Table of Contents

• Generalization problem in ASR acoustic model training and adaptationSadaoki Furui. 1-10 [doi]
• It's not you, it's me: Automatically extracting social meaning from speed datesDaniel Jurafsky. 11 [doi]
• Toward machine translation with statistics and syntax and semanticsDekai Wu. 12-21 [doi]
• Audio-visual automatic speech recognition and related bimodal speech technologies: A review of the state-of-the-art and open problemsGerasimos Potamianos. 22 [doi]
• Trends and challenges in language modeling for speech recognition and machine translationHolger Schwenk. 23 [doi]
• Manipulation of consonants in natural speechJont B. Allen, Feipeng Li. 24 [doi]
• Spoken dialogue systems: Challenges, and opportunities for researchJason D. Williams. 25 [doi]
• Voice-based information retrieval - how far are we from the text-based information retrieval ?Lin-Shan Lee, Yi-Cheng Pan. 26-43 [doi]
• Acoustic modelling for speech recognition: Hidden Markov models and beyond?Mark J. F. Gales. 44 [doi]
• Online discriminative learning: theory and applicationsNicolò Cesa-Bianchi. 45 [doi]
• New perspectives on spoken language understanding: Does machine need to fully understand speech?Tatsuya Kawahara. 46-50 [doi]
• Rapid language adaptation tools for multilingual speech processingTanja Schultz. 51 [doi]
• Investigations on features for log-linear acoustic models in continuous speech recognitionSimon Wiesler, Markus Nußbaum-Thom, Georg Heigold, Ralf Schlüter, Hermann Ney. 52-57 [doi]
• Leveraging speech production knowledge for improved speech recognitionAbhijeet Sangwan, John H. L. Hansen. 58-63 [doi]
• Optimal quantization and bit allocation for compressing large discriminative feature space transformsEtienne Marcheret, Vaibhava Goel, Peder A. Olsen. 64-69 [doi]
• Using temporal information for improving articulatory-acoustic feature classificationBarbara Schuppler, Joost van Doremalen, Odette Scharenborg, Bert Cranen, Lou Boves. 70-75 [doi]
• Generalized likelihood ratio discriminant analysisMuhammad Ali Tahir, Georg Heigold, Christian Plahl, Ralf Schlüter, Hermann Ney. 76-81 [doi]
• Multi-view learning of acoustic features for speaker recognitionKaren Livescu, Mark Stoehr. 82-86 [doi]
• Large-margin feature adaptation for automatic speech recognitionChih-Chieh Cheng, Fei Sha, Lawrence K. Saul. 87-92 [doi]
• Articulatory feature detection with Support Vector Machines for integration into ASR and phone recognitionUpendra V. Chaudhari, Michael Picheny. 93-98 [doi]
• Transition features for CRF-based speech recognition and boundary detectionSpiros Dimopoulos, Eric Fosler-Lussier, Chin-Hui Lee, Alexandros Potamianos. 99-102 [doi]
• Short-time instantaneous frequency and bandwidth features for speech recognitionPirros Tsiakoulis, Alexandros Potamianos, Dimitrios Dimitriadis. 103-106 [doi]
• Hidden Conditional Random Fields for phone recognitionYun-Hsuan Sung, Daniel Jurafsky. 107-112 [doi]
• Diagonal priors for full covariance speech recognitionPeter Bell, Simon King. 113-117 [doi]
• A study on Hidden Structural Model and its application to labeling sequencesYu Qiao, Masayuki Suzuki, Nobuaki Minematsu. 118-123 [doi]
• A hierarchical structure for modeling inter and intra phonetic information for phoneme recognitionDaniel Vásquez, Guillermo Aradilla, Rainer Gruhn, Wolfgang Minker. 124-129 [doi]
• Automatic selection of recognition errors by respeaking the intended textKeith Vertanen, Per Ola Kristensson. 130-135 [doi]
• Improving online incremental speaker adaptation with eigen feature space MLLRXiaodong Cui, Jian Xue, Bowen Zhou. 136-140 [doi]
• Kernel metric learning for phonetic classificationJui-Ting Huang, Xi Zhou, Mark Hasegawa-Johnson, Thomas S. Huang. 141-145 [doi]
• Three-layer optimizations for fast GMM computations on GPU-like parallel processorsKshitij Gupta, John D. Owens. 146-151 [doi]
• A segmental CRF approach to large vocabulary continuous speech recognitionGeoffrey Zweig, Patrick Nguyen. 152-157 [doi]
• Generalized likelihood ratio discriminant analysisHung-Shin Lee, Berlin Chen. 158-163 [doi]
• Temporal envelope subtraction for robust speech recognition using modulation spectrumSriram Ganapathy, Samuel Thomas, Hynek Hermansky. 164-169 [doi]
• Discriminative adaptive training with VTS and JUDFederico Flego, Mark J. F. Gales. 170-175 [doi]
• Hierarchical variational loopy belief propagation for multi-talker speech recognitionSteven J. Rennie, John R. Hershey, Peder A. Olsen. 176-181 [doi]
• SNR features for automatic speech recognitionPhilip N. Garner. 182-187 [doi]
• Power function-based power distribution normalization algorithm for robust speech recognitionChanwoo Kim, Richard M. Stern. 188-193 [doi]
• Mask estimation employing Posterior-based Representative Mean for missing-feature speech recognition with time-varying background noiseWooil Kim, John H. L. Hansen. 194-198 [doi]
• Noise robust model adaptation using linear spline interpolationKaustubh Kalgaonkar, Michael L. Seltzer, Alex Acero. 199-204 [doi]
• Support vector machines for noise robust ASRMark J. F. Gales, Anton Ragni, H. AlDamarki, C. Gautier. 205-210 [doi]
• Generalized cyclic transformations in speaker-independent speech recognitionFlorian Müller, Eugene Belilovsky, Alfred Mertins. 211-215 [doi]
• MLLR/MAP adaptation using pronunciation variation for non-native speech recognitionYoo Rhee Oh, Hong Kook Kim. 216-221 [doi]
• Improving joint uncertainty decoding performance by predictive methods for noise robust speech recognitionHaitian Xu, Mark J. F. Gales, K. K. Chin. 222-227 [doi]
• Improved decision trees for multi-stream HMM-based audio-visual continuous speech recognitionJing Huang, Karthik Visweswariah. 228-231 [doi]
• Extended Minimum Classification Error Training in Voice Activity DetectionTakayuki Arakawa, Haitham Al-Hassanieh, Masanori Tsujikawa, Ryosuke Isotani. 232-236 [doi]
• An improved parallel model combination method for noisy speech recognitionHadi Veisi, Hossein Sameti. 237-242 [doi]
• Robust speech recognition using a Small Power Boosting algorithmChanwoo Kim, Kshitiz Kumar, Richard M. Stern. 243-248 [doi]
• Robust distributed speech recognition using two-stage Filtered Minima Controlled Recursive AveragingNegar Ghourchian, Sid-Ahmed Selouani, Douglas D. O'Shaughnessy. 249-254 [doi]
• A study on hidden Markov model's generalization capability for speech recognitionXiong Xiao, Jinyu Li, Engsiong Chng, Haizhou Li, Chin-Hui Lee. 255-260 [doi]
• Sub-band modulation spectrum compensation for robust speech recognitionWen-hsiang Tu, Sheng-Yuan Huang, Jeih-Weih Hung. 261-265 [doi]
• An improved perceptual speech enhancement technique employing a psychoacoustically motivated weighting factorMd. Jahangir Alam, Sid-Ahmed Selouani, Douglas D. O'Shaughnessy. 266-270 [doi]
• MAP estimation of online mapping parameters in ensemble speaker and speaking environment modelingYu Tsao, Shigeki Matsuda, Satoshi Nakamura, Chin-Hui Lee. 271-275 [doi]
• Dynamic network decoding revisitedHagen Soltau, George Saon. 276-281 [doi]
• Iterative decoding: A novel re-scoring framework for confusion networksAnoop Deoras, Frederick Jelinek. 282-286 [doi]
• Island-driven search using broad phonetic classesTara N. Sainath. 287-292 [doi]
• A multiplatform speech recognition decoder based on weighted finite-state transducersEmilian Stoimenov, Tanja Schultz. 293-298 [doi]
• Scaling shrinkage-based language modelsStanley F. Chen, Lidia Mangu, Bhuvana Ramabhadran, Ruhi Sarikaya, Abhinav Sethy. 299-304 [doi]
• Discriminative training of n-gram language models for speech recognition via linear programmingVladimir Magdin, Hui Jiang 0001. 305-310 [doi]
• Constrained discriminative training of N-gram language modelsAriya Rastrow, Abhinav Sethy, Bhuvana Ramabhadran. 311-316 [doi]
• Self-supervised discriminative training of statistical language modelsPuyang Xu, Damianos Karakos, Sanjeev Khudanpur. 317-322 [doi]
• Towards the use of inferred cognitive states in language modelingNigel G. Ward, Alejandro Vega. 323-326 [doi]
• Syntactic features for Arabic speech recognitionHong-Kwang Jeff Kuo, Lidia Mangu, Ahmad Emami, Imed Zitouni, Young-Suk Lee. 327-332 [doi]
• Vietnamese large vocabulary continuous speech recognitionNgoc Thang Vu, Tanja Schultz. 333-338 [doi]
• The ESAT 2008 system for N-Best Dutch speech recognition benchmarkKris Demuynck, Antti Puurula, Dirk Van Compernolle, Patrick Wambacq. 339-344 [doi]
• On speeding phoneme recognition in a hierarchical MLP structureDaniel Vásquez, Guillermo Aradilla, Rainer Gruhn, Wolfgang Minker. 345-348 [doi]
• Robust vocabulary independent keyword spotting with graphical modelsMartin Wöllmer, Florian Eyben, Björn Schuller, Gerhard Rigoll. 349-353 [doi]
• Integrating morphology into automatic speech recognitionHasim Sak, Murat Saraclar, Tunga Güngör. 354-358 [doi]
• An exploration of large vocabulary tools for small vocabulary phonetic recognitionTara N. Sainath, Bhuvana Ramabhadran, Michael Picheny. 359-364 [doi]
• MLP based hierarchical system for task adaptation in ASRJoel Pinto, Mathew Magimai-Doss, Hervé Bourlard. 365-370 [doi]
• Detection of OOV words by combining acoustic confidence measures with linguistic featuresFrederik Stouten, Dominique Fohr, Irina Illina. 371-375 [doi]
• From speech to letters - using a novel neural network architecture for grapheme based ASRFlorian Eyben, Martin Wöllmer, Björn Schuller, Alex Graves. 376-380 [doi]
• Graph-based submodular selection for extractive summarizationHui Lin, Jeff A. Bilmes, Shasha Xie. 381-386 [doi]
• Integrating prosodic features in extractive meeting summarizationShasha Xie, Dilek Hakkani-Tür, Benoît Favre, Yang Liu. 387-391 [doi]
• Extractive speech summarization by active learningJustin Jian Zhang, Ricky Ho Yin Chan, Pascale Fung. 392-397 [doi]
• Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgramsYaodong Zhang, James R. Glass. 398-403 [doi]
• Query-by-example Spoken Term Detection For OOV termsCarolina Parada, Abhinav Sethy, Bhuvana Ramabhadran. 404-409 [doi]
• Spoken term detection from bilingual spontaneous speech using code-switched lattice-based structures for words and subword unitsHung-yi Lee, Yueh-Lien Tang, Hao Tang, Lin-Shan Lee. 410-415 [doi]
• Improved vocabulary independent search with approximate match based on Conditional Random FieldsUpendra V. Chaudhari, Michael Picheny. 416-420 [doi]
• Query-by-example spoken term detection using phonetic posteriorgram templatesTimothy J. Hazen, Wade Shen, Christopher M. White. 421-426 [doi]
• Topic-based speaker recognition for German parliamentary speechesDoris Baum. 427-431 [doi]
• Robust Speaker Diarization for short speech recordingsDavid Imseng, Gerald Friedland. 432-437 [doi]
• Ontology-based grounding of Spoken Language UnderstandingSilvia Quarteroni, Marco Dinarelli, Giuseppe Riccardi. 438-443 [doi]
• Active learning for rule-based and corpus-based Spoken Language Understanding modelsPierre Gotab, Frédéric Béchet, Géraldine Damnati. 444-449 [doi]
• Representing the Reinforcement Learning state in a negotiation dialoguePeter A. Heeman. 450-455 [doi]
• Back-off action selection in summary space-based POMDP dialogue systemsMilica Gasic, Fabrice Lefèvre, Filip Jurcícek, Simon Keizer, François Mairesse, Blaise Thomson, Kai Yu, Steve Young. 456-461 [doi]
• Response timing generation and response type selection for a spontaneous spoken dialog systemRyota Nishimura, Seiichi Nakagawa. 462-467 [doi]
• Garbage modeling with decoys for a sequential recognition scenarioMichael Levit, Shuangyu Chang, Bruce Buntschuh. 468-473 [doi]
• Correlation-based query relaxation for example-based dialog modelingCheongjae Lee, Sungjin Lee, Sangkeun Jung, Kyungduk Kim, Donghyeon Lee, Gary Geunbae Lee. 474-478 [doi]
• The exploration/exploitation trade-off in Reinforcement Learning for dialogue managementSebastian Varges, Giuseppe Riccardi, Silvia Quarteroni, Alexei V. Ivanov. 479-484 [doi]
• Any questions? Automatic question detection in meetingsKofi Boakye, Benoît Favre, Dilek Hakkani-Tür. 485-489 [doi]
• Weighted finite state transducer based statistical dialog managementChiori Hori, Kiyonori Ohtake, Teruhisa Misu, Hideki Kashioka, Satoshi Nakamura. 490-495 [doi]
• Automatic translation from parallel speech: Simultaneous interpretation as MT training dataMatthias Paulik, Alex Waibel. 496-501 [doi]
• Reinforcing language model for speech translation with auxiliary dataJia Cui, Yonggang Deng, Bowen Zhou. 502-506 [doi]
• The Asian network-based speech-to-speech translation systemSakriani Sakti, Noriyuki Kimura, Michael Paul, Chiori Hori, Eiichiro Sumita, Satoshi Nakamura, Jun Park, Chai Wutiwiwatchai, Bo Xu, Hammam Riza, Karunesh Arora, Chi Mai Luong, Haizhou Li. 507-512 [doi]
• Towards integrated machine translation using structural alignment from syntax-augmented synchronous parsingBing Xiang, Bowen Zhou, Martin Cmejrek. 513-518 [doi]
• Phone-to-word decoding through statistical machine translation and complementary system combinationDaniele Falavigna, Matteo Gerosa, Roberto Gretter, Diego Giuliani. 519-524 [doi]
• Pronunciation modeling for dialectal arabic speech recognitionHassan Al-Haj, Roger Hsiao, Ian R. Lane, Alan W. Black, Alex Waibel. 525-528 [doi]
• Speaker de-identification via voice transformationQin Jin, Arthur R. Toth, Tanja Schultz, Alan W. Black. 529-533 [doi]
• Multilingual speaker age recognition: Regression analyses on the Lwazi corpusMichael Feld, Etienne Barnard, Charl Johannes van Heerden, Christian A. Müller. 534-539 [doi]
• Comparing automatic rich transcription for Portuguese, Spanish and English Broadcast NewsFernando Batista, Isabel Trancoso, Nuno J. Mamede. 540-545 [doi]
• Discriminative Product-of-Expert acoustic mapping for cross-lingual phone recognitionKhe Chai Sim. 546-551 [doi]
• Acoustic emotion recognition: A benchmark comparison of performancesBjörn Schuller, Bogdan Vlasenko, Florian Eyben, Gerhard Rigoll, Andreas Wendemuth. 552-557 [doi]
• Local and global models for spontaneous speech segment detection and characterizationRichard Dufour, Yannick Estève, Paul Deléglise, Frédéric Béchet. 558-561 [doi]
• Lexicon adaptation for subword speech recognitionTimo Mertens, Daniel Schneider, Arild Brandrud Næss, Torbjørn Svendsen. 562-567 [doi]
• Lattice-based lexical cues for word fragment detection in conversational speechKartik Audhkhasi, Panayiotis G. Georgiou, Shrikanth S. Narayanan. 568-573 [doi]
• Sub-structure-based estimation of pronunciation proficiency and classification of learnersMasayuki Suzuki, Nobuaki Minematsu, Dean Luo, Keikichi Hirose. 574-579 [doi]
• Automatic detection of vowel pronunciation errors using multiple information sourcesJoost van Doremalen, Catia Cucchiarini, Helmer Strik. 580-585 [doi]
• Automatic punctuation generation for speechWenzhu Shen, Roger Peng Yu, Frank Seide, Ji Wu. 586-589 [doi]