Abstract is missing.
- Knowing enough to analyze spoken languagesPeter Ladefoged. 1-4 [doi]
- Syllabic fillers for Spanish HMM keyword spottingEduardo Lleida, José B. Mariño, Josep M. Salavedra, Antonio Bonafonte. 5-8 [doi]
- Minimum error classification training for HMM-based keyword spottingYasuhiro Komori, David Rain Ton. 9-12 [doi]
- A novel speech recognizer for keyword spottingGregory J. Clary, John H. L. Hansen. 13-16 [doi]
- Secondary processing using speech segments for an HMM word spotting systemHerbert Gish, Kenney Ng, Jan Robin Rohlicek. 17-20 [doi]
- Continuous word spotting for applications in telecommunicationsMing-Whei Feng, Baruch Mazor. 21-24 [doi]
- A low bit-rate CELP coder based on multi-path search methodsMaurizio Copperi. 25-28 [doi]
- Fully vector quantized arm a analysis combined with glottal model for low bit rate codingKatsushi Seza, Hirohisa Tasaki, Shinya Takahashi. 29-32 [doi]
- Vector quantization of speech LSF parameters with generalized product codesErdal Paksoy, Wai-Yip Chan, Allen Gersho. 33-36 [doi]
- Low-rate speech coding based on time-frequency interpolationYair Shoham. 37-40 [doi]
- Improved CELP speech coding at 4 kbit/s and belowTomohiko Taniguchi, Yoshinori Tanaka, Yasuji Ohta, Fumio Amano. 41-44 [doi]
- Efficient integration of coarticulation and lexical information in a finite state grammarAntonio Bonafonte, José B. Mariño, Montse Pardàs. 45-48 [doi]
- ABo Xu, Z. W. Lin, Taiyi Huang, D.-X. Xu, Y. Q. Gao. 46
- Characteristics of nasalance in canadian speakers of English and FrenchHerbert A. Leeper, A. P. Rochet, Ian R. A. MacKay. 49-52 [doi]
- Ensemble averaging applied to the analysis of fricative consonantsChristine H. Shadle, Andre Moulinier, Christian U. Dobelke, Celia Scully. 53-56 [doi]
- Effects of stress and vowel context on velar stops in british EnglishAndrew Slater, Sarah Hawkins. 57-60 [doi]
- Lip rounding coarticulation in ItalianEmanuela Magno Caldognetto, Kyriaki Vagges, Giancarlo Ferrigno, Maria Grazia Busa. 61-64 [doi]
- Intelligibility of audio-visually desynchronised speech: asymmetrical effect of phoneme positionPaula M. T. Smeele, Anne C. Sittig, Vincent J. van Heuven. 65-68 [doi]
- Speech analysis using complex orthogonal auditory transform (coat)Unto K. Laine. 69-72 [doi]
- Auditory model based speech processingYuqing Gao, Taiyi Huang, Shaoyan Chen, Jean-Paul Haton. 73-76 [doi]
- Phonetic classification of timit segments preprocessed with lyon s cochlear model using a supervised/unsupervised hybrid neural networkGary Tajchman, Nathan Intrator. 77-80 [doi]
- Formant and pitch-pulse detection using models of auditory signal processingThomas Holton, Steve Love, Stephen P. Gill. 81-84 [doi]
- Towards handling the acoustic environment in spoken language processingHynek Hermansky, Nelson Morgan. 85-88 [doi]
- Real-time speaker-independent large-vocabulary CDHMM-based continuous telephonic speech recognizerAlberto Ciaramella, Davide Clementino, Roberto Pacifici. 89-92 [doi]
- Flexible vocabulary recognition of speechMatthew Lennig, Douglas Sharp, Patrick Kenny, Vishwa Gupta, Kristin Precoda. 93-96 [doi]
- The effects of signal representations, phonetic classification techniques, and the telephone networkBenjamin Chigier, Hong C. Leung. 97-100 [doi]
- A lexicon for a text-to-speech systemLeon Gulikers, Rijk Willemse. 101-104 [doi]
- Word class assignment in a text-to-speech systemRijk Willemse, Leon Gulikers. 105-108 [doi]
- Aspects of prosodic phrasing in SwedishGösta Bruce, Björn Granström, Kjell Gustafson, David House. 109-112 [doi]
- Synthesis-by-analogy: a bilingual investigation using German and EnglishKirk P. H. Sullivan, Robert I. Damper. 113-116 [doi]
- Degas: a system for rule-based diphone speech synthesisLeonard C. Manzara, David R. Hill. 117-120 [doi]
- Comparing methods for automatic extraction of voice source parameters from continuous speechHelmer Strik, Joop Jansen, Louis Boves. 121-124 [doi]
- The influence of linguistic variations on the voice source characteristicsJacques C. Koreman, Louis Boves, Bert Cranen. 125-128 [doi]
- Dynamic voice source changes in natural and synthetic speechSarah K. Palmer, Jill House. 129-132 [doi]
- Acoustic and perceptual modelling of the voice quality caused by fundamental frequency perturbationSatoshi Imaizumi, Jan Gauffin. 133-136 [doi]
- A speech acts approach to grounding in conversationDavid R. Traum, James F. Allen. 137-140 [doi]
- A discriminative approach for ambiguity resolution based on a semantic score functionKeh-Yih Su, Jing-Shin Chang, Yi-Chung Lin. 149-152 [doi]
- The influence of semantic and syntactic information on spoken sentence recognitionNobuaki Minematsu, Sumio Ohno, Keikichi Hirose, Hiroya Fujisaki. 153-156 [doi]
- Experiments on the use of the generalized probabilistic descent method in speech recognitionStephan Euler, Joachim Zinke. 157-160 [doi]
- Improving and optimizing speaker independent, 1000 words speech recognition in SpanishRicardo de Córdoba, José Manuel Pardo, José Colás. 161-164 [doi]
- Multiple-level evaluation of speech recognition systemsJohn F. Pitrelli, David Lubensky, Benjamin Chigier, Hong C. Leung. 165-168 [doi]
- Speaker independent word recognition using continuous matching of parameters in time-spectral form based on statistical measureTatsuya Kimura, Mitsuru Endo, Shoji Hiraoka, Katsuyuki Niyada. 169-172 [doi]
- Automatic derivation of lexical models for a very large vocabulary speech recognition systemR. Roddeman, H. Drexler, Louis Boves. 173-176 [doi]
- Towards synthesis of Hindi consonants using KLSYN88Shyam Sunder Agrawal, Kenneth N. Stevens. 177-180 [doi]
- Multi-lingual synthesis evaluation methodsLouis C. W. Pols. 181-184 [doi]
- The interaction of phonetics, phonology and morphology in an icelandic text-to-speech systemBjörn Granström, Petur Helgason, Hoskuldur Thrainsson. 185-188 [doi]
- Response time as a metric for comparison of speech recognition by humans and machinesAnne Cutler, Tony Robinson. 189-192 [doi]
- Analysis of the effectiveness of system error messages in a human-machine travel planning taskSheri Hunnicutt, Lynette Hirschman, Joseph Polifroni, Stephanie Seneff. 197-200 [doi]
- Evaluating interactive spoken language systemsDavid Goodine, Lynette Hirschman, Joseph Polifroni, Stephanie Seneff, Victor Zue. 201-204 [doi]
- The cluster-identification testUte Jekosch. 205-208 [doi]
- Effects of speaking rate and talker variability on the representation of spoken words in memoryLynne C. Nygaard, Mitchell Sommers, David B. Pisoni. 209-212 [doi]
- On the absence of word segmentation at weak syllablesHugo Quené, Yvette Smits. 213-216 [doi]
- Stimulus variability and the perception of spoken words: effects of variations in speaking rate and overall amplitudeMitchell Sommers, Lynne C. Nygaard, David B. Pisoni. 217-220 [doi]
- Words within words: lexical statistics and lexical accessJames M. McQueen, Anne Cutler. 221-224 [doi]
- Experiments in continuous speech recognition with a 60, 000 word vocabularyPatrick Kenny, R. Hollan, Gilles Boulianne, Harinath Garudadri, Yan Ming Cheng, Matthew Lennig, Douglas D. O Shaughnessy. 225-228 [doi]
- HMM training on unconstrained speech for large vocabulary, continuous speech recognitionGilles Boulianne, Patrick Kenny, Matthew Lennig, Douglas D. O Shaughnessy, Paul Mermelstein. 229-232 [doi]
- Appropriate error criterion selection for continuous speech HMM minimum error trainingDavid Rainion, Shigeki Sagayama. 233-236 [doi]
- Hardware implementation of realtime 1000-word HMM-LR continuous speech recognitionAkito Nagai, Kenji Kita, Toshiyuki Hanazawa, Tadashi Suzuki, Tomohiro Iwasaki, Tsuyoshi Kawabata, Kunio Nakajima, Kiyohiro Shikano, Tsuyoshi Morimoto, Shigeki Sagayama, Akira Kurematsu. 237-240 [doi]
- Design and performance of HARC, the BBN spoken language understanding systemMadeleine Bates, Robert J. Bobrow, Pascale Fung, Robert Ingria, Francis Kubala, John Makhoul, Long Nguyen, Richard M. Schwartz, David Stallard. 241-244 [doi]
- A trellis-based language model for speech recognitionNick Waegner, Steve J. Young. 245-248 [doi]
- PARSEC: a constraint-based framework for spoken language understandingCarla B. Zoltowski, Mary P. Harper, Leah H. Jamieson, Randall A. Helzerman. 249-252 [doi]
- The HMM interface with hybrid grammar-bigram language models for speech recognitionGareth J. F. Jones, Jeremy H. Wright, E. N. Wrigley. 253-256 [doi]
- A frame-synchronous continuous speech recognition algorithm using a top-down parsing of context-free grammarAtsuhiko Kai, Seiichi Nakagawa. 257-260 [doi]
- Empirical properties of finite state approximations for phrase structure grammarsFernando Pereira, David B. Roe. 261-264 [doi]
- Formation of phonological concept structures from spoken word samplesHiroaki Kojima, Kazuyo Tanaka, Satoru Hayamizu. 269-272 [doi]
- Acquisition of the French VOT contrasts by adult speakers of Mandarin ChineseBernard L. Rochet, Fangxin Chen. 273-276 [doi]
- Phonology as a byproduct of learning to recognize and produce words: a connectionist modelMichael Gasser. 277-280 [doi]
- Objective measurement of phoneme similarityWilliam C. Treurniet. 281-284 [doi]
- Recognizing phonemes vs. recognizing phones: a comparisonMichael D. Riley, Andrej Ljolje. 285-288 [doi]
- On the role of the segment in speech processing by human listeners: evidence from speech perception and from global sound similarity judgmentsBruce L. Derwing, Terrance M. Nearey, R. A. Beinert, T. A. Bendrien. 289-292 [doi]
- The syllabic status of postvocalic resonants in an unwritten low German dialectGrace E. Wiebe, Bruce L. Derwing. 293-296 [doi]
- Performance of speaker-independent Japanese recognizer as a function of training set size and diversityOtoya Shirotsuka, G. Kawai, Michael Cohen, Jared Bernstein. 297-300 [doi]
- Continuous mixture HMM-LR using the a* algorithm for continuous speech recognitionKouichi Yamaguchi, Shigeki Sagayama, Kenji Kita, Frank K. Soong. 301-304 [doi]
- Continuously spoken sentence recognition by HMM-LRKenji Kita, Tsuyoshi Morimoto, Kazumi Ohkura, Shigeki Sagayama. 305-308 [doi]
- Word pre-selection using a redundant hash addressing method for continuous speech recognitionAkinori Ito, Shozo Makino. 309-312 [doi]
- Optimal speech recognition using phone recognition and lexical accessAndrej Ljolje, Michael D. Riley. 313-316 [doi]
- Language modelling for recognition and understanding using layered bigramsStephanie Seneff, Helen M. Meng, Victor Zue. 317-320 [doi]
- Using probabilistic shift-reduce parsing in speech recognition systemsDavid Goddeau. 321-324 [doi]
- Broca, an integrated parser for spoken languageTim Howells, David Friedman, Mark A. Fanty. 325-328 [doi]
- Blank slate language processor for speech recognitionP. V. S. Rao, Nandini Bondale. 329-332 [doi]
- Integrating two complementary approaches to spoken language understandingEric Jackson. 333-336 [doi]
- The development of lexical effects on children s phoneme identificationsMichael S. Hurlburt, Judith C. Goodman. 337-340 [doi]
- Word recognition before production of first words?Pierre A. Hallé, Benedicte de Boysson-Bardies. 341-344 [doi]
- The effect of fundamental frequency for vowel perception in infantsToshisada Deguchi, Shigeru Kiritani, Akiko Hayashi, Fumi Katoh. 345-348 [doi]
- The influence of focus distribution and lexical stress on the temporal organisation of the syllableAgaath M. C. Sluijter, Vincent J. van Heuven, Anneke Neijt. 349-352 [doi]
- The development and perceptive evaluation of a model for paragraph intonation in dutchAgaath M. C. Sluijter, Jacques M. B. Terken. 353-356 [doi]
- Pause characteristics and local phrase-dependency structure in JapaneseNobuyoshi Kaiki, Yoshinori Sagisaka. 357-360 [doi]
- F0 synthesis based on a quantitative model of German intonationBernd Möbius, Matthias Pätzold. 361-364 [doi]
- Factors affecting pitch accent placementKen Ross, Mari Ostendorf, Stefanie Shattuck-Hufnagel. 365-368 [doi]
- Speaker adaptation based on transfer vector field smoothing with continuous mixture density HMMsKazumi Ohkura, Masahide Sugiyama, Shigeki Sagayama. 369-372 [doi]
- Speaker adaptation by modifying mixture coefficients of speaker-independent mixture Gaussian HMMsTatsuo Matsuoka, Kiyohiro Shikano. 373-376 [doi]
- Minimization of speech alignment error by iterative transformation for speaker adaptationYifan Gong, Olivier Siohan, Jean-Paul Haton. 377-380 [doi]
- Vector field smoothing principle for speaker adaptationHiroaki Hattori, Shigeki Sagayama. 381-384 [doi]
- Spectral mapping onto probabilistic domain using neural networks and its application to speaker adaptive phoneme recognitionTetsunori Kobayashi, Katsuhiko Shirai. 385-388 [doi]
- Learning compatibility coefficients for word-class disambiguation relaxation processesMarcello Pelillo, Mario Refice. 389-392 [doi]
- INTERTALKER: an experimental automatic interpretation system using conceptual representationKaichiro Hatazaki, Jun Noguchi, Akitoshi Okumura, Kazunaga Yoshida, Takao Watanabe. 393-396 [doi]
- Enhancement of ATR s spoken language translation system: SL-TRANS2Tsuyoshi Morimoto, Toshiyuki Takezawa, Kazumi Ohkura, Masaaki Nagata, Fumihiro Yato, Shigeki Sagayama, Akira Kurematsu. 397-400 [doi]
- Continuous speech recognition using a combination of syntactic constraints and dependency relationshipTsuyoshi Morimoto. 401-404 [doi]
- Automatic learning in spoken language understandingRoberto Pieraccini, Zakhar Gorelov, Esther Levin, Evelyne Tzoukermann. 405-408 [doi]
- An interactive system for automated pronunciation improvementJean-Paul Lefèvre, Mervyn A. Jack, Claudio Maggio, Mario Refice, Fabio Gabrieli, Michelina Savino, Luigi Santangelo. 409-412 [doi]
- Prosodic features for automated pronunciation improvement in the spell systemEdmund Rooney, Steven M. Hiller, John Laver, Mervyn A. Jack. 413-416 [doi]
- Vowels pronunciation assessment in the spell systemMaria-Gabriella Di Benedetto, Fabrizio Carraro, Steven M. Hiller, Edmund Rooney. 417-420 [doi]
- Prosodic correlates of discourse units in spontaneous speechMarc Swerts, Ronald Geluykens, Jacques M. B. Terken. 421-424 [doi]
- Prosody as a cue for discourse structureShin ya Nakajima, James F. Allen. 425-428 [doi]
- Some intonational characteristics of discourse structureBarbara J. Grosz, Julia Hirschberg. 429-432 [doi]
- Prosody and syntax in spoken sentences of standard ChineseHiroya Fujisaki, Keikichi Hirose, Haitao Lei. 433-436 [doi]
- Modeling sentential stress in the context of a large vocabulary continuous speech recognizerKathleen Bishop. 437-440 [doi]
- Speech understanding strategies based on string classification treesRenato de Mori, Roland Kuhn. 441-448 [doi]
- Infants perception and representation of speech: development of a new theoryPatricia K. Kuhl. 449-456 [doi]
- The behavior of the larynx in spoken language productionHajime Hirose. 457-458 [doi]
- Self-organizing map with supervision for speech recognitionFranck Poirier. 459-462 [doi]
- Topology preservation for speech recognitionGregory R. De Haan, Ömer Egecioglu. 463-466 [doi]
- Towards the performance limits of connectionist feature detectorsGary Bradshaw, Alan Bell. 467-470 [doi]
- Context-dependent and -independent self-structuring hidden control models for speech recognitionHelge B. D. Sørensen. 471-474 [doi]
- Integration of frequential and temporal structurations in a symbolic learning systemMarie-José Caraty, Claude Montacié, Claude Barras. 475-478 [doi]
- Speech segment network approach for an optimal synthesis unit setNaoto Iwahashi, Yoshinori Sagisaka. 479-482 [doi]
- ATR μ-talk speech synthesis systemYoshinori Sagisaka, Nobuyoshi Kaiki, Naoto Iwahashi, Katsuhiko Mimura. 483-486 [doi]
- On the development of a name pronunciation systemBert Van Coile, Steven Leys, Luc Mortier. 487-490 [doi]
- Consonants for female speech synthesisInger Karlsson. 491-494 [doi]
- Best exemplars of English velar stops: a first reportKatharine Davis, Patricia K. Kuhl. 495-498 [doi]
- Implementation of a model for lexical access based on featuresKenneth N. Stevens, Sharon Y. Manuel, Stefanie Shattuck-Hufnagel, Sharlene Liu. 499-502 [doi]
- Perception of aperiodic speech signalsDieter Huber. 503-506 [doi]
- Acceptability and discrimination threshold for distortion of segmental duration in Japanese wordsHiroaki Kato, Minoru Tsuzaki, Yoshinori Sagisaka. 507-510 [doi]
- Two level acoustic cues for consistent stop identificationAnne Bonneau, Sylvie Coste, Linda Djezzar, Yves Laprie. 511-514 [doi]
- Speech enhancement using a statistically derived filter mappingYan Ming Cheng, Douglas D. O Shaughnessy, Peter Kabal. 515-518 [doi]
- Hidden Markov model state-based cepstral noise compensationV. Beattie, Steve J. Young. 519-522 [doi]
- A computational model of auditory scene analysisGuy J. Brown, Martin P. Cooke. 523-526 [doi]
- A new dual-channel speech enhancement technique with application to CELP coding in noiseS. Nandkumar, John H. L. Hansen, Robert J. Stets. 527-530 [doi]
- CUMULANT - based voicing decision in noise corrupted speechAsunción Moreno, José A. R. Fonollosa. 531-534 [doi]
- Smoothing hidden Markov models ay means of a self organizing feature mapEnric Monte, José B. Mariño, Eduardo Lleida. 535-538 [doi]
- LVQ-based speech recognition with high-dimensional context vectorsJyri Mäntysalo, Kari Torkkola, Teuvo Kohonen. 539-542 [doi]
- Application of self-organizing maps and LVQ in training continuous density hidden Markov models for phonemesMikko Kurimo, Kari Torkkola. 543-546 [doi]
- Identification of mono- and poly-phonemes using acoustic-phonetic features derived by a self-organising neural networkPaul Dalsgaard, Ove Andersen. 547-550 [doi]
- Using phoneme group specific LVQ-codebooks with HMMsPekka Utela, Samuel Kaski, Kari Torkkola. 551-554 [doi]
- Diagnostic perceptual experiments for text-to-speech system evaluationJan P. H. van Santen. 555-558 [doi]
- Comparison of natural and synthetic speech intelligibility for a reverse telephone directory serviceMarcello Balestri, Enzo Foti, Luciano Nebbia, Mario Oreglia, Pier Luigi Salza, Stefano Sandri. 559-562 [doi]
- A corpus-based synthesizerRichard Sproat, Julia Hirschberg, David Yarowsky. 563-566 [doi]
- High quality speech synthesis based on wavelet compilation of phoneme segmentsTomohisa Hirokawa, Kenzo Itoh, Hirokazu Sato. 567-570 [doi]
- Inventory of phonetic contrasts generated by high-level control of a formant synthesizerDavid R. Williams, Corine A. Bickley, Kenneth N. Stevens. 571-574 [doi]
- Vowel classification based on analysis-by-synthesisRolf Carlson, James Glass. 575-578 [doi]
- Extrinsic normalization of vowel formant values based on cardinal vowels mappingMaria-Gabriella Di Benedetto, Jean-Sylvain Liénard. 579-582 [doi]
- Applications of generalized linear modeling to vowel dataTerrance M. Nearey. 583-586 [doi]
- Some comments on invariance, variability and perceptual normalization in speech perceptionDavid B. Pisoni. 587-590 [doi]
- Words and voices: perceptual details are preserved in lexical representationsStephen D. Goldinger, Thomas J. Palmeri, David B. Pisoni. 591-594 [doi]
- Selectively trained neural networks for the discrimination of normal and lombard speechYolande Anglade, Dominique Fohr, Jean-Claude Junqua. 595-598 [doi]
- The use of cohort normalized scores for speaker verificationAaron E. Rosenberg, Joel DeLong, Chin-Hui Lee, Biing-Hwang Juang, Frank K. Soong. 599-602 [doi]
- Speaker recognition using concatenated phoneme modelsTomoko Matsui, Sadaoki Furui. 603-606 [doi]
- Speaker identification through a modular connectionist architecture: evaluation on the timit databaseYounès Bennani. 607-610 [doi]
- AR-vector models for free-text speaker recognitionClaude Montacié, Jean-Luc Le Floch. 611-614 [doi]
- A hidden Markov model structure for the acquisition of speech by machine, ASMFrank Fallside. 615-618 [doi]
- Speaker-independent keyword recognition based on SMQ/HMMYasuyuki Masai, Shin-ichi Tanaka, Tsuneo Nitta. 619-622 [doi]
- CRIM s spontaneous speech recognition system for the ATIS taskRégis Cardin, Diane Goupil, Roxane Lacouture, Evelyne Millien, Charles Snow, Yves Normandin. 623-626 [doi]
- Improved connected digit recognition using spectral variation functionsFabio Brugnara, Renato de Mori, Diego Giuliani, Maurizio Omologo. 627-630 [doi]
- Alternative preprocessing techniques for discrete hidden Markov model phoneme recognitionAndrew Tridgell, Bruce Millar, Kim-Anh Do. 631-634 [doi]
- Linguistic modelling in the context of oral dialogueGerhard Th. Niedermair. 635-638 [doi]
- Static and dynamic predictions : a method to improve speech understanding in cooperative dialoguesFrançois Andry. 639-642 [doi]
- Dialogue Semantics for an Oral Dialogue SystemPaul Heisterkamp, Scott McGlashan, Nick J. Youd. 643-646 [doi]
- Using pragmatics to rule out recognition errors in cooperative task-oriented dialoguesMasaaki Nagata. 647-650 [doi]
- A real-time speech dialogue system using spontaneous speech understandingYoichi Takebayashi, Hiroyuki Tsubo, Yoichi Sadamoto, Hideki Hashimoto, Hideaki Shinchi. 651-654 [doi]
- A semantic and pragmatic analysis of tone and intonation in Mandarin ChineseLi-chiung Yang. 655-658 [doi]
- On prosodic features in speech - comparative studies between Japanese and standard ChineseYoshimasa Tsukuma. 659-662 [doi]
- Prosodic encoding of English speechW. Nick Campbell. 663-666 [doi]
- Prediction of syllable duration, speech rate and tempoGunnar Fant, Anita Kruckenberg, Lennart Nord. 667-670 [doi]
- Experiments with emotive speech - acted utterances and synthesized replicasRolf Carlson, Björn Granström, Lennart Nord. 671-674 [doi]
- Adding emotion to synthetic speech dialogue systemsKatherine Morton. 675-678 [doi]
- Emotional modalities and intonation in spoken languageCari Spring, Donna Erickson, Thomas Call. 679-682 [doi]
- Are any press-conferences , interviews or dialogues true dialogues?Tatiana Slama-Cazacu. 683-686 [doi]
- Further optimisation of a robust IMELDA speech recogniser for applications with severely degraded speechClaude Lefèbvre, Dariusz A. Zwierzynski, David R. Starks, Gary Birch. 691-694 [doi]
- Multiple approaches to robust speech recognitionRichard M. Stern, Fu-Hua Liu, Yoshiaki Ohshima, Thomas M. Sullivan, Alejandro Acero. 695-698 [doi]
- Speaker-independent spoken digit recognition in noisy environments using dynamic spectral features and neural networksTadashi Kitamura, Satoshi Ando, Etsuro Hayahara. 699-702 [doi]
- ICARUS: an mwave-based real-time speech recognition system in noise and lombard effectDouglas A. Cairns, John H. L. Hansen. 703-706 [doi]
- Word recognition in the car: adapting recognizers to new environmentsChafic Mokbel, L. Barbier, Y. Kerlou, Gérard Chollet. 707-710 [doi]
- German announcements using synthetic speech the Gauss systemPeter Meyer, Hans-Wilhelm Rühl, L. Vogten. 711-714 [doi]
- Intelligent dialogues in automated telephone servicesMervyn A. Jack, John C. Foster, Fred Stentiford. 715-718 [doi]
- Experience with a dialogue description formalism for realistic applicationsPalle Bach Nielsen, Anders Baekgaard. 719-722 [doi]
- Compensating for additive-noise in automatic speech recognitionSolomon Lerner, Baruch Mazor. 723-726 [doi]
- Continuous speech recognition for medical diagnoses using a character trigram modelShoichi Matsunaga, Toshiaki Tsuboi, Tomokazu Yamada, Kiyohiro Shikano. 727-730 [doi]
- Phonetic properties of dutch accent lending pitch movements under time pressureJ. Caspars, Vincent J. van Heuven. 731-734 [doi]
- Judgments of relative prominence for adjacent and non-adjacent accentsJacques M. B. Terken, Karin van den Hombergh. 735-738 [doi]
- A perceptual study of French intonationFrédéric Beaugendre, Christophe d Alessandro, Anne Lacheret-Dujour, Jacques M. B. Terken. 739-742 [doi]
- The phonetics of IGBO toneMark Liberman, J. Michael Schultz, Soonhyun Hong, Vincent Okeke. 743-746 [doi]
- Stress shift as pitch accent placement: within-word early accent placement in american EnglishStefanie Shattuck-Hufnagel. 747-750 [doi]
- Phonetic differences between read and spontaneous speechEleonora Blaauw. 751-754 [doi]
- Changing speech styles: strategies in read speech and casual and careful spontaneous speechMaxine Eskenazi. 755-758 [doi]
- Usage of words and sentence structures in spontaneous versus text materialNoriko Umeda, Karen Wallace, Josephine Horna. 759-762 [doi]
- Statistical and linguistic analyses of F0 in read and spontaneous speechNancy A. Daly, Victor Zue. 763-766 [doi]
- Spontaneous speech in English and ItalianLinda Shockey, Edda Farnetani. 767-770 [doi]
- A three-dimensional FEM simulation of the effects of the vocal tract shape on the transfer functionChengxiang Lu, Takayoshi Nakai, Hisayoshi Suzuki. 771-774 [doi]
- Mandibular contributions to speech productionKiyoshi Oshimat, Vincent L. Gracco. 775-778 [doi]
- Measurement of three-dimensional shapes of vocal tract and nasal cavity using magnetic resonance imaging techniqueMasafumi Matsumura. 779-782 [doi]
- Electromyographie studies on the production of pitch contour in accentless dialects in JapaneseShigeru Kiritani, Hajime Hirose, Kikuo Maekawa, Tsutomu Sato. 783-786 [doi]
- Non-linear annotation of multi-channel speech dataAlain Marchal, William J. Hardcastle, K. Nicolaidis, Noël Nguyen, Fiona Gibbon. 787-790 [doi]
- A phoneme labelling workbench using HMM and spectrogram reading knowledgeShingo Fujiwara, Yasuhiro Komori, Masahide Sugiyama. 791-794 [doi]
- Automatic discovery of acoustic measurements for phonetic classificationMichael S. Phillips, Victor Zue. 795-798 [doi]
- Detection of unknown words and automatic estimation of their transcriptions in continuous speech recognitionKatunobu Itou, Satoru Hayamizu, Hozumi Tanaka. 799-802 [doi]
- A HMM-based system for automatic segmentation and labeling of speechFabio Brugnara, Daniele Falavigna, Maurizio Omologo. 803-806 [doi]
- Vocal tract area functions of Swedish vowels and a new three-parameter modelGunnar Fant. 807-810 [doi]
- Acoustic and production pilot studies of speech vowels produced in noiseJean-Claude Junqua. 811-814 [doi]
- Active models for regularizing formant trajectoriesYves Laprie, Marie-Odile Berger. 815-818 [doi]
- Vowel-consonant-vowel transitions: analysis, modeling, and synthesisRené Carré, Samir Chennoukh, Mohamad Mrayati. 819-822 [doi]
- Phonetic analyses of the TIMIT corpus of american EnglishPatricia A. Keating, B. Blankenship, Dani Byrd, Edward Flemming, Yuichi Todaka. 823-826 [doi]
- Sex, dialects, and reductionDani Byrd. 827-830 [doi]
- Phonetic universals and hindi segment durationManjari Ohala, John J. Ohala. 831-834 [doi]
- Acoustic and articulatory correlates of contrastive emphasis in repeated correctionsDonna Erickson, Osamu Fujimura. 835-838 [doi]
- Effects of context and redundancy in the perception of naturally produced English vowelsGary Tajchman, Marcia A. Bush. 839-842 [doi]
- Improvements of magnetometer sensing system for monitoring tongue point movements during speechYorinobu Sonoda, Kohichi Ogata. 843-846 [doi]
- Inverse filtering of the glottal waveform using the Itakura-saito distortion measurePaavo Alku. 847-850 [doi]
- Measurement of intraoral sound pressure distributions of Japanese vowelsKunitoshi Motoki, Nobuhiro Miki. 851-854 [doi]
- A modification of the viterbi algorithm for stochastic phonographic transductionRobert W. P. Luk, Robert I. Damper. 855-858 [doi]
- Criteria for labelling prosodic aspects of English speechPaul C. Bagshaw, Briony J. Williams. 859-862 [doi]
- DTW-based phonetic labeling using explicit phoneme duration constraintsYifan Gong, Jean-Paul Haton. 863-866 [doi]
- TOBI: a standard for labeling English prosodyKim E. A. Silverman, Mary E. Beckman, John F. Pitrelli, Mari Ostendorf, Colin W. Wightman, Patti Price, Janet B. Pierrehumbert, Julia Hirschberg. 867-870 [doi]
- Consistency of judgements in manual labelling of phonetic segments: the distinction between clear and unclear casesBarbara Eisen, Hans-Günther Tillmann, Christoph Draxler. 871-874 [doi]
- Representing the tongue surface with curve fitsMaureen Stone, Subhash Lele. 875-878 [doi]
- Muscle forces in vowel vocal tract formationKatherine S. Harris, Eric Vatikiotis-Bateson, Peter J. Alfonso. 879-882 [doi]
- Neural network modeling of speech motor controlMakoto Hirayama, Eric Vatikiotis-Bateson, Mitsuo Kawato, Kiyoshi Honda. 883-886 [doi]
- The articulatory dynamics of running speech: gestures from phonemes?Eric Vatikiotis-Bateson, Makoto Hirayama, Kiyoshi Honda, Mitsuo Kawato. 887-890 [doi]
- A telephone speech database of spelled and spoken namesRonald A. Cole, Krist Roginski, Mark A. Fanty. 891-894 [doi]
- The OGI multi-language telephone speech corpusYeshwant K. Muthusamy, Ronald A. Cole, Beatrice T. Oshika. 895-898 [doi]
- The design for the wall street journal-based CSR corpusDouglas B. Paul, Janet M. Baker. 899-902 [doi]
- Multi-site data collection for a spoken language corpus - MAD COWLynette Hirschman. 903-906 [doi]
- Collection and analyses of WSJ-CSR corpus at MITMichael S. Phillips, James R. Glass, Joseph Polifroni, Victor Zue. 907-910 [doi]
- Connectionist gender adaptation in a hybrid neural network / hidden Markov model speech recognition systemVictor Abrash, Horacio Franco, Michael Cohen, Nelson Morgan, Yochai Konig. 911-914 [doi]
- Hybrid neural network/hidden Markov model continuous-speech recognitionMichael Cohen, Horacio Franco, Nelson Morgan, David E. Rumelhart, Victor Abrash. 915-918 [doi]
- Semantic hidden Markov networksGernot A. Fink, Franz Kummert, Gerhard Sagerer, Ernst Günter Schukat-Talamazzini, Heinrich Niemann. 919-922 [doi]
- Hesitation sounds: is there coarticulation across pause?Use Lehiste, Donna Erickson. 923-926 [doi]
- Acoustic analysis of laughterCorine A. Bickley, Sheri Hunnicutt. 927-930 [doi]
- Analysis of false starts in spontaneous speechDouglas D. O Shaughnessy. 931-934 [doi]
- Processing disfluent speech: recognising disfluency before lexical accessRobin J. Lickley, Ellen Gurman Bard. 935-938 [doi]
- A flexible multimodal dialogue architecture independent of the applicationPhilippe Morin, Jean-Claude Junqua, Jean-Marie Pierrel. 939-942 [doi]
- Studies of vowel and consonant reductionSharon Y. Manuel, Stefanie Shattuck-Hufnagel, Marie K. Huffman, Kenneth N. Stevens, Rolf Carlson, Sheri Hunnicutt. 943-946 [doi]
- Formant frequencies of vowels in English function wordsNoriko Umeda. 947-950 [doi]
- The lip benefit: auditory and visual intelligibility of French speech in noiseChristian Benoît, Tayeb Mohamadi. 951-954 [doi]
- Phonological assessment of deaf children s productive knowledge as a basis for speech-trainingAnne-Marie Öster. 955-958 [doi]
- Factors affecting voicing distinction of stops for the hearing impairedHideaki Seki, Akiko Hayashi, Satoshi Imaizumi, Takehiko Harada, Hiroshi Hosoi. 959-962 [doi]
- Investigations into the auditory F0 speechreading enhancement effect using a sinusoidal replica of the F0 contourArthur Boothroyd, Robin S. Waldstein, Eddy Yeung. 963-966 [doi]
- Some considerations on pitch and timing control in deaf childrenFrancesco Cutugno. 967-970 [doi]
- Chinese recognition and synthesis system based on Chinese syllablesFuyuan Mo, Changli Li, Tao Chen. 971-974 [doi]
- Accelerated stochastic approximation method based parameter estimation of monosyllables and their recognition using a neural networkHirofumi Yogo, Naoki Inagaki. 975-978 [doi]
- Diphone-based speech recognition using time-event neural networksToomas Altosaar, Matti Karjalainen. 979-982 [doi]
- Segment based variable frame rate speech analysis and recognition using a spectral variation functionGiovanni Flammia, Paul Dalsgaard, Ove Andersen, Børge Lindberg. 983-986 [doi]
- Familiarity with the language transcribed and context as determinants of intratranscriber agreementCatia Cucchiarini, Renée van Bezooijen. 987-990 [doi]
- Intonation of clause-internal filled pausesElizabeth Shriberg, Robin J. Lickley. 991-994 [doi]
- User behaviors affecting speech recognitionElizabeth Wade, Elizabeth Shriberg, Patti Price. 995-998 [doi]
- Intelligibility of the French spoken in France compared across listeners from France and from the Ivory CoastChristian Benoît. 999-1002 [doi]
- Dialect-dependent speech recognizers for canadian and european FrenchJulie Brousseau, Sally Anne Fox. 1003-1006 [doi]
- Automatic segmentation and identification of ten languages using telephone speechYeshwant K. Muthusamy, Ronald A. Cole. 1007-1010 [doi]
- Speaker-independent, text-independent language identification by HMMSeiichi Nakagawa, Yoshio Ueda, Takashi Seino. 1011-1014 [doi]
- A discrimination method between Japanese dialectsShuichi Itahashi, Tsutomu Yamashita. 1015-1018 [doi]
- Rate of speech effects in aphasia: an acoustic analysis of voice onset timeShari R. Baum. 1019-1022 [doi]
- Cue extraction and integration in speech perception for the hearing impairedHiroshi Hosoi, Satoshi Imaizumi, Akiko Hayashi, Takehiko Harada, Hideaki Seki. 1027-1030 [doi]
- The relationship between spectral details in naturally produced vowels and identification errors in noise and reverberationAnna K. Nabelek. 1031-1034 [doi]
- Speech processing effects on intelligibility for hearing-impaired listenersDonald G. Jamieson, Leonard Cornelisse. 1035-1038 [doi]
- Pathological voice analysis using cepstra, bispectra and group delay functionsB. Boyanov, Gérard Chollet. 1039-1042 [doi]
- Lateralization of speech sounds by binaural distributing processingQianje Fu, Peyu Xia, Ren-Hua Wang. 1043-1046 [doi]
- Studies of glottal excitation and vocal tract parameters using inverse filtering and a parameterized input modelJ. P. Liu, Geneviève Baudoin, Gérard Chollet. 1051-1054 [doi]
- Speeded detection of vowels and steady-state consonantsDennis Norris, Brit van Ooyen, Anne Cutler. 1055-1058 [doi]
- The role of F3 and F4 in identifying place of articulation for stop consonantsAbeer Alwan. 1063-1066 [doi]
- A new measure for perceptual weight of acoustic cues: an experiment on voicing in French intervocalic [t, d]Thomas R. Sawallis. 1067-1070 [doi]
- Objective speech quality assessment in patients with intra-oral cancers: voiceless fricativesAlan Wrench, Mervyn A. Jack, John Laver, Mary S. Jackson, David S. Soutar, A. Gerry Robertson, Janet MacKenzie Beck. 1071-1074 [doi]
- Tongue contact, active articulators, and coarticulationBruce Connell. 1075-1078 [doi]
- Cross-languages differences in the identification of intervocalic stop consonants by Japanese and dutch listenersMakio Kashino, Astrid van Wieringen, Louis C. W. Pols. 1079-1082 [doi]
- Effects of typicality and interstimulus interval on the discrimination of speech stimuli: within-subject comparisonMinoru Tsuzaki. 1083-1086 [doi]
- Perceptual studies on vowels excised from continuous speechRonald A. Cole, Yeshwant K. Muthusamy. 1087-1090 [doi]
- Can level words from one speaking style become teaks when spliced into another speaking style?Florien J. Koopmans-van Beinum. 1099-1102 [doi]
- Speech errors and task demandBeverley Gable, Helen Nemeth, Martin Haran. 1103-1106 [doi]
- Analysis of phonation type using laryngographic techniquesJohn H. Esling, B. Craig Dickson, Roy C. Snell. 1107-1110 [doi]
- Effect of prototypes of vowels on speech perception in Japanese and EnglishSumi Shigeno. 1111-1114 [doi]
- Characteristics of voice picked up from outer skin of larynxTomo-o Morohashi, Tetsuya Shimamura, Hiroyuki Yashima, Jouji Suzuki. 1115-1118 [doi]
- CSRE: a speech research environmentDonald G. Jamieson, Ketan Ramji, Issam Kheirallah, Terrance M. Nearey. 1127-1130 [doi]
- Is overall error rate a valid measure of speech synthesiser and natural speech performance at the segmental level?Mikael Goldstein, Ove Till. 1131-1134 [doi]
- Text-to-speech conversion for dutch: comprehensibility and acceptabilityWilly Jongenburger, Renée van Bezooijen. 1135-1138 [doi]
- Segmental power control for Japanese speech synthesisKenzo Itoh, Tomohisa Hirokawa, Hirokazu Sato. 1143-1146 [doi]
- Glottal waveform synthesis with volterra shapersJean Schoentgen. 1147-1150 [doi]
- Yet another rule compiler for text-to-speech conversion?Ken Ceder, Bertil Lyberg. 1151-1154 [doi]
- Prosody generation models constructed by considering speech tempo influence on prosodyKazuhiko Iwata, Yukio Mitome. 1155-1158 [doi]
- Extracting microprosodic information from diphones - a simple way to model segmental effects on prosody for synthetic speechAlex I. C. Monaghan. 1159-1162 [doi]
- Generation of natural sounding speech stimuli by means of linear cepstral interpolationArjan van Hessen. 1163-1166 [doi]
- Prosodic encoding of syntactic structure for speech synthesisW. Nick Campbell, Colin W. Wightman. 1167-1170 [doi]
- A nucleus-based timing model applied to multi-dialect speech synthesis by ruleSusan R. Hertz, Marie K. Huffman. 1171-1174 [doi]
- Evaluating the prosody of synthesized utterances within a dialogue systemJill House, Nick J. Youd. 1175-1178 [doi]
- Prosodics in a syllable-based text-to-speech synthesis systemMarcel Tatham, Eric Lewis. 1179-1182 [doi]
- From lexicon to rules: toward a descriptive method of French text-to-phonetics transcriptionRabia Belrhali, Véronique Aubergé, Louis-Jean Boë. 1183-1186 [doi]
- Formant transformation from male to female synthetic voicesMarianne Elmlund, Ida Frehr, Niels Reinholt Petersen. 1187-1190 [doi]
- Multilingual phoneme to grapheme conversion system based on HMMPanagiotis A. Rentzepopoulos, George K. Kokkinakis. 1191-1194 [doi]
- Fundamental frequency control using linguistic informationNoriyo Hara, Hisayoshi Tsubaki, Hisashi Wakita. 1195-1198 [doi]
- A comparison of statistical and rule based methods of determining segmental durationsAndrew P. Breen. 1199-1202 [doi]
- Generation and extraction of high quality synthesis unitsJ. R. Andrews, K. M. Curtis, Volker Kraft. 1203-1206 [doi]
- Evaluating the overall comprehensibility of speech synthesizersT. I. Boogaart, Kim E. A. Silverman. 1207-1210 [doi]
- Automatic generation of optimized unit dictionaries for text to speech synthesisOlivier Boëffard, Laurent Miclet, S. White. 1211-1214 [doi]
- Relationships between syllable, word and sentence intelligibilities of synthetic speechHideki Kasuya, Seiki Kasuya. 1215-1218 [doi]
- Unrestricted text-to-speech revisited: rhythm and intonationDavid R. Hill, Craig-Richard Schock, Leonard C. Manzara. 1219-1222 [doi]
- HADIFIX - a speech synthesis system for GermanThomas Portele, Birgit Steffan, Rainer Preuß, Walter F. Sendlmeier, Wolfgang Hess. 1227-1230 [doi]
- Two different methodologies for evaluating the comprehension of synthetic passagesCristina Delogu, Stella Conte, Andrea Paoloni, Ciro Sementina. 1231-1234 [doi]
- A target-interpolation model for the intonation of dutchCarlos Gussenhoven, Toni C. M. Rietveld. 1235-1238 [doi]
- A study of F0 reset in naturally-read utterances in JapaneseKazue Hata, Yoko Hasegawa. 1239-1242 [doi]
- Analyzing postposition drops in spoken JapaneseJunko Hosaka, Toshiyuki Takezawa, Noriyoshi Uratani. 1251-1254 [doi]
- Fundamental frequency patterns of Chinese in different speech modesJialu Zhang, Xinghui Hu. 1255-1258 [doi]
- The multifarious r-soundKnut Kvale, Arne Kjell Foldvik. 1259-1262 [doi]
- Parameter setting for abstract stress in tokyo JapaneseEiji Yamada. 1267-1270 [doi]
- A method for studying prosody in texts read aloudGeorg Ottesen. 1271-1274 [doi]
- Linguistic versus phonetic explanation of consonant lengthening after short vowels: a contrastive study of dutch and EnglishVincent J. van Heuven. 1275-1278 [doi]
- Comparing phoneme and feature based speech recognition using artificial neural networksKjell Elenius, Mats Blomberg. 1279-1282 [doi]
- Prosodic cues to the perception of syntactic boundariesEva Strangert. 1283-1286 [doi]
- A new model of intonation for use with speech synthesis and recognitionPaul Taylor, Stephen Isard. 1287-1290 [doi]
- Computerized error detection/correction in teaching German sounds: some problems and solutionsRudolf Weiss. 1291-1294 [doi]
- Velum and epiglottis behavior during the production of Arabic pharyngeals and laryngeals: a fiberscopic studyAhmed M. Elgendy. 1295-1298 [doi]
- A prosodic comparison of spontaneous speech and read speechKim E. A. Silverman, Eleonora Blaauw, Judith Spitz, John F. Pitrelli. 1299-1302 [doi]
- Phonological and psychological evidence that listeners normalize the speech signalJohn J. Ohala, Maria Grazia Busa, Karen Harrison. 1303-1306 [doi]
- Intonation and the request/question distinctionElizabeth A. Hinkelman. 1307-1310 [doi]
- The English voicing contrast as velocity perturbationRobert F. Port, Fred Cummins. 1311-1314 [doi]
- How many phonologies are there in one speaker? some experimental evidenceMichael S. Ziolkowski, Mayumi Usami, Karen L. Landahl, Brenda K. Tunnock. 1315-1318 [doi]
- Decomposition into syllable complexes and the accenting of Japanese loanwordsHirokazu Sato. 1319-1322 [doi]
- Temporal structure in bisyllabic word frame: an evidence for relational invariance and variability from standard ChineseJianfen Cao. 1323-1326 [doi]
- Towards a robust speech interface for teleoperation systemsJames H. Bradford. 1331-1334 [doi]
- Phonetic recognition experiments with recurrent neural networksPiero Cosi, Paolo Frasconi, Marco Gori, N. Griggio. 1335-1338 [doi]
- Some aspects on context and response range effects when assessing naturalness of Swedish sentences generated by 4 synthesiser systemsMikael Goldstein, Björn Lindström, Ove Till. 1339-1342 [doi]
- Probabilistic prediction of parts-of-speech from word spelling using decision treesMarcello Pelillo, Franca Moro, Mario Refice. 1343-1346 [doi]
- Single word detection system with a neural classifier for recognizing speech at variable levels of background noiseDieter Barschdorff, Ulrich Gärtner. 1347-1350 [doi]
- A rapid semi-automatic simulation technique for investigating interactive speech and handwritingSharon L. Oviatt, Philip R. Cohen, Martin Fong, Michael Frank. 1351-1354 [doi]
- Speech understanding on a massively parallel computerSang-Hwa Chung, Dan I. Moldovan. 1355-1358 [doi]
- Rationale for performance phonology Chan-Do Lee. 1359-1362 [doi]
- The effect of information feedback on the performance of a phoneme recognizer using kohonen mapTakuya Koizumi, Jyoji Urata, Shuji Taniguchi. 1363-1366 [doi]
- A method of dialogue management for the speech response systemYasuharu Asano, Keikichi Hirose, Hiroya Fujisaki. 1367-1370 [doi]
- Syllable duration prediction for speech recognitionYumi Takizawa, Eiichi Tsuboka. 1371-1374 [doi]
- Comparison between two methodologies of testing isolated word speech recognizersF. Canavesio, Giuseppe Castagneri, Giuseppe Di Fabbrizio, Francesco Senia. 1375-1378 [doi]
- Extracting fuzzy features from MLP for recognition of speechHe Jun, Henri Leich. 1379-1382 [doi]
- A fuzzy partition model (FPM) neural network architecture for speaker-independent continuous speech recognitionKeiji Fukuzawa, Yoshinaga Kato, Masahide Sugiyama. 1383-1386 [doi]
- Conception of speech filters based on a neural networkA. Ennaji, Jean Rouat. 1387-1390 [doi]
- Speaker set identification through speaker group modelingHong-Kwang Jeff Kuo, Chin-Hui Lee, Aaron E. Rosenberg. 1391-1394 [doi]
- Identification of principal ergonomic requirements for interactive spoken language systemsStephen Springer, Sara Basson, Judith Spitz. 1395-1398 [doi]
- Performance of the united kingdom intelligent network automatic speech recognition systemThomas E. Jacobs, Eric R. Buhrke. 1399-1402 [doi]
- Evaluation of parsing strategies in natural language spoken man-machine dialogueGuy Deville, Pierre Mousel. 1403-1406 [doi]
- An information retrieval system with a speech interfaceYasuhisa Niimi, Yutaka Kobayashi. 1407-1410 [doi]
- Phoneme performance in speaker recognitionJ. P. Eatock, J. S. D. Mason. 1411-1414 [doi]
- Natural language processing in the chronus systemEvelyne Tzoukermann, Roberto Pieraccini, Zakhar Gorelov. 1415-1418 [doi]
- Contribution of neural networks for phoneme identification in the APHODEX expert systemDominique Francois, Dominique Fohr. 1419-1422 [doi]
- A CSR-NL interface architectureDouglas B. Paul. 1423-1426 [doi]
- Speech interface for a man-machine dialog with the unix operating systemPierre Lefebvre, Frank Poirier, G. Duncan. 1427-1430 [doi]
- Transformation of databases for the evaluation of speech recognizersP. Bardaud, François Capman, Chafic Mokbel, Chakib Tadj, Gérard Chollet. 1431-1434 [doi]
- Dialog management for speech output from concept representationYoichi Yamashita, Riichiro Mizoguchi. 1435-1438 [doi]
- Speaker verification using locations and sizes of multipulses on neural networksSeiichiro Hangai, Shigetoshi Sugiyama, Kazuhiro Miyauchi. 1439-1442 [doi]
- Word rejection using multiple sink modelsCarlos Teixeira, Isabel Trancoso. 1443-1446 [doi]
- Modeling task driven oral dialogueAlain Cozannet. 1451-1454 [doi]
- Introducing neural predictor to hidden Markov model for speech recognitionWei-ying Li, Kechu Yi, Zheng Hu. 1455-1458 [doi]
- A neural network based on subnets - SNNFeng Liu, Jianxin Jiang, Jun Cheng, Kechu Yi. 1459-1462 [doi]
- Rapid non-supervised speaker adaptation of semicontinuous hidden Markov modelsFlorian Schiel. 1463-1466 [doi]
- Rule-based recognition of phoneme classesD. Ederveen, Louis Boves. 1467-1470 [doi]
- A new method of speaker-independent speech recognition using multiphone HMMJie Yi, Kei Miki. 1471-1474 [doi]
- A speaker adaptation based on corrective training and learning vector quantizationMyoung-Wan Koo, Chong Kwan Un. 1475-1478 [doi]
- Phoneme recognition in continuous speech based on mutual information considering phonemic duration and connectivityKatsuhiko Shirai, Shigeki Okawa, Tetsunori Kobayashi. 1479-1482 [doi]
- A real-time speaker-independent continuous speech recognition system based on demi-syllable unitsShinji Koga, Ryosuke Isotani, Satoshi Tsukada, Kazunaga Yoshida, Kaichiro Hatazaki, Takao Watanabe. 1483-1486 [doi]
- Speech recognition in noisy environmentsSaeed Vaseghi, Ben P. Milner. 1487-1490 [doi]
- An enhanced interpolation technique for context-specific probability estimation in speech and language modellingFergus R. McInnes. 1491-1494 [doi]
- Channel adaptation for a continuous speech recognizerLorenzo Fissore, Pietro Laface, Giorgio Micca, G. Sperto. 1495-1498 [doi]
- A new algorithm for connected digit recognitionS. Cifuentes, José Colás, Mohammed H. Savoji, José Manuel Pardo. 1499-1502 [doi]
- Stochastic modeling of syllable-based units for continuous speech recognitionGünther Ruske, Bernd Plannerer, Tanja Schultz. 1503-1506 [doi]
- HARK: an experimental speech recognition systemDavid M. Goblirsch, Toffee A. Albina. 1507-1510 [doi]
- The SSS-LR continuous speech recognition system: integrating SSS-derived allophone models and a phoneme-context-dependent LR parserAkito Nagai, Jun-ichi Takami, Shigeki Sagayama. 1511-1514 [doi]
- J-SUMMIT: a Japanese segment-based speech recognition systemShinsuke Sakai, Michael S. Phillips. 1515-1518 [doi]
- Optimal discriminative training for HMMs to recognize noisy speechShinobu Mizuta, Kunio Nakajima. 1519-1522 [doi]
- Architecture and algorithms of a real-time word recognizer for telephone inputShingo Kuroiwa, Kazuya Takeda, Fumihiro Yato, Seiichi Yamamoto, Kunihiko Owa, Makoto Shozakai, Ryuuji Matsumoto. 1523-1526 [doi]
- Speaker independent speech recognition method using word spotting technique and its application to VCR programmingHiroyasu Kuwano, Kazuya Nomura, Atsushi Ookumo, Shoji Hiraoka, Taisuke Watanabe, Katsuyuki Niyada. 1527-1530 [doi]
- Transputer implementation of front-end processors for speech recognition systemsS. Lennon, Eliathamby Ambikairajah. 1531-1534 [doi]
- Phoneme HMM evaluation algorithm without phoneme labelingYasuhiro Minami, Tatsuo Matsuoka, Kiyohiro Shikano. 1535-1538 [doi]
- Architecture of a configurable application interface for speech recognition systemsAndreas Noll, Henning Bergmann, Hans-Hermann Hamer, Annedore Paeseler, Horst Tomaschewski. 1539-1542 [doi]
- An interactive environment for speech recognition researchMark A. Fanty, John Pochmara, Ronald A. Cole. 1543-1546 [doi]
- An approach to unlimited vocabulary continuous speech recognition based on context-dependent phoneme modelingYoshiharu Abe, Kunio Nakajima. 1547-1550 [doi]
- Acoustic subword models in the berkeley restaurant projectChuck Wooters, Nelson Morgan. 1551-1554 [doi]
- Segmented trellis algorithms for the continuous speech recognitionYutaka Kobayashi, Yasuhisa Niimi. 1559-1562 [doi]
- Study of the time extension flat net for speech recognitionDao Wen Chen. 1567-1568 [doi]
- Syntactic anaphora resolution in a speech understanding systemUte Ziegenhain. 1569-1572 [doi]
- The dialog module of the speech recognition and dialog system EVARMarion Mast, Ralf Kompe, Franz Kummert, Heinrich Niemann, Elmar Nöth. 1573-1576 [doi]
- Statistical recovery of wideband speech from narrowband speechYan Ming Cheng, Douglas D. O Shaughnessy, Paul Mermelstein. 1577-1580 [doi]
- Speaker related variability in cepstral representations of dutch speech segmentsHenk van den Heuvel, Toni C. M. Rietveld. 1581-1584 [doi]
- Experiences from a real-world telephone application: teledialoguePer Rosenbeck, Bo Baungaard. 1585-1588 [doi]
- Robust estimation of time-varying LP parameters on speechK. Y. Lee, P. Ha, J. Rheem, S. Ann, I. Song. 1589-1592 [doi]
- On the AR modelling of the one-sided autocorrelation sequence for noisy speech recognitionJavier Hernando, Climent Nadeu, Eduardo Lleida. 1593-1596 [doi]
- Robust pitch detection by narrow band spectrum analysisHiroshi Shimodaira, Mitsuru Nakai. 1597-1600 [doi]
- A microcomputer-based system for real-time analysis and display of laryngograph signalsS. Eady, B. Craig Dickson, Roy C. Snell, J. Woolsey, P. Ollek, A. Wynrib, J. Clayards. 1601-1604 [doi]
- Parse scoring with prosodic informationN. M. Veilleux, Mari Ostendorf, Colin W. Wightman. 1605-1608 [doi]
- Topic identification using a neural network with a keyword-spotting preprocessorYing Cheng, Paul Fortier, Yves Normandin. 1609-1612 [doi]
- Frequency domain speech codingShane Switzer, Tim Anderson, Matthew Kabrisky, Steven K. Rogers, Bruce W. Suter. 1613-1616 [doi]
- MEDIATEX-TASF: a closed captioning real-time service in FrenchRaymond Descout, Robert Bergeron, Bernard Meriald. 1617-1620 [doi]
- The wavelet transform for speech analysisS. A. Wilde, K. M. Curtis. 1621-1624 [doi]
- Problems and algorithms in optimal linguistic decoding: a unified formulationPablo Aibar, Andrés Marzal, Enrique Vidal, Francisco Casacuberta. 1625-1628 [doi]
- A spectro-temporal analysis of speech based on nonlinear operatorsJean Rouat, Sylvain Lemieux, Alain Migneault. 1629-1632 [doi]
- A PC graphic tool for speech research based on a DSP boardMiguel A. Berrojo, Javier Corrales, Jesus Macias, Santiago Aguilera. 1633-1636 [doi]
- A spoken language dialogue system for automatic collection of spontaneous speechSatoru Hayamizu, Katunobu Itou, Masafumi Tamoto, Kazuyo Tanaka. 1637-1640 [doi]
- A powerful disambiguating mechanism for speech understanding systems based on ATMsShingo Nishioka, Yoichi Yamashita, Riichiro Mizoguchi. 1641-1644 [doi]
- A mixed Gaussian-stochastic code book for CELP coder in LSP speech codingNajib Naja, Jean-Marc Boucher, Samir Saoudi. 1645-1648 [doi]
- A method to estimate the transfer function of ARMA model of speech wave using prony method and homomorphic analysisHiroyuki Kamata, Yoshihisa Ishida. 1649-1652 [doi]
- An integrated dialogue design and continuous speech recognition system environmentBørge Lindberg, Bjarne Andersen, Anders Baekgaard, Tom Brøndsted, Paul Dalsgaard, Jan Kristiansen. 1653-1656 [doi]
- The PSH/DISPE helium speech cdromAlain Marchal, Christine Meunier, P. Gavarry. 1657-1660 [doi]
- Vocal cord vibration during consonants - high-speed digital imaging using a fiberscopeShigeru Kiritani, Hiroshi Imagawa, Hajime Hirose. 1661-1664 [doi]