMatthias Eichner, Matthias Wolff, Rüdiger Hoffmann. 701-704 [doi]
• Improved Jacobian adaptation for fast acoustic model adaptation in noisy speech recognitionRuhi Sarikaya, John H. L. Hansen. 702-705 [doi]
• Office message center - a spoken dialogue systemJiang Han, YongHong Yan, Zhiwei Lin, Yong Wang, Jian Liu, Danjun Liu, Zhihui Wang. 704-706 [doi]
• Glottal excitation modeling using HMM with application to robust analysis of speech signalAkira Sasou, Kazuyo Tanaka. 704-707 [doi]
• Using F0 within a phonologically motivated method of unit selectionAndrew P. Breen, James Salter. 705-708 [doi]
• A study of vocal tract length normalization with generation-dependent acoustic modelsKeiko Fujita, Yoshio Ono, Yoshihisa Nakatoh. 706-709 [doi]
• A new method for understanding sequences of utterances by multiple speakersNoboru Miyazaki, Jun-ichi Hirasawa, Mikio Nakano, Kiyoaki Aikawa. 707-710 [doi]
• Automatic segmentation of speech based on hidden Markov models and acoustic featuresLaura Docío Fernández, Carmen García-Mateo. 708-711 [doi]
• Analysis of the degradation of French vowels induced by the TD-PSOLA algorithm, in text-to-speech contextChristophe Blouin, Paul C. Bagshaw. 709-712 [doi]
• Optimal on-line Bayesian model selection for speaker adaptationShaojun Wang, Yunxin Zhao. 710-713 [doi]
• Improvement of dialogue efficiency by dialogue control model according to performance of processesHideaki Kikuchi, Katsuhiko Shirai. 711-714 [doi]
• VERBMOBIL dialogues: multifaced analysisAkira Kurematsu, Youichi Akegami, Susanne Burger, Susanne Jekat, Brigitte Lause, Victoria MacLaren, Daniela Oppermann, Tanja Schultz. 712-715 [doi]
• Automatic construction of acoustic inventory for the concatenative speech synthesis for polishArtur Janicki. 713-716 [doi]
• Unsupervised audio stream segmentation and clustering via the Bayesian information criterionBowen Zhou, John H. L. Hansen. 714-717 [doi]
• MUXING: a telephone-access Mandarin conversational systemChao Wang, D. Scott Cyphers, Xiaolong Mou, Joseph Polifroni, Stephanie Seneff, J. Yi, Victor Zue. 715-718 [doi]
• A computation-efficient parameter adaptation algorithm for the generalized spectral subtraction methodJin-Jie Zhang, Zhi-Gang Cao, Zheng-Xin Ma. 716-719 [doi]
• Universal and multilingual unit selection for DRESSDiane Hirschfeld, Matthias Wolff. 717-720 [doi]
• Frame-period adaptation for speaking rate robust speech recognitionSatoru Tsuge, Toshiaki Fukada, Kenji Kita. 718-721 [doi]
• Jaspis - a framework for multilingual adaptive speech applicationsMarkku Turunen, Jaakko Hakulinen. 719-722 [doi]
• A semantic tagging tool for spoken dialogue corpusMasahiro Araki, Kiyoshi Ueda, Takuya Nishimoto, Yasuhisa Niimi. 720-723 [doi]
• Improving speech synthesis for high intelligibility under adverse conditionsDavis Pan, Brian Heng, Shiufun Cheung, Ed Chang. 721-724 [doi]
• Cross-language use of acoustic information for automatic speech recognitionC. Nieuwoudt, Elizabeth C. Botha. 722-725 [doi]
• The CU communicator: an architecture for dialogue systemsBryan L. Pellom, Wayne Ward, Sameer Pradhan. 723-726 [doi]
• The phonetic labeling on read and spontaneous discourse corporaAijun Li, Xiaoxia Chen, Guohua Sun, Wu Hua, Zhigang Yin, Yiqing Zu, Fang Zheng, Zhanjiang Song. 724-727 [doi]
• Development of a formant-based analysis-synthesis system and generation of high quality liquid sounds of JapaneseNobuyuki Nishizawa, Nobuaki Minematsu, Keikichi Hirose. 725-728 [doi]
• Selective training of HMMs by using two-stage clusteringShoei Sato, Toru Imai, Hideki Tanaka, Akio Ando. 726-729 [doi]
• Preferred modalities in dialogue systemsVildan Bilici, Emiel Krahmer, Saskia te Riele, Raymond N. J. Veldhuis. 727-730 [doi]
• The quality of multilingual automatic segmentation using German MAUSNicole Beringer, Florian Schiel. 728-731 [doi]
• Synthesizing and evaluating an artificial language: klingonOliver Jokisch, Matthias Eichner. 729-732 [doi]
• Compensation of noise effects for robust speech recognition in car environmentsÁngel de la Torre, Dominique Fohr, Jean-Paul Haton. 730-733 [doi]
• Introduction to the IST-HLT project speech-driven multimodal automatic directory assistance (SMADA)Frédéric Béchet, Elisabeth den Os, Lou Boves, Jürgen Sienel. 731-734 [doi]
• UWB_S01 corpus - a czech read-speech corpusVlasta Radová, Josef Psutka. 732-735 [doi]
• Non-standard word and homograph resolution for asian language text analysisCraig Olinsky, Alan W. Black. 733-736 [doi]
• Bayesian speaker adaptation based on probabilistic principal component analysisDong Kook Kim, Nam Soo Kim. 734-737 [doi]
• Using HPSG to represent multi-modal grammar in multi-modal dialogueCrusoe Mao, Tony Tuo, Danjun Liu. 735-738 [doi]
• Web-based monitoring, logging and reporting tools for multi-service multi-modal systemsGiuseppe Di Fabbrizio, Shrikanth Narayanan. 736-739 [doi]
• Re-estimation of LPC coefficients in the sense of l&inf; criterionZhang Sen, Katsuhiko Shirai. 737-740 [doi]
• MLLR-based accent model adaptation without accented dataWai Kat Liu, Pascale Fung. 738-741 [doi]
• An efficient dialogue control method under system²s limited knowledgeKohji Dohsaka, Norihito Yasuda, Noboru Miyazaki, Mikio Nakano, Kiyoaki Aikawa. 739-742 [doi]
• Comparing the recognition performance of CSRs: in search of an adequate metric and statistical significance testHelmer Strik, Catia Cucchiarini, Judith M. Kessens. 740-743 [doi]
• An efficient codebook search algorithm for EVRCSung-Kyo Jung, Yong-Soo Choi, Young-Cheol Park, Dae Hee Youn. 741-744 [doi]
• Fast speaker adaptation using eigenspace-based maximum likelihood linear regressionKuan-Ting Chen, Wen-Wei Liau, Hsin-Min Wang, Lin-Shan Lee. 742-745 [doi]
• A distributed spoken user interface based on open agent architecture (OAA)Ying Cheng, Anurag Gupta, Raymond H. Lee. 743-746 [doi]
• Perceptual dimensions of speech sound quality in modern transmission systemsAlexander Raake. 744-747 [doi]
• The reduction of the search time by the pre-determination of the grid bit in the g.723.1 MP-MLQJong Kuk Kim, Jeong-Jin Kim, Myung Jin Bae. 745-749 [doi]
• Stream confidence estimation for audio-visual speech recognitionGerasimos Potamianos, Chalapathy Neti. 746-749 [doi]
• Bimodal speech recognition using coupled hidden Markov modelsStephen M. Chu, Thomas S. Huang. 747-750 [doi]
• Real-time telephone transmission simulation for speech recognizer and dialogue system evaluation and improvementSebastian Möller, Hervé Bourlard. 750-753 [doi]
• The effect of reduced spectral information on Japanese consonant perception: comparison between L1 and L2 listenersMasahiko Komatsu, Won Tokuma, Shinichi Tokuma, Takayuki Arai. 750-753 [doi]
• A parallel multi-stream model for sign language recognitionJiyong Ma, Wen Gao. 751-754 [doi]
• Can cantonese children with cochlear implants perceive lexical tones?Valter Ciocca, Rani Aisha, Alex Francis, Lena Wong. 754-757 [doi]
• HMM-based echo and announcement modeling approaches for noise suppression avoiding the problem of false triggersRathinavelu Chengalvarayan, David L. Thomson. 754-757 [doi]
• MOTHER: a new generation of talking heads providing a flexible articulatory control for video-realistic speech animationLionel Revéret, Gérard Bailly, Pierre Badin. 755-758 [doi]
• Speaker information enhancementFangxin Chen. 758-761 [doi]
• Recognition of spoken words in the continuous speech: effects of transitional probabilityMichael C. W. Yip. 758-761 [doi]
• Modeling visual coarticulation in synthetic talking heads using a lip motion unit inventory with concatenative synthesisSteve Minnis, Andrew P. Breen. 759-762 [doi]
• Exhaustive search for lower-bound error-rates in vocal tract length normalizationHans Dolfing. 762-765 [doi]
• Detection of speech landmarks using temporal cuesAriel Salomon, Carol Y. Espy-Wilson. 762-765 [doi]
• A generation system for Chinese textsHua Wu, Taiyi Huang, Bo Xu. 763-767 [doi]
• A set of Japanese word cohorts rated for relative familiarityTakashi Otake, Anne Cutler. 766-769 [doi]
• Use of voicing information to improve the robustness of the spectral parameter setDusan Macho, Climent Nadeu. 766-769 [doi]
• Formal and natural language generation in the Mercury conversational systemStephanie Seneff, Joseph Polifroni. 767-770 [doi]
• Residual noise compensation by a sequential EM algorithm for robust speech recognition in nonstationary noiseKaisheng Yao, Bertram E. Shi, Satoshi Nakamura, Zhigang Cao. 770-773 [doi]
• The phonetic value of the devocalized vowel in Japanese - in case of velar plosiveKimiko Yamakawa, Hiromitsu Miyazono, Ryoji Baba. 770-773 [doi]
• A method of creating a new speaker²s voicefont in a text-to-speech systemTakashi Saito, Masaharu Sakamoto. 771-774 [doi]
• Principal mixture speaker adaptation for improved continuous speech recognitionHui Ye, Pascale Fung, Taiyi Huang. 774-777 [doi]
• Signal approximation in Hilbert space and its application on articulatory speech synthesisJun Huang, Stephen E. Levinson, Mark Hasegawa-Johnson. 775-778 [doi]
• Positive and negative influences of the lexicon on phonemic decision-makingJames M. McQueen, Anne Cutler, Dennis Norris. 778-781 [doi]
• Reduced impedance mismatch in speech database accessToomas Altosaar, Martti Vainio. 778-781 [doi]
• Quality improvement of PSOLA analysis-synthesis using partial zero-phase conversionNobuaki Minematsu, Seiichi Nakagawa. 779-782 [doi]
• Internet training system for listening and pronunciation of Chinese stop consonantsJiapeng Tian, Jouji Miwa. 782-785 [doi]
• Phonotactic and acoustic cues for word segmentation in EnglishAndrea Weber. 782-785 [doi]
• A machine learning approach to Swedish word pronunciationHanna Lindgren, Jessica Granberg. 783-786 [doi]
• Identification of Japanese double-mora phonemes considering speaking rate for the use in CALL systemsCarlos Toshinori Ishi, Keikichi Hirose, Nobuaki Minematsu. 786-790 [doi]
• Intelligibility of time-compressed speech: three ways of time-compressionEsther Janse. 786-789 [doi]
• An improved speech analysis-synthesis algorithm based on the autoregressive with exogenous input speech production modelTakahiro Ohtsuka, Hideki Kasuya. 787-790 [doi]
• Evidence for demodulation in speech perceptionHartmut Traunmller. 790-793 [doi]
• Combination of temporal trajectory filtering and projection measure for robust speaker identificationKuo-Hwei Yuo, Tai-Hwei Hwang, Hsiao-Chuan Wang. 791-794 [doi]
• Fast decoding for indexation of broadcast dataJean-Luc Gauvain, Lori Lamel. 794-797 [doi]
• A combined adaptive and decision tree based speech separation technique for telemedicine applicationsYunxin Zhao, Xiao Zhang, Xiaodong He, Laura Schopp. 795-798 [doi]
• Update progress of Sinohear: advanced Mandarin LVCSR system at NLPRSheng Gao, Bo Xu, Hong Zhang, Bing Zhao, Chengrong Li, Taiyi Huang. 798-801 [doi]
• Additive and convolutional noises compensation for speaker recognitionOlivier Bellot, Driss Matrouf, Téva Merlin, Jean-François Bonastre. 799-802 [doi]
• Combined acoustic and linguistic look-ahead for one-pass time-synchronous decodingXavier L. Aubert, Reinhard Blasig. 802-805 [doi]
• Dialect adaptation for Mandarin Chinese speech recognitionFrédéric Beaugendre, Tom Claes, Hugo Van Hamme. 803-806 [doi]
• Large-vocabulary speech recognition under adverse acoustic environmentsLi Deng, Alex Acero, Mike Plumpe, Xuedong Huang. 806-809 [doi]
• Can automatic speaker verification be improved by training the algorithms on emotional speech?Klaus R. Scherer, Tom Johnstone, Gudrun Klasmeyer, Thomas Bänziger. 807-810 [doi]
• Acoustic language model classes for a large vocabulary continuous speech recognizerVolker Fischer, Siegfried Kunzmann. 810-813 [doi]
• New distance measures for text-independent speaker identificationZhong-hua Wang, Cheng Wu, David Lubensky. 811-814 [doi]
• A hybrid speech recognizer combining HMMs and polynomial classificationFranz Kummert, Gernot A. Fink, Gerhard Sagerer. 814-817 [doi]
• Automatic speech recognition in Mandarin for embedded platformsFengguang Zhao, Prabhu Raghavan, Sunil K. Gupta, Ziyi Lu, Wentao Gu. 815-818 [doi]
• Accent modeling based on pronunciation dictionary adaptation for large vocabulary Mandarin speech recognitionChao Huang, Eric Chang, Jianlai Zhou, Kai-Fu Lee. 818-821 [doi]
• Confidence measure based unsupervised speaker adaptationHusheng Li, Jia Liu, Runsheng Liu. 819-822 [doi]
• A mixed and code excitation LPC vocoder at 1.76 kb/sJinzhong Zhang, Yingmin He, Renshu Yu. 822-825 [doi]
• Improved variable preselection list length estimation using NNs in a large vocabulary telephone speech recognition systemJavier Macías Guarasa, Javier Ferreiros, José Colás, Ascensión Gallardo-Antolín, Juan Manuel Pardo. 823-826 [doi]
• Efficient segment quantization of LSP parameters for very low bit speech codingMinoru Kohata, Ikuya Mitsuya, Motoyuki Suzuki, Shozo Makino. 826-829 [doi]
• Incorporating multiple-HMM acoustic modeling in a modular large vocabulary speech recognition system in telephone environmentAscensión Gallardo-Antolín, Javier Ferreiros, Javier Macías Guarasa, Ricardo de Córdoba, Juan Manuel Pardo. 827-830 [doi]
• Phonetic vocoder assessmentCarlos M. Ribeiro, Isabel Trancoso, Diamantino Caseiro. 830-833 [doi]
• Decision tree based text-to-phoneme mapping for speech recognitionJanne Suontausta, Juha Häkkinen. 831-834 [doi]
• A new low bit rate speech coder based on intraframe waveform interpolationHongtao Hu, Limin Du. 834-837 [doi]
• Reduced traceback matrix storage for small footprint model alignmentJeff Meunier. 835-838 [doi]
• Discriminatively derived HMM-based announcement modeling approach for noise control avoiding the problem of false alarmsRathinavelu Chengalvarayan, David L. Thomson. 838-841 [doi]
• Dynamic adaptation of vocabulary independent HMMs to an application environmentClaudio Vair, Luciano Fissore, Pietro Laface. 839-842 [doi]
• Instantaneous-distortion based weighted acoustic modeling for robust recognition of coded speechJuan M. Huerta, Richard M. Stern. 842-845 [doi]
• Synergy of spectral and perceptual features in multi-source connectionist speech recognitionRoberto Gemello, Loreta Moisa, Pietro Laface. 843-846 [doi]
• High performance connected digit recognition through gender-dependent acoustic modelling and vocal tract length normalisationRamalingam Hariharan, Olli Viikki. 847-850 [doi]
• Adapting phonetic decision trees between languages for continuous speech recognitionNitendra Rajput, L. Venkata Subramaniam, Ashish Verma. 850-852 [doi]
• Transcription of broadcast news with a time constraint: IBM’s 10xRT HUB4 systemEllen Eide, Benoît Maison, Dimitri Kanevsky, Peder A. Olsen, S. S. Chen, Lidia Mangu, Mark J. F. Gales, Miroslav Novak, Ramesh A. Gopinath. 851-854 [doi]
• Speaker normalization in the MFCC domainStephen Cox. 853-856 [doi]
• Exact alpha-beta computation in logarithmic space with application to MAP word graph constructionGeoffrey Zweig, Mukund Padmanabhan. 855-858 [doi]
• Data-driven phonetic regression class tree estimation for MLLR adaptationReinhold Haeb-Umbach. 857-860 [doi]
• Relationship among speaking style, inter-phoneme s distance and speech recognition performanceKazumasa Yamamoto, Seiichi Nakagawa. 859-862 [doi]
• Constrained maximum likelihood linear regression for speaker adaptationMohamed Afify, Olivier Siohan. 861-864 [doi]
• Spanish recogniser of continuously spelled names over the telephoneRubén San Segundo, José Colás, Javier Ferreiros, Javier Macías Guarasa, Juan Miguel Pardo. 863-866 [doi]
• Predictive speaker adaptation based on least squares methodWoo-Yong Choi, Hyung Soon Kim. 865-868 [doi]
• Two-stream modeling of Mandarin tonesFrank Seide, Nick J.-C. Wang. 867-870 [doi]
• HMM adaptation using vector taylor series for noisy speech recognitionAlex Acero, Li Deng, Trausti Kristjansson, Jerry Zhang. 869-872 [doi]
• A neural network speech recognizer based on the both acoustic steady portions and transitionsSeyyed Ali Seyyed Salehi. 871-874 [doi]
• Minimum risk acoustic clustering for multilingual acoustic model combinationDimitra Vergyri, Stavros Tsakalidis, William Byrne. 873-876 [doi]
• Belief networks for a syntactic and semantic analysis of spoken utterances for speech understandingMarc Hofmann, Manfred Lang. 875-878 [doi]
• Talking to thimble jellies: children²s conversational speech with animated charactersSharon L. Oviatt. 877-880 [doi]
• A robust speech understanding system using conceptual relational grammarJiping Sun, Roberto Togneri, Li Deng. 879-882 [doi]
• A high-resolution glottal pulse trackerRobert D. Rodman, David F. McAllister, Donald L. Bitzer, D. Chappell. 881-884 [doi]
• Incorporating tone information into Cantonese large-vocabulary continuous speech recognitionWai H. Lau, Tan Lee, Yiu Wing Wong, P. C. Ching. 883-886 [doi]
• Analysis of voice production in breathy, normal and pressed phonation by comparing inverse filtering and videokymographyPaavo Alku, Jan G. Svec, Erkki Vilkman, Frantisek Sram. 885-888 [doi]
• A novel loss function for the overall risk criterion based discriminative training of HMM modelsJanez Kaiser, Bogomir Horvat, Zdravko Kacic. 887-890 [doi]
• Model of the mechanical linkage of the upper lip-jaw for the articulatory coordinationTakayuki Ito, Hiroaki Gomi, Masaaki Honda. 889-892 [doi]
• Looking for topic similarities of highly inflected languages for language model adaptationMirjam Sepesy Maucec, Zdravko Kacic, Bogomir Horvat. 891-894 [doi]
• Measurement of palatolingual contact pressure and tongue force using a force-sensor-mounted palatal plateMasafumi Matsumura, Takuya Niikawa, Taku Torii, Hitoshi Yamasaki, Hisanaga Hara, Takashi Tachimura, Takeshi Wada. 893-896 [doi]
• Integrating MAP and linear transformation for language model adaptationDavid Janiszek, Frédéric Béchet, Renato de Mori. 895-898 [doi]
• Utterance verification based speech recognition systemBeng Tiong Tan, Yong Gu, Trevor Thomas. 899-902 [doi]
• A 3d tongue model based on MRI dataOlov Engwall. 901-904 [doi]
• Use of linear extrapolation based linear predictive cepstral features (LE-LPCC) for Tamil speech recognitionRathinavelu Chengalvarayan. 903-906 [doi]
• Speech quality improvement in TTS system using ABS/OLA sinusoidal modelJae-Hyun Bae, Heo-Jin Byeon, Yung-Hwan Oh. 905-908 [doi]
• Robust fundamental frequency estimation using instantaneous frequencies of harmonic componentsYoshinori Atake, Toshio Irino, Hideki Kawahara, Jinlin Lu, Satoshi Nakamura, Kiyohiro Shikano. 907-910 [doi]
• A study of palatal segments production by danish speakersMarielle Bruyninckx, Bernard Harmegnies. 909-912 [doi]
• Integrating different acoustic and syntactic language models in a continuous speech recognition systemAmparo Varona, Inés Torres, Miren Karmele López de Ipiña, Luis Javier Rodríguez. 911-914 [doi]
• Dynamic selection of feature spaces for robust speech recognitionBhuvana Ramabhadran, Yuqing Gao, Michael Picheny. 913-916 [doi]
• Combining multiple speech recognizers using voting and language model informationHolger Schwenk, Jean-Luc Gauvain. 915-918 [doi]
• A probabilistic model of integration of acoustic cues in FV syllablesSantiago Fernández, Sergio Feijóo. 917-920 [doi]
• Dialogue management based on inferred behavioral goal - improving the accuracy of understanding by dialogue context -Keisuke Watanabe, Yasushi Ishikawa. 919-922 [doi]
• Directed graphical models of classifier combination: application to phone recognitionJeff A. Bilmes, Katrin Kirchhoff. 921 [doi]
• Speech recognition using context conditional word posterior probabilitiesRalf Schlüter, Frank Wessel, Hermann Ney. 923-926 [doi]
• Real-time multilingual HMM training robust to channel variationsEa-Ee Jan, Jaime Botella Ordinas, George Saon, Salim Roukos. 925-928 [doi]
• The use of syllable segmentation information in continuous speech recognition hybrid systems applied to the Portuguese languageHugo Meinedo, João Paulo Neto. 927-930 [doi]
• The intelligibility of German and English speech to Dutch listenersSander J. van Wijngaarden, Herman J. M. Steeneken. 929-932 [doi]
• Combination of acoustic models in continuous speech recognition hybrid systemsHugo Meinedo, João Paulo Neto. 931-934 [doi]
• On the use of bandpass liftering in speaker recognitionBin Zhen, Xihong Wu, Zhimin Liu, Huisheng Chi. 933-936 [doi]
• Automatic speech recognition of non-native speakers using consonant-vowel-consonant (CVC) wordsDavid A. van Leeuwen, Sander J. van Wijngaarden. 935-938 [doi]
• On auditory-phonetic short-term transformationRené Carré, Liliane Sprenger-Charolles, Souhila Messaoud-Galusi, Willy Serniclaes. 937-940 [doi]
• Understanding Chinese in spoken dialogue systemsGang Zhao, Hong Xu. 939-942 [doi]
• Predicting the perceptual confusion of synthetic plosive consonants in noiseJames J. Hant, Abeer Alwan. 941-944 [doi]
• A front-end using the harmonicity cue for speech enhancement in loud noiseFrédéric Berthommier, Hervé Glotin, Emmanuel Tessier. 943-946 [doi]
• Compound splitting and lexical unit recombination for improved performance of a speech recognition system for German parliamentary speechesMartha Larson, Daniel Willett, Joachim Köhler, Gerhard Rigoll. 945-948 [doi]
• Lucent automatic speech recognition: a speech recognition engine for internet and telephony srvice applicationsQiru Zhou, Sergey Kosenko. 947-950 [doi]
• Learning and transfer of learning for synthetic speechMartine van Zundert, Jacques M. B. Terken. 949-952 [doi]
• Automatic speech recognition using dynamic bayesian networks with both acoustic and articulatory variablesTodd A. Stephenson, Hervé Bourlard, Samy Bengio, Andrew C. Morris. 951-954 [doi]
• Neural plasticity revealed in perceptual training of a Japanese adult listener to learn american /l-r/ contrast: a whole-head magnetoencephalography studyYang Zhang, Patricia K. Kuhl, Toshiaki Imada, Paul Iverson, John Pruitt, Makoto Kotani, Erica Stevens. 953-956 [doi]
• Towards robust telephony speech recognition in office and automobile environmentsSubrata Das, David Lubensky. 955-958 [doi]
• The effect of consonantal context and acoustic characteristics on the discrimination between the English vowel /i/ and /e/ by Japanese learnersAkiyo Joto. 957-960 [doi]
• Extracting phonological chunks based on piecewise linear segment latticesHiroaki Kojima, Kazuyo Tanaka. 959-962 [doi]
• A study on emotional feature recognition in speechLi Zhao, Wei Lu, Ye Jiang, Zhenyang Wu. 961-964 [doi]
• Evaluating hierarchical hybrid statistical language modelsLucian Galescu, James F. Allen. 963-966 [doi]
• LPC, LPCC and MFCC parameterisation applied to the detection of voice impairmentsJuan Ignacio Godino-Llorente, Santiago Aguilera-Navarro, Pedro Gómez Vilda. 965-968 [doi]
• An efficient lexical tree search for large vocabulary continuous speech recognitionJun Ogata, Yasuo Ariki. 967-970 [doi]
• A complementary approach to computer-aided transcription: synergy of statistical-based and kbnowledge discovery paradigmsBenjamin Ka-Yin T sou, Tom B. Y. Lai. 969-972 [doi]
• Reliability evaluation of speech recognition in acoustic modelingBin Jia, Xiaoyan Zhu, Yupin Luo, Dongcheng Hu. 971-974 [doi]
• Teraspeech’2000 : a 10, 000 speakers databaseMarie-José Caraty, Claude Montacié. 973-976 [doi]
• Using GMM for voiced/voiceless segmentation and tone decision in Mandarin continuous speech recognitionChing X. Xu. 975-978 [doi]
• The MATE workbench - a tool in support of spoken dialogue annotation and information extractionLaila Dybkjær, Niels Ole Bernsen. 977-980 [doi]
• Auditory spectrum based features (ASBF) for robust speech recognitionChi H. Yim, Oscar C. Au, Wanggen Wan, Cyan L. Keung, Carrson C. Fung. 979-982 [doi]
• Discarding impossible events from statistical language modelsArmelle Brun, David Langlois, Kamel Smaïli, Jean-Paul Haton. 981-984 [doi]
• Large vocabulary Mandarin speech recognition with different approaches in modeling tonesEric Chang, Jian-Lai Zhou, Shuo Di, Chao Huang, Kai-Fu Lee. 983-986 [doi]
• A tool to build a treebank for conversational ChineseYves Lepage, Nicolas Auclerc, Satoshi Shirai. 985-988 [doi]
• Fast very large vocabulary recognition based on compact DAWG-structured language modelsKallirroi Georgila, Kyriakos N. Sgarbas, Nikos Fakotakis, George Kokkinakis. 987-990 [doi]
• Parameter reduction in a text-independent speaker verification systemRoland Auckenthaler, Michael J. Carey 0002, John Maso. 989-992 [doi]
• Crosslinguistic disfluency modeling: a comparative analysis of Swedish and tok pisin human-human ATIS dialoguesRobert Eklund. 991-994 [doi]
• Advances on HMM-based text-dependent speaker verificationYong Gu, Trevor Thomas. 993-996 [doi]
• Vector space representation of language probabilities through SVD of n-gram matrixShiro Terashima, Kazuya Takeda, Fumitada Itakura. 995-998 [doi]
• Optimisation of GMM in speaker recognitionRobert P. Stapert, John S. D. Mason, Roland Auckenthaler. 997-1000 [doi]
• Spoken language parsing based on incremental disambiguationYoshihide Kato, Shigeki Matsubara, Katsuhiko Toyama, Yasuyoshi Inagaki. 999-1002 [doi]
• Distance-based Gaussian mixture model for speaker recognition over the telephoneRan D. Zilca, Yuval Bistritz. 1001-1004 [doi]
• Jacobian adaptation of HMM with initial model selection for noisy speech recognitionHiroshi Shimodaira, Yutaka Kato, Toshihiko Akae, Mitsuru Nakai, Shigeki Sagayama. 1003-1006 [doi]
• Pruning abnormal data for better making a decision in speaker verificationJun-Hui Liu, Ke Chen. 1005-1008 [doi]
• The BBN Byblos 2000 conversational Mandarin LVCSR systemHan Shu, Chuck Wooters, Owen Kimball, Thomas Colthurst, Fred Richardson, Spyros Matsoukas, Herbert Gish. 1007-1010 [doi]
• ASR, dialects, and acoustic/phonological distancesLouis ten Bosch. 1009-1012 [doi]
• The 2000 BBN Byblos LVCSR systemThomas Colthurst, Owen Kimball, Fred Richardson, Han Shu, Chuck Wooters, Rukmini Iyer, Herbert Gish. 1011-1014 [doi]
• Speaker verification by integrating dynamic and static features using subspace methodMasafumi Nishida, Yasuo Ariki. 1013-1016 [doi]
• Broadcast news transcription in MandarinLangzhou Chen, Lori Lamel, Gilles Adda, Jean-Luc Gauvain. 1015-1018 [doi]
• Improvement of speaker recognition system by individual information weightingSu-Hyun Kim, Gil-Jin Jang, Yung-Hwan Oh. 1017-1020 [doi]
• Word concept model: a knowledge representation for dialogue agentsYang Li, Tong Zhang, Stephen E. Levinson. 1019-1022 [doi]
• Speaker verification in noise using temporal constraintsNéstor Becerra Yoma, Tarciano Facco Pegoraro. 1021-1024 [doi]
• Audio-visual speech recognition using MCE-based hmms and model-dependent stream weightsChiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura. 1023-1026 [doi]
• Speaker identification using discriminative features selectionBogdan Sabac, Inge Gavat, Zica Valsan. 1025-1028 [doi]
• Automatic diagnosis of recognition errors in large vocabulary continuous speech recognition systemsHiroaki Nanjo, Akinobu Lee, Tatsuya Kawahara. 1027-1030 [doi]
• A further investigation on speech features for speaker characterizationIvan Magrin-Chagnolleau, Guillaume Gravier, Mouhamadou Seck, Olivier Boëffard, Raphaël Blouet, Frédéric Bimbot. 1029-1032 [doi]
• Taiwanese corpus collection via continuous speech recognition toolYuang-Chin Chiang, Zhi-Siang Yang, Ren-Yuan Lyu. 1031-1034 [doi]
• Language identification from short segments of speechJyotsana Balleda, Hema A. Murthy, T. Nagarajan. 1033-1036 [doi]
• Optimal maximum likelihood on phonetic decision tree acoustic model for LVCSRBaosheng Yuan, QingWei Zhao, Qing Guo, Xiangdong Zhang, Zhiwei Lin. 1035-1038 [doi]
• Generation of utterances based on visual context informationSusanne Kronenberg, Franz Kummert. 1037-1040 [doi]
• Frame level likelihood transformations for ASR and utterance verificationKonstantin P. Markov, Satoshi Nakamura. 1038-1041 [doi]
• A spoken dialogue system for conference/workshop servicesMazin G. Rahim, Roberto Pieraccini, Wieland Eckert, Esther Levin, Giuseppe Di Fabbrizio, Giuseppe Riccardi, Candace A. Kamm, Shrikanth Narayanan. 1041-1044 [doi]
• Integrating recognition confidence scoring with language understanding and dialogue modelingTimothy J. Hazen, Theresa Burianek, Joseph Polifroni, Stephanie Seneff. 1042-1045 [doi]
• Developing robust, user-centred multimodal spoken language systems: the MUeSLI projectGavin E. Churcher, Peter J. Wyard. 1045-1048 [doi]
• Speech recognition based on estimation of mutual informationYibiao Yu, Heming Zhao. 1046-1049 [doi]
• TABOR - a norwegian spoken dialogue system for bus travel informationMagne Hallstein Johnsen, Torbjørn Svendsen, Tore Amble, Trym Holter, Erik Harborg. 1049-1052 [doi]
• Keyword spotting in auto-attendant systemQing Guo, YongHong Yan, Zhiwei Lin, Baosheng Yuan, QingWei Zhao, Jian Liu. 1050-1052 [doi]
• A new approach for modeling OOV wordsWeimin Ren, Chengfa Wang, Wen Gao, Jinpei Xu. 1053-1056 [doi]
• Language understanding component for Chinese dialogue systemYinfei Huang, Fang Zheng, Mingxing Xu, Pengju Yan, Wenhu Wu. 1053-1056 [doi]
• Speech recognition using error spottingRachida El Méliani, Douglas D. O Shaughnessy. 1057-1060 [doi]
• Designing a domain independent platform of spoken dialogue systemKazumi Aoyama, Izumi Hirano, Hideaki Kikuchi, Katsuhiko Shirai. 1057-1060 [doi]
• An enhanced BLSTIP dialogue research platformQiru Zhou, Antoine Saad, Sherif Abdou. 1061-1064 [doi]
• Robust endpoint detection for in-car speech recognitionChung-Ho Yang, Ming-Shiun Hsieh. 1061-1064 [doi]
• Internet speech analysis system using e-mail and web technologyJouji Miwa, Masaru Kumagai. 1065-1068 [doi]
• Using machine learning method and subword unit representations for spoken document categorizationWeidong Qu, Katsuhiko Shirai. 1065-1068 [doi]
• ASR satisficing: the effects of ASR accuracy on speech retrievalLitza A. Stark, Steve Whittaker, Julia Hirschberg. 1069-1072 [doi]
• Multi-class linear dimension reduction by generalized Fisher criteriaMarco Loog, Reinhold Haeb-Umbach. 1069-1072 [doi]
• Improving the representation of time structure in front-ends for automatic speech recognitionWendy J. Holmes. 1073-1076 [doi]
• A system for retrieving broadcast news speech documents using voice input keywords and similarity between wordsHiromitsu Nishizaki, Seiichi Nakagawa. 1073-1076 [doi]
• Intention extraction and semantic matching for internet FAQ retrieval using spoken language queryYu-Sheng Lai, Kuen-Lin Lee, Chung-Hsien Wu. 1077-1080 [doi]
• Speech analysis by rule extraction from trained artificial neural networksKatrin Kirchhoff. 1077-1080 [doi]
• Minimum mean square error spectral peak envelope estimation for automatic vowel classificationJaishree Venugopal, Stephen A. Zahorian, Montri Karnjanadecha. 1081-1084 [doi]
• A domain-independent model to improve spelling in a web environmentRobert J. van Vark, Jelle K. de Haan, Léon J. M. Rothkrantz. 1081-1084 [doi]
• Probabilistic compensation of unreliable feature components for robust speech recognitionCyan L. Keung, Oscar C. Au, Chi H. Yim, Carrson C. Fung. 1085-1087 [doi]
• Expanded vector space model based on word space in cross media retrieval of news speech dataSeiichi Takao, Jun Ogata, Yasuo Ariki. 1085-1088 [doi]
• A new tone conversion method for Mandarin by an adaptive linear prediction analysisCongxiu Wang, Qihu Li, Guoying Zhao, Li Yin, Shuai Hao, Da Meng. 1088-1091 [doi]
• Audio stream phrase recognition for a national gallery of the spoken word: one small step John H. L. Hansen, Bowen Zhou, Murat Akbacak, Ruhi Sarikaya, Bryan L. Pellom. 1089-1092 [doi]
• Pronunciation variants description using recognition error modeling with phonetic derivation hypothesesHideharu Nakajima, Yoshinori Sagisaka, Hirofumi Yamamoto. 1093-1096 [doi]
• Evaluating responsiveness in spoken dialog systemsWataru Tsukahara, Nigel Ward. 1097-1100 [doi]
• Characteristics of spoken language required for objective quality evaluation of echo cancellersNobuhiko Kitawaki, Futoshi Asano, Takeshi Yamada. 1101-1104 [doi]
• Evaluation of the ATR-matrix speech translation system with a pair comparison method between the system and humansFumiaki Sugaya, Toshiyuki Takezawa, Akio Yokoo, Yoshinori Sagisaka, Seiichi Yamamoto. 1105-1108 [doi]
• An automatic timing detection method for superimposing closed captions of TV programsIchiro Maruyama, Yoshiharu Abe, Terumasa Ehara, Katsuhiko Shirai. 1109-1112 [doi]
• Normalized time-frequency speech representation in articulation training systemsMarcel Ogner, Zdravko Kacic. 1113-1116 [doi]
• Semantic transcoding: making the handicapped and the aged free from their barriers in obtaining information on the webShinichi Torihara, Katashi Nagao. 1117-1120 [doi]
• The use of nonlinear energy transformation for Tamil connected-digit speech recognitionRathinavelu Chengalvarayan. 1121-1124 [doi]
• State based sub-band Wiener filters for speech enhancement in car environmentsAimin Chen, Saeed Vaseghi. 1125-1128 [doi]
• Total least squares based subband modelling for scalable speech representations with damped sinusoidsKris Hermus, Werner Verhelst, Patrick Wambacq, Philippe Lemmerling. 1129-1132 [doi]
• Speech enhancement: new approaches to soft decisionJoon-Hyuk Chang, Nam Soo Kim. 1133-1136 [doi]