Table of Contents

• Recent advances in speech recognitionSadaoki Furui. 3-12 [doi]
• On the acquisition of speech by machines, ASMFrank Fallside. 13-14 [doi]
• Speaker independent recognition of spontaneously spoken connected digitsPadma Ramesh, Jay G. Wilpon, Maureen A. McGee, David B. Roe, Chin-Hui Lee, Lawrence R. Rabiner. 17-20 [doi]
• Immediate recognition of embedded command wordsP. S. Gopalakrishnan, David Nahamoo. 21-24 [doi]
• HMM-based wordspotting for voice editing and indexingLynn Wilcox, Marcia A. Bush. 25-28 [doi]
• Large vocabulary speaker-adaptive continuous speech recognition research overview at dragon systemsJanet M. Baker. 29-32 [doi]
• Continuous density HMM context dependent phones for speech recognition over the telephoneVictoria Sgardoni, Dimitrios A. Gaganelis, Eleftherios D. Frangoulis. 33-36 [doi]
• Text-to-speech synthesizer using superposition of sinusoidal waves generated by synchronized oscillatorsKatsuhiko Shirai, Kazuo Hashimoto, Tetsunori Kobayashi. 39-42 [doi]
• Synthesis-by-rule using compost: modelling resonance trajectoriesM. Guerti, G. Bailly. 43-46 [doi]
• Neural network based spectral interpolation method for speech synthesis by ruleYasushi Ishikawa, Kunio Nakajima. 47-50 [doi]
• A rule-based segmental synthesis module for FrenchMartine Garnier-Rizet. 51-54 [doi]
• Effects of system voice quality on user utterances in speech dialogue systemsNorman M. Fraser, G. Nigel Gilbert. 57-60 [doi]
• A human factors study of speech-to-text technology: consequences of discrete speechP. Day, Andreas Grünupp, Klaus-Peter Muthig. 61-64 [doi]
• A comparison of document composition using a listening typewriter and conventional office systemsIain R. Murray, John L. Arnott, Alan F. Newell. 65-68 [doi]
• Mixed mode input for a standard wordprocessor. investigating links between input mode, speech and keyboard, and specific task areasMary Zajicek, Jill Hewitt. 73-76 [doi]
• Experiments with a non-linear spectral subtractor (NSS), hidden Markov models and the projection, for robust speech recognition in carsPhilip Lockwood, Jérôme Boudy. 79-82 [doi]
• Noise reduction for speech enhancement in cars: non-linear spectral subtraction / kalman filteringPhilip Lockwood, C. Baillargeat, J. M. Gillot, Jérôme Boudy, Gérard Faucon. 83-86 [doi]
• Isolated word recognition with integrated noise reductionKlaus Fellbaum, Dieter Becker. 87-90 [doi]
• A comparative study of parameters and distances for noisy speech recognitionJavier Hernando, Climent Nadeu. 91-94 [doi]
• A new reliability-based phoneme segmentation method for the neural phonetic typewriterJorma Laaksonen. 97-100 [doi]
• Isolated word adaptive recognizer based on neural networksBruno Apolloni, Francesco Pazienti, Vincenzo Trotta. 101-104 [doi]
• Evaluation of speaker-independent phoneme recognition on TIMIT database using TDNNsNobuo Hataoka, Alex Waibel. 105-108 [doi]
• Phonetic context in hybrid HMM/MLP continuous speech recognitionNelson Morgan, Hervé Bourlard, Chuck Wooters, Phil Kohn, Michael Cohen. 109-112 [doi]
• Neural network classification of complex-valued speech featuresE. C. Andrews, John S. Mason. 113-116 [doi]
• Rewiring lexical networks on the flyDennis Norris. 117-120 [doi]
• Phoneme recognition with an artificial neural networkKjell Elenius, G. Takacs. 121-124 [doi]
• A new self-organization algorithm of forming a phoneme mapJianxin Jiang, Kechu Yi, Zheng Hu. 125-128 [doi]
• Phoneme classification using neural networks based on acoustic-phonetic structureShuping Ran, J. Bruce Millar. 129-132 [doi]
• Networks for speech recognition structurally optimised by genetic techniques implemented on parallel hardwareNigel Dodd, Donald MacFarlane, Chris Marland. 133-136 [doi]
• Influence of vietnamese tone and prosody on the acquisition of English stress patternsJeff Pittam, John Ingram. 139-142 [doi]
• The voiced/unvoiced distinction of initial stops by normal and hearing impaired listenersWalter F. Sendlmeier. 143-146 [doi]
• Comparison of formant transition based stop classifiers: time-varying and time-invariant signal modelsKrishna S. Nathan. 147-150 [doi]
• The effect of context on labiality in FrenchChristian Benoît, Christian Abry, L. J. Roe. 151-156 [doi]
• Nasalisation in bengali speech sounds acoustic-phonetic studyA. K. Datta, N. R. Ganguli, B. Mukherjee. 157-160 [doi]
• Vowel formant frequency distribution of a major indian languageN. R. Ganguli. 161-164 [doi]
• Effects of language change on voice quality in bilingual speakers, corpus content effectBernard Harmegnies, Marielle Bruyninckx, Joaquim Llisterri, Dolors Poch. 165-168 [doi]
• Phoneme-based training for large-vocabulary recognition in six european languagesPaul G. Bamberg, Anne Demedts, John Elder, Caroline B. Huang, Charles Ingold, Mark A. Mandel, Linda Manganaro, Stijn Van Even. 175-182 [doi]
• 1.0 TANGORA - a large vocabulary speech recognition system for five languagesHelene Cerf-Danon, Steven DeGennaro, Marco Ferretti, Jorge Gonzalez, Eric Keppel. 183-192 [doi]
• Prototype systems for large-vocabulary speech recognition: polyglot and spicosHermann Ney, Roberto Billi. 193-200 [doi]
• Adaptation of grammar-based language models for continuous speech recognitionJ. H. Wright. 203-206 [doi]
• A robustness and discrimination oriented score function for integrating speech and language processingKeh-Yih Su, Tung-Hui Chiang, Yi-Chung Lin. 207-210 [doi]
• Improving speech understanding performance through feedback verificationPaolo Baggia, Lorenzo Fissore, Elisabetta Gerbino, Egidio P. Giachin, Claudio Rullent. 211-214 [doi]
• Computation of upper-bounds for island-driven stochastic parsersAnna Corazza, Renato de Mori, Roberto Gretter, Giorgio Satta. 215-218 [doi]
• A parser for speech lattices using a UCG grammarFrançois Andry, J. H. Simon Thornton. 219-222 [doi]
• Using pragmatic and semantic knowledge to correct parsing of spoken language utterancesSheryl Young, Michael Matessa. 223-227 [doi]
• Hybrid sinusoidal modeling of speech without voicing decisionArnaldo J. Abrantes, Jorge S. Marques, Isabel Trancoso. 231-234 [doi]
• Harmonic coding of speech: an experimental studyJorge S. Marques, Isabel Trancoso, Arnaldo J. Abrantes. 235-238 [doi]
• A multiband excitation linear predictive speech coderDavid Rowe, William Cowley, Andrew Perkis. 239-242 [doi]
• A new coded excitation model using multifrequency decompositionShu Hung Leung, K. L. Lai, O. Y. Wong, Andrew Luk. 245-248 [doi]
• Speaker related variability in the durations of dutch speech segmentsHenk van den Heuvel, Bert Cranen, Toni C. M. Rietveld. 251-254 [doi]
• Numerical simulations of glottal flowJohan Liljencrants. 255-258 [doi]
• Modelling of source characteristics of speech sounds by means of the LF-modelJoop Jansen, Bert Cranen, Louis Boves. 259-262 [doi]
• Evidence of chaos in phonatory samplesHanspeter Herzel, J. Wendler. 263-266 [doi]
• Source-tract coupling and the subglottal system in an articulatory synthesizerVan Loan Trinh, Bernard Guérin, Eric Castelli. 267-270 [doi]
• The effects of in internal reference system and cross-modality matching on the subjective rating of speech synthesisersMario Rossi, Robert Espesser, Chaslav Pavlovic. 273-276 [doi]
• Evaluation of speech synthesis techniques in a comprehension taskH. A. Sydeserff, R. J. Caley, Stephen D. Isard, Mervyn A. Jack, Alex I. C. Monaghan, J. Verhoeven. 277-280 [doi]
• SOAP - a speech output assessment package for controlled multilingual evaluation of synthetic speechP. A. Howard-Jones. 281-284 [doi]
• A physical approach to speech quality assessment: correlation patterns in the speech spectrogramTammo Houtgast, Jan A. Verhave. 285-288 [doi]
• Weighted MTF for predicting speech intelligibility in reverberant sound fieldsH. Miyata, Tammo Houtgast. 289-292 [doi]
• Speech intelligibility studies for the european hermes spaceplaneUte Jekosch. 293-296 [doi]
• An application of speech processing and encoding scheme for Chinese lexical tone and consonant perception by hearing impaired listenersJianing Wei, Andrew Faulkner, Adrian Fourcin. 299-302 [doi]
• On the development of a phone communication aid for the hearing impairedDimitri Kanevsky, P. Gopalakrishan, Catalina Danis, G. Daggett, E. Epstein, David Nahamoo. 303-306 [doi]
• A spoken language interface for a telephone switchboard operator centerYolande Anglade, Jean-Marie Pierrel, Jean-Claude Junqua. 307-310 [doi]
• A communication system for the disabled with emotional synthetic speech produced by ruleIain R. Murray, John L. Arnott, Norman Alm, Alan F. Newell. 311-314 [doi]
• German speech synthesis by concatenation of non-parametric unitsThomas Portele, Birgit Steffan, Rainer Preuß, Wolfgang Hess. 317-320 [doi]
• Automatic document reader with speech output capabilitiesGiuseppe Abbattista, Antonello Riccio, Enzo Mumolo. 321-324 [doi]
• Tools and processes for developing low-cost and high-quality text-to-speech synthesis for communication aidsR. W. King. 325-329 [doi]
• Perceptual linear predictive (PLP) analysis-resynthesis techniqueHynek Hermansky, Louis Anthony Cox Jr.. 329-332 [doi]
• A display technique for measurements of natural and synthetic articulatory dynamicsReinhold Greisbach, Bernd J. Kröger, O. Esser, G. Plaßmann. 333-336 [doi]
• Statistical models for the Chinese text-to-speech systemYueh-Chin Chang, Yi-Fan Lee, Bang-Er Shia, Hsiao-Chuan Wang. 337-340 [doi]
• A realtime speech synthesis systemP. A. Taylor, I. A. Nairn, Andrew M. Sutherland, Mervyn A. Jack. 341-344 [doi]
• Voice tranformation using PSOLA techniqueHélène Valbret, Eric Moulines, Jean-Pierre Tubach. 345-348 [doi]
• Phonetic ergodic HMM for speech synthesisMassimo Giustiniani, Piero Pierucci. 349-352 [doi]
• Quality evaluation of text-to-speech synthesizers using magnitude estimation, categorical estimation, pair comparison and reaction time methodsCristina Delogu, P. Paoloni, Paolo Pocci, Ciro Sementina. 353-356 [doi]
• Neural nets and hidden Markov models: review and generalizationsHervé Bourlard. 363-369 [doi]
• Coding of wideband speechN. S. Jayant, J. D. Johnston, Y. Shoham. 373-379 [doi]
• Stochastic representation of semantic structure for speech understandingRoberto Pieraccini, Esther Levin. 383-386 [doi]
• Incorporating probabilities into the dualgram language modelColin Matheson, Fergus R. McInnes. 387-390 [doi]
• A dynamic programming based framework for stochastic spoken language understandingEgidio P. Giachin. 391-394 [doi]
• Learning language models through the ECGI methodNatividad Prieto, Enrique Vidal. 395-398 [doi]
• Using a generative grammar to train a probabilistic language model for speaker-independent speech recognitionRoberto Cremonini, Marco Ferretti, M. C. Galimberti, Giulio Maltese, Federico Mancini. 399-402 [doi]
• Optimal construction of context sensitive quantizer for phoneme recognition in continuous speechKatsuhiko Shirai, E. Kitagawa, T. Endo. 405-408 [doi]
• Generalising from single-speaker recognition in a feature-based recogniserMary O Kane, P. E. Kenne, D. Landy, S. Atkins. 409-412 [doi]
• Improved speech recognition using high-pass filtering of subband envelopesH. G. Hirsch, Peter Meyer, Hans-Wilhelm Rühl. 413-416 [doi]
• Comparing two phoneme identification methods using a continuous speech recognizerYifan Gong, Jean-Paul Haton. 417-420 [doi]
• Knowledge-based phoneme recognitionD. Ederveen, Louis Boves. 421-424 [doi]
• Speaker characterization in dutch using prosodic parametersJ. Kraayeveld, A. C. M. Rietveld, Vincent J. van Heuven. 427-430 [doi]
• Analytical strategy for speaker identificationJean-François Bonastre, Henri Meloni, Philippe Langlais. 435-438 [doi]
• Optimization of perceptually-based spectral transforms in speaker identificationL. Xu, John S. Mason. 439-442 [doi]
• A mixed speech F0 estimation algorithmAlain de Cheveigné. 445-448 [doi]
• A perceptually-based pitch extractor for band-limited speechEdward Jones, Eliathamby Ambikairajah. 449-452 [doi]
• A robust pseudo perceptual pitch estimatorYu-Hua Gu. 453-456 [doi]
• Pitch estimation based on a "narrowed" autocorrelation functionNeviano Dal Degan, Marco Fratti. 457-460 [doi]
• The syntax-oriented spoken Japanese understanding system SPOJOS-SYNO IISeiichi Nakagawa, Yoshimitsu Hirata, Isao Murase. 463-466 [doi]
• An adaptable man-machine interface using connected-word recognitionHenning Bergmann, Hans-Hermann Hamer, Andreas Noll, Annedore Paeseler, Horst Tomaschewski. 467-470 [doi]
• An approach to automatic recognition of keywords in unconstrained speech using parametric modelsM. J. Poza, C. de la Torre, Daniel Tapias, Luis Villarrubia. 471-474 [doi]
• Toward vocabulary-independent recognition of telephone speechI. Lee Hetherington, Hong C. Leung, Victor W. Zue. 475-478 [doi]
• English alphabet recognition with telephone speechRonald A. Cole, Krist Roginski, Mark A. Fanty. 479-482 [doi]
• Evolutionary language models in air traffic control trainingJ.-Y. Fiset, Jean-Marc Robert, Raymond Descout. 483-486 [doi]
• Isolated-word sentence recognition using probabilistic context-free grammarGareth J. F. Jones, Jeremy H. Wright, E. N. Wrigley, Michael J. Carey 0002, Eluned S. Parris. 487-489 [doi]
• A look-ahead search technique for large vocabulary continuous speech recognitionReinhold Haeb-Umbach, Hermann Ney. 495-498 [doi]
• Spectral subtraction for front-end noise reduction in a speech recognizerCarlos Teixeira, Isabel Trancoso. 499-502 [doi]
• BREF, a large vocabulary spoken corpus for FrenchLori F. Larnel, Jean-Luc Gauvain, Maxine Eskenazi. 505-508 [doi]
• Speech field databases: development and analysisLuc Mathan, Dominique Morin. 509-512 [doi]
• Large scale Japanese dialect speech corporaShuichi Itahashi. 513-516 [doi]
• Assessment of continuous speech recognisers using recogniser sensitivity analysisRichard Winski, Kamran Kordi. 521-524 [doi]
• A tool for assessment of acoustic phonetic latticesC. Bourjot, A. Boyer, D. Fohr. 525-528 [doi]
• Ramos - recognizer assessment by means of manipulation of speech applied to connected speech recognitionHerman J. M. Steeneken, Jeroen G. van Velden. 529-532 [doi]
• Comparing various feature vectors in automatic speech recognitionPaul van Alphen, Louis C. W. Pols. 533-536 [doi]
• The MIT ATIS system; preliminary development, spontaneous speech data collection, and performance evaluationVictor W. Zue, James R. Glass, David Goodine, Lynette Hirschman, Hong C. Leung, Michael S. Phillips, Joseph Polifroni, Stephanie Seneff. 537-540 [doi]
• Construction of an Arabic speech data base - duration model of Arabic vowelsS. Benaouicha, A. Rajouani, M. Zyoute. 541-544 [doi]
• Pitch extraction and separation of overlapping speechP. N. Denbigh, J. Zhao. 545-548 [doi]
• Phonetically motivated acoustic parameters for continuous speech recognition using artificial neural networksYoshua Bengio, Renato de Mori, Giovanni Flammia, Ralf Kompe. 551-554 [doi]
• Adapting input transformations using alpha-nets for whole word speech recognitionMichael J. Carey, Eluned S. Parris. 555-558 [doi]
• TIMIT phoneme recognition using an HMM-derived recurrent neural networkLes T. Niles. 559-562 [doi]
• ANN-based speech recognition using a preprocessor for non-linear time compressionP. O. Husoy, Torbjørn Svendsen. 563-566 [doi]
• A self-structuring neural noise reduction modelHelge B. D. Sørensen, Uwe Hartmann. 567-570 [doi]
• Utilizing empirical data for postposition classification toward spoken Japanese speech recognitionJunko Hosaka, Toshiyuki Takezawa, Terumasa Ehara. 573-576 [doi]
• Automatic learning of lexical representations for sub-word unit based speech recognition systemsMichael S. Phillips, James R. Glass, Victor W. Zue. 577-580 [doi]
• Lexical tree compressionRoxane Lacouture, Renato de Mori. 581-584 [doi]
• Lexical access with a statistically-derived phonetic networkMichael D. Riley, Andrej Ljolje. 585-588 [doi]
• Admissible strategies for acoustic matching with a large vocabularyGiuliano Antoniol, Fabio Brugnara, Diego Giuliani. 589-592 [doi]
• Frame substitution and adaptive post-filtering in speech codingDaniele Sereno. 595-598 [doi]
• Effective lost speech frame reconstruction for CELP codersS. A. Atungsiri, R. Soheili, Ahmet M. Kondoz, Barry G. Evans. 599-602 [doi]
• Evaluation and improvement of coded speech quality degraded by cell loss in ATM networksHiromi Nagabuchi, Nobuhiko Kitawaki. 603-606 [doi]
• Combined source-channel coding for a very noisy channedAlain J. Vigier. 607-610 [doi]
• Testing and quality enhancement of the GSM full rate voice channelG. Rosina, M. Sant' Agostino, E. Turco, Luigi Vetrano. 611-614 [doi]
• Generation of duration rules for a Spanish text-to-speech synthesizerAlejandro Macarrón, J. Gregorio Escalada, Miguel Angel Rodriguez. 617-620 [doi]
• Implementing duration expert rules into a text-to-speech synthesis systemL. Mortamet. 621-624 [doi]
• Statistical modeling of segmental duration and power control for JapaneseNobuyoshi Kaiki, Katsuhiko Mimura, Yoshinori Sagisaka. 625-628 [doi]
• Phrase-level factors affecting timing in speechW. Nick Campbell. 629-632 [doi]
• Phoneme duration rules for speech synthesis by neural networksMatti Karjalainen, Toomas Altosaar. 633-636 [doi]
• Context-sensitive phoneme lattice generation using interpolated demi-diphone and triphone modelsFergus R. McInnes. 639-642 [doi]
• Experiments of 991-word speaker independent continuous speech recognition on DARPA RM taskJ. M. Song, T. Thomas, M. Patel. 643-646 [doi]
• Bottom-up acoustic-phonetic decoding for the selection of word cohorts from a large vocabularyHenri Meloni, Frédéric Bechet, Philippe Gilles. 647-650 [doi]
• Entropic training for HMM speech recognitionAntonio M. Peinado, Ramon Román, José C. Segura, Antonio J. Rubio, Pedro García, Jesús E. Díaz-Verdejo. 651-654 [doi]
• Energy, duration and Markov modelsPatrick Kenny, S. Parthasarathy, V. N. Gupta, Matthew Lennig, Paul Mermelstein, Douglas D. O Shaughnessy. 655-658 [doi]
• Context-sensitive phoneme lattice generation using interpolated demi-diphone and triphone modelsFergus R. McInnes. 663-666 [doi]
• An efficient implementation of the n-best algorithm for lexical accessPeter Nowell, Henry S. Thompson. 667-670 [doi]
• Automatic derivation of HMM alternative pronunciation network topologiesAlessandro Falaschi, Massimo Pucci. 671-674 [doi]
• On the structure of subword units for a speaker independent continuous speech taskIsabel Galiano, Francisco Casacuberta, Emilio Sanchis. 675-678 [doi]
• Generate word transcription dictionary from sentence utterances and evaluate its effect on speaker-independent continuous speech recognitionYunxin Zhao, Hisashi Wakita, Xinhua Zhuang. 679-682 [doi]
• Multi-lingual acoustic-phonetic features for a number of european languagesPaul Dalsgaard, Ove Andersen, William J. Barry. 685-688 [doi]
• A non-linear filtering method applied to automatic segmentation of multilingual speech corporaHarouna Kabré, Guy Perennou, Nadine Vigouroux. 689-692 [doi]
• A preliminary statistical evaluation of manual and automatic segmentation discrepanciesPiero Cosi, Daniele Falavigna, Maurizio Omologo. 693-696 [doi]
• A computational tool for examining lexical segmentation in continuous speechJames M. McQueen, Edward John Briscoe. 697-700 [doi]
• On-line speech segmentation using adaptive models: application to variable rate speech codingG. Feng, N. Achab, R. Combescure. 705-708 [doi]
• Automatic diphone segmentationP. A. Taylor, Stephen D. Isard. 709-711 [doi]
• An automatic diphone segmentation systemGeorg Ottesen. 713-716 [doi]
• An evaluation oof spectral transitivity functions for speech segmentation in variable frame-rate speech vocodingRichard Brierton, Barry M. G. Cheetham. 717-720 [doi]
• Speaker clustering for dialectic robustness in speaker independent recognitionDirk Van Compernolle, J. Smolders, P. Jaspers, T. Hellemans. 723-726 [doi]
• Experience with speech recognition in automating telephone operator functionsDina Yashchin, William C. G. Ortel. 727-730 [doi]
• HMM modeling in the public telephone network environment: experiments and resultsF. Canavesio, Lorenzo Fissore, Mario Oreglia, P. Ruscitti. 731-734 [doi]
• Influence of field data in HMM training for a vocal serverDominique Morin. 735-738 [doi]
• An isolated word speech recognizer prototype for mobile-radio applicationsAlberto Ciaramella, Lorenzo Fissore, Alberto Pacchiotti, Roberto Pacifici. 739-742 [doi]
• Linguistic modelling for a speech interface in the office contextJames Monaghan, Christine Cheepen. 745-748 [doi]
• Ill-formedness problem in the spoken language processingAndrea Di Carlo, Rino Falcone. 749-752 [doi]
• A technique to automatically assign parts-of-speech to words taking into account word-ending information through a probabilistic modelGiulio Maltese, Federico Mancini. 753-756 [doi]
• Syntactic category disambiguation through relaxation processesMarcello Pelillo, Mario Refice. 757-760 [doi]
• Computational requirements of probabilistic LR parsing for speech recognition using a natural language grammarE. N. Wrigley, Jeremy H. Wright. 761-764 [doi]
• Phonotypical transcription through the GEPH expert systemJ. Tihoni, G. Pérennon. 767-770 [doi]
• A spelling corrector for use in text-to-speech synthesis for EnglishBriony Williams, Franziska Maier. 771-774 [doi]
• Robust and efficient parsing for applications such as text-to-speech conversionThomas Russi. 775-778 [doi]
• Stochastic transduction for English text-to-phoneme conversionRobert W. P. Luk, Robert I. Damper. 779-782 [doi]
• Acoustic distribution clustering in phonetic hidden Markov modelsMei-Yuh Hwang, Xuedong Huang. 785-788 [doi]
• Modelling articulatory inter-timing variation in a speech recognition system based on synthetic referencesMats Blomberg. 789-792 [doi]
• Improving short-time speech frame recognition results by using contextKari Torkkola, Mikko Kokkonen, Mikko Kurimo, Pekka Utela. 793-796 [doi]
• Phoneme to grapheme conversion using HMMPanagiotis A. Rentzepopoulos, George K. Kokkinakis. 797-800 [doi]
• A bi-directional model of English pronunciationS. H. Parfitt, R. A. Sharman. 801-804 [doi]
• Variable rate speech coding using perceptive thresholds and adaptive VUS detectionPeter Meyer, W. Peters, J. Paulus. 809-812 [doi]
• A secure and robust CELP coder for land and satellite mobile systemsM. R. Suddle, S. A. Atungsiri, Ahmet M. Kondoz, Barry G. Evans. 813-816 [doi]
• A 4.8 kbps celp coder with post-processingCarlos M. Ribeiro, Isabel Trancoso. 817-820 [doi]
• A real-time high quality joint-excitation linear predictive coder at 8 kbpsK. W. Law, O. Y. Wong, C. F. Chan. 821-824 [doi]
• Some experiments in perceptual masking of quantizing noise in analysis-by-synthesis speech codersRosario Drogo Deiacovo, Roberto Montagna. 825-828 [doi]
• A very high-quality CELP coder at the rate of 2400 bpsGao Yang, Henri Leich, René Boite. 829-832 [doi]
• A vocoder using high-order LPC filter with very few non-zero coefficientsC. F. Chan, S. H. Leung. 839-842 [doi]
• Full integration of speech and language understanding in the MIT spoken language systemDavid Goodine, Stephanie Seneff, Lynette Hirschman, Michael S. Phillips. 845-848 [doi]
• Dialogue interpretation model and its application to next utterance prediction for spoken language processingTakayuki Yamaoka, Hitoshi Iida. 849-852 [doi]
• Dialogue management in an extension number guidance systemIzuru Nogaito, Masahiko Takahashi, Shingo Kuroiwa, Fumihiro Yato. 857-860 [doi]
• Automatic learning of acoustic and syntactic-semantic levels in continuous speech understandingEncarna Segarra, Pedro Garcia. 861-864 [doi]
• A man-machine dialogue system for speech access to e-mail information using the telephone: implementation and first resultsPaolo Baggia, Alberto Ciaramella, Davide Clementino, Lorenzo Fissore, Elisabetta Gerbino, Egidio P. Giachin, Giorgio Micca, Luciano Nebbia, Roberto Pacifici, G. Pirani, Claudio Rullent. 865-868 [doi]
• Performance of text-to-speech conversion for dutch: a comparative evaluation of allophone and diphone based synthesis at the level of the segment, the word, and the paragraphRenée van Bezooijen, Louis C. W. Pols. 871-874 [doi]
• Quality comparisons of prosodic and of acoustic components of various synthesisersChristian Benoît, Françoise Emerard, Betina Schnabel, A. Tseva. 875-878 [doi]
• Assessment of intonation in text-to-speech synthesis systems - a pilot test in English and ItalianMartine Griee, Kiki Vagges, Daniel Hirst. 879-882 [doi]
• Evaluation of the naturalness of prosody generated by the CSTR TTS systemAlex I. C. Monaghan. 883-886 [doi]
• Speech-model processes for objective quality measurements of speech-coding systemsUlrich Halka. 887-890 [doi]
• Low bit rate speech coding using CELP with adaptive excitation codebookU. Kipper, Herbert Reininger, Dietrich Wolf. 893-896 [doi]
• A real-time implementable 7 khz speech coder at 16 kbit/sArild Fuldseth, E. Harborg, F. T. Johansen, J. E. Knudsen. 897-900 [doi]
• Adaptive spectral weighting for vector predictive coding of the LPC-spectraD. J. Zarkadis. 901-904 [doi]
• Medium band speech coding using optimal scalar quantization of LSPSamir Saoudi, Jean-Marc Boucher, Alain Le Guyader. 905-908 [doi]
• Joint source and channel coding of line spectrum pairsPhilip Secker, Andrew Perkis. 909-912 [doi]
• An algorithm for computing LSP frequencies directly from the reflection coefficientsC. F. Chan, K. W. Law. 913-916 [doi]
• Adaptation techniques in tied density hidden Markov modelsStephan Euler. 919-922 [doi]
• On the modelization of allophones in an HMM based speech recognition systemDenis Jouvet, Katarina Bartkova, Jean Monné. 923-926 [doi]
• Automatic adjustments of the structure of Markov models for speech recognition applicationsDenis Jouvet, Laurent Mauuary, Jean Monné. 927-930 [doi]
• Speech recognition using stochastic explicit-segment modelingHong C. Leung, I. Lee Hetherington, Victor W. Zue. 931-934 [doi]
• Comparison of time-dependent acoustic features for a speaker-independent speech recognition systemD. Dubois. 935-938 [doi]
• Bayesian learning for hidden Markov model with Gaussian mixture state observation densitiesJean-Luc Gauvain, Chin-Hui Lee. 939-942 [doi]
• Voice controlled mail ordering via telephone using SPREINHans-Wilhelm Rühl. 945-948 [doi]
• A voice dialling device for mobile radioStefan Dobler, Werner Armbruester, Peter Meyer, Hans-Wilhelm Rühl. 949-952 [doi]
• A continuous speech recognition approach for the design of a dictation machineKamel Smaïli, François Charpillet, Jean-Marie Pierrel, Jean-Paul Haton. 953-956 [doi]
• Automatic speech recognition in the Spanish telephone networkDavid L. Thomson, Jay G. Wilpon, Rafid A. Sukkar, Dimitrios P. Prezas. 957-960 [doi]
• Computer-aided, voice-based, medical report preparation: an application to radiologyRoberto Billi, P. Buttafava, P. De Stefani, M. Gamba, D. Voltolini. 961-964 [doi]
• A recognition / synthesis system applied to database access through the telephone networkFilipe N. Carlos, Jose P. Carmona, Pedro M. Chagas, Luís C. Oliveira, António Joaquim Serralheiro, Isabel Trancoso. 965-968 [doi]
• An experiment in using a hypertext system in phonetics and speech processing educationSeppo Helle. 969-972 [doi]
• A. RE. s. : an interface for automatic reporting by speechGiuliano Antoniol, Fabio Brugnara, F. Dalla Palma, Gianni Lazzari, E. Moser. 973-976 [doi]
• COGNITO - an experimental voice-controlled telecommunication systemU. Schultheiß, Bernd Lochschmidt. 977-980 [doi]
• A voice interactive language instruction systemJared Bernstein, Dimitry Rtischev. 981-984 [doi]
• Macro and micro features for automated pronunciation improvement in the spell systemEdmund Rooney, Steven M. Hiller, John Laver, Maria-Gabriella Di Benedetto. 985-988 [doi]
• Comparison of continuous mixture densities and TDNN in a viterbi-framework: experiments on speaker dependent DARPA RM1+Laurence Devillers, Christian Dugast. 991-994 [doi]
• A comparison of two compression functions used for noisy vowel detection with back-propagation networksPeter Thurston, Dennis Norris. 995-998 [doi]
• Comparison between two different approaches in speaker - independent isolated digit recognitionJavier Ferreiros, A. Castro, José M. Pardo. 999-1002 [doi]
• DVQ: dynamic vector quantization application to speech processingFranck Poirier. 1003-1006 [doi]
• A comparative study on hybrid acoustic phonetic decoders based on artificial neural networksYoshua Bengio, Renato de Mori, Giovanni Flammia, Ralf Kompe. 1007-1010 [doi]
• Time-delay neural network architectures for high-performance speaker-independent recognitionHidefumi Sawai, Satoru Nakamura. 1011-1014 [doi]
• Recurrent neural nets as building blocks for human word recognitionPeter Wittenburg, R. Couwenberg. 1015-1018 [doi]
• A neural net model for vector quantizationFisseha Mekuria, Tore Fjällbrant. 1019-1022 [doi]
• Lexical access using a recurrent error propagation networkN. H. Russell, Frank Fallside, A. J. Robinson, Richard W. Prager. 1023-1026 [doi]
• Model or non-model based classifiersPeter Brauer, Per Hedelin, Dieter Huber, Petter Knagenhjelm, Johan Molno. 1027-1030 [doi]
• Event-based recognition and analysis of speech by neural networksToomas Altosaar, Matti Karjalainen. 1031-1034 [doi]
• Up from trigrams! - the struggle for improved language modelsFrederick Jelinek. 1037-1040 [doi]
• Synthesis: modelling variability and constraintsRolf Carlson. 1043-1048 [doi]
• The role of dialogue in speech recognition the case of the yellowMarc Guyomard, Jacques Siroux, Alain Cozannet. 1051-1054 [doi]
• Interpretation of context-dependent utterances in man-machine dialogueElisabetta Gerbino, Paolo Baggia. 1055-1058 [doi]
• The description of minor clauses in information-seeking telephone dialoguesS. Eggins, Julie Vonwiller, Christian Matthiessen, P. Sefton. 1059-1062 [doi]
• Toward a spoken language translator for restricted-domain context-free languagesDavid B. Roe, Fernando Pereira, Richard Sproat, Michael D. Riley, Pedro J. Moreno, Alejandro Macarrón. 1063-1066 [doi]
• Bidirectional machine translation in indian languagesN. Venkata Subramaniam, Narayanan Alwar, G. Mallikarjuna, P. Prabhakar Rao, Subramanian Raman. 1067-1070 [doi]
• Exact monitoring of the numerical error in various speech algorithmsConstantin Papaodysseus, E. Koukoutsis, C. Triantafillou, C. Vasilatos. 1073-1076 [doi]
• Automatic computation and comparison of dynamically varying voice source parametersJacques C. Koreman, Bert Cranen, Louis Boves. 1077-1080 [doi]
• Glottal wave analysis with pitch synchronous iterative adaptive inverse filteringPaavo Alku. 1081-1084 [doi]
• Generalized functional approximation for source-filter system modelingThierry Galas, Xavier Rodet. 1085-1088 [doi]
• An evaluation of temporal decompositionFrédéric Bimbot, Bishnu S. Atal. 1089-1092 [doi]
• A discriminative recognizer for isolated and continuous speech using statistical separability measuresKlaus Zünkler. 1095-1098 [doi]
• Speaker adaptation based on articulatory featuresOtto Schmidbauer, Harald Höge. 1099-1102 [doi]
• A parallel HMM approach to speech recognitionFabio Brugnara, Renato de Mori, Diego Giuliani, Maurizio Omologo. 1103-1106 [doi]
• Speaker independent word recognition using HMMs with an orthogonalized phonetic segment codebookTsuneo Nitta, Jun ichi Iwasaki, Hiroshi Matsu ura. 1107-1110 [doi]
• Unsupervised speaker normalization by speaker Markov model converter for speaker-independent speech recognitionPascale Fung, Tatsuya Kawahara, Shuji Doshita. 1111-1114 [doi]
• The influence of formant track shape on the perception of synthetic vowelsR. J. J. H. van Son, Louis C. W. Pols. 1117-1120 [doi]
• Fluctuation of noise background: measurement and significance in relation to speech maskingP. A. Howard-Jones. 1121-1124 [doi]
• The audibility of narrow band noise in fiat spectral complex soundsC. Ma, L. F. Willems. 1125-1128 [doi]
• The importance of spectral quality of vowels for the intelligibility of sentencesGitta P. M. Laan, Dick R. van Bergem, Florien J. Koopmans-van Beinum. 1129-1132 [doi]
• On the mutual dependency of octave-band-specific contributions to speech intelligibilityHerman J. M. Steeneken, Tammo Houtgast. 1133-1136 [doi]
• On the relation between voice source characteristics and prosodyHelmer Strik, Louis Boves. 1145-1148 [doi]
• Prosody in a rule-based norwegian text-to-speech systemSverre Stensby. 1149-1152 [doi]
• Synthesizing intonation for speech in hindiA. S. Madhukumar, S. Rajendran, C. Chandra Sekhar, B. Yegnanarayana. 1153-1156 [doi]
• An investigation of the relation between perceived pitch accent and automatically-located accent in british EnglishJames Hieronymus, Briony J. Williams. 1157-1160 [doi]
• Modelling Italian intonation in a text-to-speech systemSilvia Quazza. 1161-1164 [doi]
• An analysis of strategies for finding prosodic clues in textMichael H. O Malley, Howard Resnick, Michelle Caisse. 1165-1168 [doi]
• A coded dictionary for stress assignment rules in ItalianMarcello Balestri. 1169-1172 [doi]
• Simultaneous recognition of concurrent speech signals using hidden Markov model decompositionA. P. Varga, Roger K. Moore. 1175-1178 [doi]
• A large vocabulary parallel processing continuous speech recognition systemI. A. Ballantyne, Andrew M. Sutherland, J. M. Hannah, Mervyn A. Jack. 1179-1182 [doi]
• Techniques for robust word spotting in continuous speech messagesRichard C. Rose, Edward M. Hofstetter. 1183-1186 [doi]
• Word spotting by CSR through vector quantized background modelsAlessandro Falaschi, Alfredo Micozzi. 1187-1190 [doi]
• Towards an artificial laboratory for the design and simulation of cooperative speech processing algorithmsJean-Claude Junqua, Hisashi Wakita. 1191-1194 [doi]
• Accent specific modifications for continuous speech recognition based on a sub-word lattice approachKeith Edwards, Fergus R. McInnes, Mervyn A. Jack. 1195-1198 [doi]
• Two level continuous speech recognition using demisyllable-based HMM word spottingEduardo Lleida, José B. Mariño, Climent Nadeu, Albert Oliveras. 1199-1202 [doi]
• Tradeoffs in the design of regression features for word recognitionTed H. Applebaum, Brian A. Hanson. 1203-1206 [doi]
• A fast algorithm for deleted interpolationLalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer, David Nahamoo. 1209-1212 [doi]
• Recent work in continuous speech recognition using the connectionist viterbi training procedureMichael A. Franzini, Alex Waibel, Kai-Fu Lee. 1213-1216 [doi]
• A search organization for large-vocabulary recognition based on n-best decodingVolker Steinbiss. 1217-1220 [doi]
• VINICS: a continuous speech recognizer based on a new robust formulationYifan Gong, Jean-Paul Haton. 1221-1224 [doi]
• A matrix representation of HMM-based speech recognition algorithmsShigeki Sagayama. 1225-1228 [doi]
• Speech maker: text-to-speech conversion based on a multi-level, synchronized data structureEnrico te Lindert, Hugo van Leeuwen. 1231-1234 [doi]
• A new text-to-speech synthesis systemEric Lewis, Mark Tatham. 1235-1238 [doi]
• DIXI - portuguese text-to-speech systemLuís C. Oliveira, Céu Viana, Isabel Trancoso. 1239-1242 [doi]
• Higher-level linguistic information in a text-to-speech system for danishP. Molbaek Hansen, N. Reinholt Petersen, Jørgen Rischel, Carsten Henriksen. 1243-1246 [doi]
• Adaptation of the multivox text-to-speech system to ItalianGábor Olaszy. 1247-1250 [doi]
• Correlation analysis of vowels and their application to speech recognitionPartha Niyogi, Victor W. Zue. 1253-1256 [doi]
• Use of phonetic knowledge when designing and training stochastic models for speech recognitionJohn N. Holmes. 1257-1260 [doi]
• Modelling phones by microsegments in a phonetically oriented recognition systemBernhard Kaspar, Karlheinz Schuhmacher. 1261-1264 [doi]
• An extended LVQ2 algorithm and its application to phoneme classificationIl K. Kim, H. S. Lee. 1265-1268 [doi]
• A hierarchical broad phonetic classification schemeP. J. Dix, G. J. Vernooij, Gerrit Bloothooft. 1269-1272 [doi]
• Using text analysis to predict intonational boundariesJulia Hirschberg. 1275-1278 [doi]
• Why do speakers accent given information ?Merle Horne. 1279-1282 [doi]
• Automatic prosody assignment for interactive synthesized dialogue systemsJulie Vonwiller, R. W. King, R. W. T. Lloyd. 1283-1286 [doi]
• Generating intonation in a voice dialogue systemNickYoud NickYoud, Jill House. 1287-1290 [doi]
• Computing linguistic knowledge for text-to-speech systems with PROSORodolfo Delmonte, Roberto Dolci. 1291-1294 [doi]
• Acoustic echo cancellation using prediction residual signalsC. Acker, Peter Vary, H. Ostendarp. 1297-1300 [doi]
• An evaluation of adaptive noise cancelling for speech recognitionH. S. Dabis, Alan Wrench. 1301-1304 [doi]
• An efficient algorithm for real-time voiced/unvoiced decisionEnzo Mumolo, Antonello Riccio, Giuseppe Abbattista. 1305-1308 [doi]
• Models of pitch perceptionTim Aarset, Ben Gold. 1309-1312 [doi]
• A new perspective on LPC excitation using singular value decompositionP. Corney, John S. Mason. 1315-1318 [doi]
• Intra-speaker transplantation of speech characteristics an application of waveform vocoding techniques and DTWWerner Verhelst, Marcel Borger. 1319-1322 [doi]
• Decomposition of the LPC excitation using wavelet functionsS. H. Leung, O. Y. Wong, K. L. Lai. 1327-1330 [doi]
• An adaptive cochlear model for speech recognitionEliathamby Ambikairajah, Liam Kilmartin. 1331-1334 [doi]
• Speech segmentation and classification using higher order momentsGianni Jacovitti, Piero Pierucci, Alessandro Falaschi. 1335-1338 [doi]
• A PC-housed speaker independent large vocabulary continuous telephonic speech recognizerAlberto Ciaramella, Davide Clementino, Roberto Pacifici. 1341-1344 [doi]
• Speaker independent continuous HMM-based recognition of isolated words on a real-time multi-DSP systemAbdulmesih Aktas, Klaus Zünkler. 1345-1348 [doi]
• A real time speech decoder using instantaneous frequency and energyAnastasios Tsopanoglou, Efstathios D. Kyriakis-Bitzaros, J. Mourjopoulos, George K. Kokkinakis. 1349-1352 [doi]
• Fast hardware for efficient parallel processing of speech signalsM. Schultheiß, Arild Lacroix. 1353-1356 [doi]
• The one chip speech recognition systemJan Sedivý, Jiff Filcev, Jan Uhlír, Tomas Vanek, Václav Hanzl, Zdenek Oliva, Petr Kotek. 1357-1631 [doi]
• Influence of the telephone line on automatic speech recognitionLuis Villarrubia, M. J. Poza, C. Crespo. 1363-1366 [doi]
• Compensation for the effect of the communication channel in auditory-like analysis of speech (RASTA-PLP)Hynek Hermansky, Nelson Morgan, Aruna Bayya, Phil Kohn. 1367-1370 [doi]
• A study of endpoint detection algorithms in adverse conditions: incidence on a DTW and HMM recognizerJean-Claude Junqua, Ben Reaves, Brian Mak. 1371-1374 [doi]
• Speech enhancement in the case of speech recognizersKlára Vicsi. 1379-1381 [doi]
• A robust feature extraction method for automatic speech recognition in noisy environmentsJuan Gómez-Mena, J. Santos-Suarez, Ramón García Gómez. 1383-1386 [doi]
• Selection of speech units for a speaker-independent CSR taskLorenzo Fissore, Egidio P. Giachin, Pietro Laface, Giorgio Micca. 1389-1392 [doi]
• Word juncture modeling using inter-word context-dependent phone-like unitsEgidio P. Giachin, Chin-Hui Lee, Lawrence R. Rabiner, Aaron E. Rosenberg, Roberto Pieraccini. 1393-1396 [doi]
• Phoneme-context-dependent LR parsing algorithms for HMM-based continuous speech recognitionAkito Nagai, Shigeki Sagayama, Kenji Kita. 1397-1400 [doi]
• Optimizing lexical fast search in a large vocabulary isolated word speech recognition systemH. Drexler, R. Roddeman, Louis Boves, Helmer Strik. 1401-1404 [doi]
• Integrated phoneme-function word architecture of hidden control neural networks for continuous speech recognitionBojan Petek, Alex Waibel, Joseph M. Tebelskis. 1407-1410 [doi]
• Multiple dynamic features to enhance neural net based speaker verificationX. Zhang, John S. Mason, E. C. Andrews. 1411-1414 [doi]
• Time-delay neural networks embedding time alignment: a performance analysisPatrick Haffner, Alex Waibel. 1415-1418 [doi]
• Phoneme recognition using recurrent neural networksYohji Fukuda, Haruya Matsumoto. 1419-1423 [doi]
• An integration of knowledge and neural networks toward a phoneme typewriter without a language modelYasuhiro Komori, Kaichiro Hatazaki. 1423-1426 [doi]
• Signal processing using an auditory filter bank with side-lobes and phase-jumpsTore Fjällbrant, Fisseha Mekuria. 1429-1431 [doi]
• An auditorily based spectral transformation of speech signalsManfred Beham. 1437-1440 [doi]
• On and off units detect information bottle-necks for speech recognitionAndrew C. Morris, Pierre Escudier, Jean-Luc Schwartz. 1441-1444 [doi]
• Detection times for vowels versus consonantsBrit van Ooyen, Anne Cutler, Dennis Norris. 1451-1454 [doi]
• The influence of sentence accent, word stress, and word class on the quality of vowelsDick R. van Bergem. 1455-1458 [doi]
• A peak-and-level model for focus words in read and spontaneous natural speech and in synthetic speechFlorien J. Koopmans-van Beinum. 1459-1462 [doi]
• Connected speech processes in second language learningJohn Ingram, Jeff Pittam. 1463-1466 [doi]
• Speech understanding and dialogue over the telephone: an overview of progress in the sundial projectJeremy Peckham. 1469-1472 [doi]
• A system for natural spoken language queries design, implementation and assessmentJean-Pierre Tubach, P. Doignon. 1473-1476 [doi]
• Operational validation of syntactic-semantic models in a spoken man-machine dialogue systemGuy Deville, Pierre Mousel. 1477-1480 [doi]
• References in a multimodal dialogue: towards a unified processingBertrand Gaiffe, Laurent Romary, Jean-Marie Pierrel. 1481-1485 [doi]
• The user-unix dialogue: a novel integrated approach to enhancing the operating system interfacePierre Lefebvre, G. Duncan, Frank Poirier. 1487-1490 [doi]
• The contribution of vision to speech perceptionPaula M. T. Smeele, Anne C. Sittig. 1495-1497 [doi]
• Processing disfluent speech: how and when are disfluencies found?Robin J. Lickley, R. C. Shillcock, Ellen Gurman Bard. 1499-1502 [doi]
• Building a user interface for a speech recognition-based telephone application systemA. Chointere, Jean-Marc Robert, Raymond Descout. 1503-1506 [doi]
• System design and human factors in auditory interfacesA. C. Murray, Clive Frankish, Dylan M. Jones. 1507-1510 [doi]