Table of Contents

• Text-dependent speaker verification using decoupled and integrated speaker and speech recognizersDouglas A. Reynolds, Beth A. Carlson. [doi]
• Applying phonetic knowledge to lexical accessKenneth N. Stevens. 3-14 [doi]
• Syllabic duration control for vocabulary-free speech recognitionTakatoshi Jitsuhiro, Tomokazu Yamada, Shigeki Sagayama. 15-18 [doi]
• Effectiveness of pause information in the content word detection of spoken dialoguesKazuyuki Takagi, Shuichi Itahashi. 19-22 [doi]
• Connected Japanese digit recognition with pitch accent-dependent modelsKazuhiro Kondo. 23-26 [doi]
• Temporal control and training selection for HMM-based systemClaude Barras, Marie-José Caraty, Claude Montacié. 27-30 [doi]
• HMM-based tone recognition of Chinese trisyllables using double codebooks on fundamental frequency and waveform powerKeikichi Hirose, Xinhni Hu. 31-34 [doi]
• Very low delay and high quality coding of 20 hz -15 khz speech at 64 kbit/SC. Murgia, Gang Feng, Catherine Quinquis, Alain Le Guyader. 37-40 [doi]
• Wideband CELP coder at 16-kbit/s with 10-ms frameShigeaki Sasaki, Akitoshi Kataoka, Takehiro Moriya. 41-44 [doi]
• High quality 14.1kb/s wideband speech coderA. W. Black, Ian A. Atkinson, Ahmet M. Kondoz, Barry G. Evans. 45-48 [doi]
• A multipulse-deconvolution codec for wideband speechVictoria Abreu-Sernández, Domingo Docampo-Amoedo. 49-52 [doi]
• Multi-channel linear predictive coding of audio signalsThierry Chonavel, Samir Saoudi. 53-56 [doi]
• Voice processing architecture for computer-telephony integrationRafael Ciria, Rafael Sarmiento de Sotomayor, Cristina Aguila, José Parera, Juan Santos. 63-66 [doi]
• Fast convergent analog adaptive filterL. Ortiz-Balbuena, Héctor M. Pérez Meana, A. Martinez-Gonzalez, L. Nino de Rivera, Mariko Nakano-Miyatake. 67-70 [doi]
• Efficient isolated word recognition in Spanish based on static modelingManuel A. Leandro, Alvaro Villegas, José Manuel Pardo. 71-74 [doi]
• Reliability in a multi-agent spoken language recognition systemJean-Luc Cochard, Olivier Oppizzi. 75-78 [doi]
• A study of speaker adaptation based on minimum classification error trainingTomoko Matsui, Sadaoki Furui. 81-84 [doi]
• Maximum likelihood based discriminative training of acoustic modelsAlbino Nogueiras Rodriguez, José B. Mariño. 85-88 [doi]
• Discriminant learning with minimum memory loss for improved non-vocabulary rejectionHugues Leprieur, Patrick Haffner. 89-92 [doi]
• Codebook weights adaptation for discriminative training of SCHMM-based speech recognition systemsCesar Martín del Alamo, F. Javier Caminero-Gil, Celinda de la Torre-Munilla, Lis Hernández-Gómez. 93-96 [doi]
• Discriminative training of hidden Markov models using overall risk criterion and reduced gradient methodKyungMin Na, Bumki Jeon, Dong-Il Chang, Soo-Ik Chae, SouGuil Ann. 97-100 [doi]
• Discriminative training of HMM based speech recognizer with gradient projection methodQiang Huo, Chorkin Chan. 101-104 [doi]
• Optimization of speech parameter weighting for CDHMM word recognitionJavier Hernando Pericas, J. Ayarte, Enric Monte. 105-108 [doi]
• Integrated optimization of feature transformation for speech recognitionStephan Euler. 109-112 [doi]
• Phoneme transition detection and broad classification using a simple model based on the function of onset detector cells found in the cochlear nucleusAndrew C. Morris, José M. Pardo. 115-118 [doi]
• Linear predictive coding of speech using an analogue cochlear modelEric Fragnière, André van Schaik, Eric A. Vittoz. 119-122 [doi]
• Pitch extraction of telephone bandwidth speech using a place-temporal approachEdward Jones, Eliathamby Ambikairajah. 123-126 [doi]
• A binaural selectivity model for speech recognitionMarkus Bodden, Timothy R. Anderson. 127-130 [doi]
• Speech recognition experiments in a noisy environment using auditory system modellingCristina Dobrin, Petri Haavisto, Kari Laurila, Jaakko Astola. 131-134 [doi]
• Source separation by a functional model of amplitude demodulationFrédéric Berthommier, Georg F. Meyer. 135-138 [doi]
• Real-time implementation of spectral subtraction algorithm for suppression of acoustic noise in speechVratislav Davidek, Pavel Sovka, Jiri Sika. 141-144 [doi]
• Speech synthesis for the new pan-european traffic message control system RDS-TMCBert Van Coile, Hans-Wilhelm Rühl, L. Vogten, M. Thoone, S. Goß, D. Delaey, E. Moons, Jacques M. B. Terken, Jan-Roelof de Pijper, M. Kugler, P. Kaufholz, R. Krüger, Steven Leys, S. Willems. 145-148 [doi]
• Echo cancelling in speech recognition systemsRoberto Pacifici, G. Manca. 149-152 [doi]
• Parallel implementation of an hybrid neural network used for speech recognition taskTeodoro Calonge Cano, L. Alonso, Rui Ralha, A. L. Sánchez. 153-156 [doi]
• Hardware design of LPC coding for speech feature extractionM. Li, J. T. Proudfoot. 157-160 [doi]
• Modularization in task-specific language modellingHenning Bergmann, Hans-Hermann Hamer, Andreas Noll, Annedore Paeseler, Horst Tomaschewski. 161-164 [doi]
• Beyond NYQUIST: towards the recovery of broad-bandwidth speech from narrow-bandwidth speechCarlos Avendaño, Hynek Hermansky, Eric A. Wan. 165-168 [doi]
• Auditory mechanisms for speech perceptionWilliam A. Ainsworth. 171-178 [doi]
• Large vocabulary multilingual speech recognition using HTKD. Pye, Philip C. Woodland, Steve J. Young. 181-184 [doi]
• Issues in Large Vocabulary, Multilingual Speech RecognitionLori Lamel, Martine Adda-Decker, Jean-Luc Gauvain. 185-188 [doi]
• Comparative performance in large-vocabulary isolated-word recognition in five european languagesJames Barnett, Paul G. Bamberg, Martin Held, Juan Huerta, Linda Manganaro, Adam Weiss. 189-192 [doi]
• French speech recognition in an automatic dictation system for translators: the transtalk projectJulie Brousseau, Caroline Drouin, George F. Foster, Pierre Isabelle, Roland Kuhn, Yves Normandin, Pierre Plamondon. 193-196 [doi]
• The Philips large-vocabulary recognition system for american English, French, and GermanChristian Dugast, Xavier L. Aubert, Reinhard Kneser. 197-200 [doi]
• A syllable-based very-large-vocabulary voice retrieval system for Chinese databases with textual attributesSung-Chien Lin, Lee-Feng Chien, Keh-Jiann Chen, Lin-Shan Lee. 203-206 [doi]
• The AT&t 60, 000 word speech-to-text systemMichael Riley, Andrej Ljolje, Donald Hindle, Fernando Pereira. 207-210 [doi]
• Fast and accurate continuous speech recognition for Chinese language with very large vocabularyTai-Hsuan Ho, Hsin-Min Wang, Lee-Feng Chien, Keh-Jiann Chen, Lin-Shan Lee. 211-214 [doi]
• Methods towards the very large vocabulary Chinese speech recognitionZuoying Wang, Jun Wu, Xi Xiao, Jin Quo. 215-218 [doi]
• Utterance clustering for large vocabulary continuous speech recognitionG. D. Cook, Anthony J. Robinson. 219-222 [doi]
• Vector quantization of glottal pulsesThomas Eriksson, Jan Linden, Jan Skoglund. 225-228 [doi]
• A speech coding algorithm based on prototypes interpolation with critical bands and phase codingMichele Festa, Daniele Sereno. 229-232 [doi]
• Very low-bitrate speech coding using perceptually-derived spectral dataD. E. Tsoukalas, Jiannis Mouropoulos, George Kokkinakis. 233-236 [doi]
• A new very low bit rate speech coder: the step decomposition vocoderLorenzo Piazzo. 237-240 [doi]
• Time envelope LP vocoder: a new coding technique at very low bit ratesIan A. Atkinson, Ahmet M. Kondoz, Barry G. Evans. 241-244 [doi]
• Shift-invariant adaptive local trigonometric decompositionIsrael Cohen, Shalom Raz, David Malah. 247-250 [doi]
• Spectral envelope of speech using waveletsPaul Micallef, Edward Chilton. 251-254 [doi]
• Multiresolution speech analysis using fast time-varying orthogonal wavelet packet transform algorithmsAndrzej Drygajlo, Nicolas Thevoz. 255-258 [doi]
• Second- and third-order wigner distributions in hierarchical recognition of speech phonemesMaria Rangoussi, Flemming Pedersen. 259-262 [doi]
• The use of maximum a posteriori parameters in linear prediction of speechGaafar M. K. Saleh, Mahesan Niranjan, W. J. Fitzgerald. 263-268 [doi]
• Observed long-term changes in customer calling patterns in a telephone application using automatic speech recognitionWilliam C. G. Ortel. 269-272 [doi]
• Combining speech algorithms into a natural application of speech technology for telephone network servicesAyman Asadi, David Lubensky, L. Madhavrao, Jayant M. Naik, Vijay Raman, George Vysotsky. 273-276 [doi]
• Intelligent answering machine-secretaryYevgeny Ludovik, Valeriy Sibirtsev. 277-280 [doi]
• Verbal-gestural behaviors in multimodal spoken language interpreting telecommunicationsKyung-ho Loken-Kim, Young-Duk Park, Suguru Mizunashi, Laurel Fais, Tsuyoshi Morimoto. 281-284 [doi]
• Large vocabulary, word-based Mandarin dictation systemJung-Kuei Chen, Lin-Shan Lee, Frank K. Soong. 285-288 [doi]
• Read my lips... and my jaw! how intelligible are the components of a speaker s face?Bertrand Le Goff, Thierry Guiard-Marigny, Christian Benoît. 291-294 [doi]
• Rule-based visual speech synthesisJonas Beskow. 299-302 [doi]
• A new algorithm for visual synthesis of speechFabio Lavagetto, Paolo Lavagetto. 303-306 [doi]
• Audiovisual speech recognition using the fuzzy shape filters modelHarouna Kabré. 307-310 [doi]
• On the use of features from prediction residual signals in speaker identificationJialong He, Li Liu, Günther Palm. 313-316 [doi]
• Some nonparametric distance measures in speaker verificationKai Tat Ng, Haizhou Li, Jean-Paul Haton. 317-320 [doi]
• Adaptive transforms for speaker recognitionMichael J. Carey, Graham Tattersall, Eluned S. Parris. 321-324 [doi]
• Speaker recognition with discriminative speaker VQ modelsKai Tat Ng, Jian Su, Bingzheng Xu. 325-328 [doi]
• Parametric speaker recognition over large population of telephonic voicesA. Federico, Andrea Paoloni. 329-332 [doi]
• Speaker recognition experiments in Estonian using multi-layer feed-forward neural netsToomas Altosaar, Einar Meister. 333-336 [doi]
• Effect of utterance duration and phonetic content on speaker identification using second-order statistical methodsIvan Magrin-Chagnolleau, Jean-François Bonastre, Frédéric Bimbot. 337-340 [doi]
• Automatic speaker recognition using formants-based nearest-neighbour distance measurePavel V. Labulin, Sergey L. Koval, Andrey N. Raev. 341-344 [doi]
• Discrimination of voices of twins and siblings for speaker verificationM. Mehdi Homayounpour, Gérard Chollet. 345-348 [doi]
• Theoretical error prediction for a language identification system using optimal phoneme clusteringKay M. Berkling, Etienne Barnard. 351-354 [doi]
• Separation of speakers in audio dataJesper Ø. Olsen. 355-358 [doi]
• Text-dependent speaker verification using dynamic time warping and vector quantization of LSFJ.-L. Bonifas, I. Hernaez Rioja, B. Etxebarria Gonzalez, S. Saoudi. 359-362 [doi]
• On MMI learning of Gaussian mixture for speaker modelsHaizhou Li, Jean-Paul Haton, Yifan Gong. 363-366 [doi]
• Evaluation of Bayes decision approach to automatic determination of thresholds for speaker verificationYifan Gong. 367-370 [doi]
• Comparison of different HMM based methods for speaker verificationDaniele Falavigna. 371-374 [doi]
• Speaker classification by neural network for short utteranses using phoneme groups in FarsiJ. Sheikhzadegan, M. Tebiani, M. Lotfizad, Mahmood R. Roohani. 375-378 [doi]
• Speaker recognition experiments on the NTIMIT databaseJean-Luc Le Floch, Claude Montacié, Marie-José Caraty. 379-382 [doi]
• Speaker identification using vector quantisation with codeword-specific derivative codingMichael Wagner, John S. Mason, J. Bruce Millar. 383-386 [doi]
• A voiced/unvoiced speech discrimination technique based on fuzzy logicFrancesco Beritelli, Salvatore Casale, Marco Russo. 389-392 [doi]
• Evaluation of a periodic/aperiodic speech decomposition algorithmVassilios Darsinos, Christophe d Alessandro, B. Yegnanarayana. 393-396 [doi]
• A pitch determination and voiced/unvoiced decision algorithm for noisy speechJean Rouat, Yong Chun Liu, Daniel Morissette. 397-400 [doi]
• Modulated Gaussian wavelet transform based speech analyser (MGWTSA) pitch detection algorithm (PDA)Léonard Janer. 401-404 [doi]
• A time-frequency approach to epoch detectionJuan L. Navarro-Mesa, Ignasi Esquerra-Llucia. 405-408 [doi]
• An improved epoch detection algorithm based on sinusoidal modelling of speechM. L. Larreategui, F. J. Ancin, R. A. Carrasco. 409-412 [doi]
• A method for fully automatic analysis and modelling of voice source characteristicsVassilios Darsinos, Dimitrios Galanis, George Kokkinakis. 413-416 [doi]
• Dynamic vowel quality: a new determination formalism based on perceptual experimentsHartmut R. Pfitzinger. 417-420 [doi]
• A method for quantitative analysis of the local speech rateSumio Ohno, Hiroya Fujisaki. 421-424 [doi]
• Voice personality transformation using an orthogonal vector space conversionKi-Seung Lee, Dae Hee Youn, Il Whan Cha. 427-430 [doi]
• Spectral mapping for voice conversion using speaker selection and vector field smoothingMakoto Hashimoto, Norio Higuchi. 431-435 [doi]
• Analysis of acoustic features affecting speaker identificationNorio Higuchi, Makoto Hashimoto. 435-438 [doi]
• Speaker individualities in fundamental frequency contours and its controlMasato Akagi, Taw Ienaga. 439-442 [doi]
• Interpolating MBE v/UV mixture function for high quality synthesis of speechKing-fai Lam, Cheung-fat Chan. 443-447 [doi]
• Statistical methods for voice quality transformationYannis Stylianou, Olivier Cappé, Eric Moulines. 447-450 [doi]
• High-quality speech modification based on a harmonic + noise modelYannis Stylianou, Jean Laroche, Eric Moulines. 451-454 [doi]
• Source generator based stressed speech perturbationSahar E. Bou-Ghazah, John H. L. Hansen. 455-458 [doi]
• Improved algorithms for speech recognition in noise using lateral inhibition and SNR weightingNéstor Becerra Yoma, Fergus R. McInnes, Mervyn A. Jack. 461-464 [doi]
• Noise adaptation using linear regression for continuous noisy speech recognitionOlivier Siohan, Yifan Gong, Jean-Paul Haton. 465-468 [doi]
• Dynamic parameter compensation for speech recognition in noiseRuikang Yang, Markku Majaniemi, Petri Haavisto. 469-472 [doi]
• Robust speech recognition in noise using speech enhancement based on masking properties of the auditory system and adaptive HMMAndrzej Drygajlo, Nathalie Virag, Gregoire Cosendai. 473-476 [doi]
• Canonical correlation based compensation approach for robust speech recognition in noisy environmentDong Yu, Taiyi Huang. 477-480 [doi]
• A unified approach for robust speech recognitionPedro J. Moreno, Bhiksha Raj, Richard M. Stern. 481-484 [doi]
• Effect of rasta-type processing for speech recognition with speaking-rate mismatchesHarald Singer, Kuldip K. Paliwal, Tomohiko Beppu, Yoshinori Sagisaka. 487-490 [doi]
• Fast speakers in large vocabulary continuous speech recognition: analysis & antidotesNikki Mirghafori, Eric Foster, Nelson Morgan. 491-494 [doi]
• Signal conditioned minimum error rate trainingWu Chou, Mazin G. Rahim, Eric Buhrke. 495-498 [doi]
• Non-uniform unit HMMS for speech recognitionTakeshi Matsumura, Shoichi Matsunaga. 499-502 [doi]
• Training data clustering for improved speech recognitionAnanth Sankar, Françoise Beaufays, Vassilios Digalakis. 503-506 [doi]
• On the use of bi-directional contextual dependence in acoustic modeling for speech recognitionQiang Huo, Chorkin Chan. 507-510 [doi]
• Spontaneous speech recognition using dynamic CEPSTRA incorporating forward and backward masking effectTomohiko Beppu, Kiyoaki Aikawa. 511-514 [doi]
• Stochastic trajectory models for speech recognition: an extension to modelling time correlationMohamed Afify, Yifan Gong, Jean-Paul Haton. 515-518 [doi]
• An analysis of cepstral-time matrices for noise and channel robust speech recognitionBen P. Milner, Saeed Vaseghi. 519-522 [doi]
• A confidence measure for acoustic likelihood scoresZe ev Rivlin. 523-526 [doi]
• Discriminative utterance verification for connected digits recognitionMazin G. Rahim, Chin-Hui Lee, Biing-Hwang Juang. 529-532 [doi]
• MCE estimation of VQ parameters for MVQHMM speech recognitionAntonio M. Peinado, Antonio J. Rubio, José C. Segura, Victoria E. Sánchez, Jesús E. Díaz-Verdejo. 533-536 [doi]
• Discriminative training for continuous speech recognitionWolfgang Reichl, Günther Ruske. 537-540 [doi]
• Minimum classification error training algorithm for feature extractor and pattern classifier in speech recognitionKuldip K. Paliwal, Michiel Bacchiani, Yoshinori Sagisaka. 541-544 [doi]
• A discriminative filter bank model for speech recognitionAlain Biem, Erik McDermott, Shigeru Katagiri. 545-548 [doi]
• A stochastic grammar for isolated representation of syntactic and semantic knowledgeHolger Stahl, Johannes Müller. 551-554 [doi]
• Concept-based spontaneous speech understanding systemEsther Levin, Roberto Pieraccini. 555-558 [doi]
• Semantic decoding of speech in constrained domainsAntonio Bonafonte, José B. Mariño, Eduardo Lleida. 559-562 [doi]
• A speech understanding architecture for an information query systemMarcello Federico, Fabrizio Vernesoni. 563-566 [doi]
• A one-pass search algorithm for understanding natural spoken time utterances by stochastic modelsJosef G. Bauer, Holger Stahl, Johannes Müller. 567-570 [doi]
• Improvements in an HMM-based speech synthesiserR. E. Donovan, Philip C. Woodland. 573-576 [doi]
• Sub-phonemic optimal path search for concatenative speech synthesisYoshiharu Itoh, Makoto Hashimoto, Norio Higuchi. 577-580 [doi]
• Optimising selection of units from speech databases for concatenative synthesisAlan W. Black, Nick Campbell. 581-584 [doi]
• Automatic data-driven prosodic modeling for text-to-speechEduardo López Gonzalo, Luis Hernández A. Gómez. 585-588 [doi]
• Text-to-speech oriented automatic learning of Italian prosodyF. Mana, Silvia Quazza. 589-592 [doi]
• A simple method of predicting the duration of syllablesAndrew P. Breen. 595-598 [doi]
• Generating French intonation at different speaking ratesFrédéric Beaugendre. 603-606 [doi]
• Segmental duration in French text-to-speech synthesisEvelyne Tzoukermann, Olivier Soumoy. 607-610 [doi]
• Developing the prosodic component for Swedish speech synthesisMerle Horne, Marcus Filipsson. 611-614 [doi]
• Speaker recognition with temporal transition modelsHaizhou Li, Jean-Paul Haton, Jian Su, Yifan Gong. 617-620 [doi]
• Speaker recognition using HMM composition in noisy environmentsTomoko Matsui, Tomohito Kanno, Sadaoki Furui. 621-624 [doi]
• Speaker recognition using HMM with experiments on the yoho databaseChiwei Che, Qiguang Lin. 625-628 [doi]
• Speaker recognition modelsKin Yu, John S. Mason, John Oglesby. 629-632 [doi]
• Multi-state predictive neural networks for text-independent speaker recognitionThierry Artières, Patrick Gallinari. 633-636 [doi]
• Results of a speaker verification service trial using HMM modelsAnand R. Setlur, Thomas Jacobs. 639-642 [doi]
• Application of phonetic weighting to the neural tree network based speaker recognition systemHan-Sheng Liou, Richard J. Mammone. 643-646 [doi]
• Experiments with speaker verification over the telephoneJean-Luc Gauvain, Lori Lamel, B. Prouts. 651-654 [doi]
• Speech coding based on the discrete-time wavelet transform and human auditory system propertiesDan Stefanoiu, Radwan Kastantin, Gang Feng. 661-664 [doi]
• Wavelets for low bit rate speech coding applicationsF. J. Ancin, M. L. Larreategui, B. L. Burrows, R. A. Carrasco. 665-669 [doi]
• Adaptive speech vector coding with a multiresolution hierarchical codebookE. Mandridake, R. Atay, M. Najim. 669-672 [doi]
• Subband analysis-by-synthesis codingAndrei Popescu, Nicolas Moreau. 673-676 [doi]
• A robust 2.4kb/s LP-MBE with iterative LP modellingClifford I. Parris, Danny Wong, Francois Chambon. 677-680 [doi]
• Improved transient representation and quantization for sinusoidal speech codersM. S. Torres-Guijarro, Francisco Javier Casajús-Quirós. 681-684 [doi]
• Efficient multiband excitation linear predictive coding of speech at 1.6 kbpsEric W. M. Yu, Cheung-fat Chan. 685-688 [doi]
• Spectral envelope estimation for low bit-rate sinusoidal speech codersBarry M. G. Cheetham, X. Q. Sun, W. T. K. Wong. 693-696 [doi]
• Improved CELP algorithm suited for various speech coding applicationsSofia Moreno Perez, Ramón García Gómez. 699-702 [doi]
• Comparative study of two codecs for an enhanced GSM systemS. A. Atungsiri, Ahmet M. Kondoz, Barry G. Evans. 703-707 [doi]
• Fast low-delay CELP coding of speech at 8kbpsSiu-pun Chui, Cheung-fat Chan. 707-710 [doi]
• A low bit-rate speech coder using the perceptual properties of the human earHong-Goo Kang, Jeong Tae Seo, Il Whan Cha, Dae Hee Youn. 711-714 [doi]
• Very fast CELP coding using stochastic innovationsSilvio Cucchi, Marco Fratti. 715-718 [doi]
• Fast codebook search algorithm based on hamming ECC for algebraic CELP speech codingM. Bouraoui, W. Glass, Gang Feng. 719-722 [doi]
• Implementation aspects of the GSM half-rate speech codecTim Fingscheidt, Thomas Wiechers, Eckhard Delfs. 723-726 [doi]
• Low and variable bit-rate speech coding for ATM networksScott D. Watson, Barry M. G. Cheetham, W. T. K. Wong, A. V. Lewis. 727-730 [doi]
• A differential encoding method for the LTP delay in CELP codersAndrei Popescu, Nicolas Moreau, Claude Lamblin. 731-733 [doi]
• Robust, n-best formant trackingPhilipp Schmid, Etienne Barnard. 737-740 [doi]
• Formant tracking using reassigned spectrumF. Plante, William A. Ainsworth. 741-744 [doi]
• Direct calculation of the vocal tract area function from measured formant frequenciesJean Schoentgen, Sorin Ciocea. 745-748 [doi]
• Robust estimation of spectral center-of-gravity trajectories using mixture spline modelsDon X. Sun. 749-752 [doi]
• Bound for minkowski metric based on LP distortion measureJeng-Shyang Pan, Fergus R. McInnes, Mervyn A. Jack. 753-756 [doi]
• An algorithm for speech parameter generation from continuous mixture HMMs with dynamic featuresKeiichi Tokuda, Takashi Masuko, Tetsuya Yamada, Takao Kobayashi, Satoshi Imai. 757-760 [doi]
• Deriving articulatory representations of speechHywel B. Richards, John S. Mason, Melvyn J. Hunt, John S. Bridle. 761-764 [doi]
• Improved acoustic-phonetic modeling in philips dictation system by handling liaisons and multiple pronunciationsXavier L. Aubert, Christian Dugast. 767-770 [doi]
• Digit recognition with stochastic perceptual speech modelsNelson Morgan, Su-Lin Wu, Hervé Bourlard. 771-774 [doi]
• On incorporating phonemic constraints in hidden Markov models for speech recognitionR. N. V. Sitaram, Thippur Sreenivas. 775-778 [doi]
• An improvement on syllable-based continuous Mandarin speech recognition via using inter-syllable boundary modelsSaga Chang, Sin-Horng Chen. 779-782 [doi]
• Optimizing baseforms for HMM-based speech recognitionTorbjørn Svendsen, Frank K. Soong, Heiko Purnhagen. 783-787 [doi]
• Acoustic modeling of context dependent units, for large vocabulary speech recognition in SpanishJ. Alvarez-Cercadillo, Chin-Hui Lee, Luis A. Hernández Gómez. 787-790 [doi]
• Estimation of statistical phoneme center and its application to accurate phoneme modellingShigeki Okawa, Katsuhiko Shirai. 791-794 [doi]
• Hybrid hidden Markov models in speech recognitionZ. Li, Patrick Kenny, Douglas D. O Shaughnessy. 795-798 [doi]
• Acoustic-phonetic modeling for flexible vocabulary speech recognitionLuciano Fissore, Franco Ravera, Pietro Laface. 799-802 [doi]
• Segmental duration and HMM modelingPierre Dumouchel, Douglas D. O Shaughnessy. 803-806 [doi]
• A knowledge-based model for speaker-independent, acoustic-phonetic decodingA. Ghio, Mario Rossi. 807-810 [doi]
• A database for microphone array experimentationEa-Ee Jan, Piergiorgio Svaizer, James L. Flanagan. 813-816 [doi]
• The OGI 22 language telephone speech corpusTerri Lander, Ronald A. Cole, Beatrice T. Oshika, Mike Noel. 817-820 [doi]
• New telephone speech corpora at CSLURonald A. Cole, Mike Noel, Terri Lander, T. Durham. 821-824 [doi]
• The Dutch polyphone corpusEls den Os, T. I. Boogaart, Lou Boves, Esther Klabbers. 825-828 [doi]
• The waxholm application databaseJ. Bertenstam, Mats Blomberg, Rolf Carlson, Kjell Elenius, Björn Granström, Joakim Gustafson, Sheri Hunnicutt, J. Hogberg, Roger Lindell, Lennart Neovius, Lennart Nord, Antonio de Serpa-Leitao, N. Strom. 833-836 [doi]
• A pitch extraction reference databaseF. Plante, Georg F. Meyer, William A. Ainsworth. 837-840 [doi]
• Eagles spoken language working group: overview and resultsRichard Winski, Roger K. Moore, Dafydd Gibbon. 841-845 [doi]
• CEUDEX: a data base oriented to context-dependent units training in Spanish for continuous speech recognitionCelinda de la Torre-Munilla, Luis Hernández A. Gómez, Daniel Tapias Merino. 845-848 [doi]
• Design of a phonetic corpus for a speech database in basque languageKarmele López de Ipiña, Inés Torres, Lourdes Oñederra. 851-854 [doi]
• you d better say nothing than say something wrong : analogy, accuracy and text-to-speech applicationsVito Pirrelli, Stefano Federici. 855-858 [doi]
• Bulgarian speech database: a pilot studyA. Misheva, S. Dimitrova, V. Filipov, E. Grigoreva, M. Nikov, Peter Roach, Simon Arnfield. 859-863 [doi]
• The Phondat-verbmobil speech corpusWolfgang J. Hess, Klaus J. Kohler, Hans-Günther Tillmann. 863-866 [doi]
• EUROM - a spoken language resource for the EU - the SAM projectsDominic S. F. Chan, Adrian Fourcin, Dafydd Gibbon, Björn Granström, Mark Huckvale, George Kokkinakis, Knut Kvale, Lori Lamel, Børge Lindberg, Asunción Moreno, Jiannis Mouropoulos, Francesco Senia, Isabel Trancoso, Corin t Veld, Jerome Zeiliger. 867-870 [doi]
• A flexible formal language for the orthographic transcription of spontaneous spoken dialoguesGernot A. Fink, Michaela Johanntokrax, Brigitte Schaffranietz. 871-874 [doi]
• Design and implementation of Mandarin speech database in taiwanHsiao-Chuan Wang. 875-877 [doi]
• Towards increasing speech recognition error ratesHervé Bourlard. 883-894 [doi]
• Word hypothesizer based on reliably detected phoneme similarity regionsPhilippe Morin, Ted H. Applebaum. 897-900 [doi]
• Experimental analysis of the search space for 20 000-word speech recognitionStefan Ortmanns, Hermann Ney. 901-904 [doi]
• Speech parsing by downward request search based on the divide and conquer methodMing-Sheng Wang, Satoshi Imai. 905-908 [doi]
• Fast match based on decision treeClaire Waast, Lalit R. Bahl, Marc El-Bèze. 909-913 [doi]
• Fast and accurate beam search using forward heuristic functions in HMM-LR speech recognitionYoshiaki Noda, Shigeki Sagayama. 913-916 [doi]
• On the speech feature selection problem: are dynamic features more important than the static ones?Jan Nouza. 919-922 [doi]
• Filtering the time sequence of spectral parameters for speaker-independent CDHMM word recognitionCliment Nadeu, Pau Pachès-Leal, Biing-Hwang Juang. 923-926 [doi]
• Robust phoneme prototype extraction for speech recognitionDimitris Tambakas, Nikos Fakotakis, George Kokkinakis. 927-930 [doi]
• The even transform: a variance-equalizing orthogonal transformation and its application to speech recognitionMelvyn J. Hunt. 931-934 [doi]
• Using segmental coefficients in HMM speech recognitionKai Hbener. 935-938 [doi]
• Intensity and vocal effort as cues in the perception of stressAgaath M. C. Sluijter, Vincent J. van Heuven. 941-944 [doi]
• The effect of voice pitch on perception of synthetic Polish vowelsMariusz Owsianny. 945-948 [doi]
• Perception of prepausal tonal contours: implications for automatic stylization of intonationDavid House. 949-952 [doi]
• Experimental study on perception of the glottal explosive of the Japanese ryukyu dialectTomio Takara. 953-956 [doi]
• Measurement of pitch perception for F0 glidesChristophe d Alessandro, Sophie Rosset, O. Piot. 957-960 [doi]
• The influence of local context on the identification of vowels and consonantsR. J. J. H. van Son, Louis C. W. Pols. 967-970 [doi]
• Effect of preceding noise duration on the perception of voiced plosives and vowelsWilliam A. Ainsworth. 971-974 [doi]
• Influence of a prior knowledge of the vocalic context on stop burst perceptionAnne Bonneau, Linda Djezzar, Yves Laprie. 975-978 [doi]
• Listeners use of the information-accentuation interdependence in processing implicit and explicit referencesWilma van Donselaar. 979-982 [doi]
• Analysis and modeling of fundamental frequency contours of English utterancesHiroya Fujisaki, Sumio Ohno. 985-988 [doi]
• Symbolic coding of higher-level characteristics of fundamental frequency curvesP. Nicolas, Daniel Hirst. 989-992 [doi]
• A dynamical system model for recognizing intonation patternsKen Ross, Mari Ostendorf. 993-996 [doi]
• Syntactic influence on prosodic phrasing in the framework of the link grammarAndrew J. Hunt. 997-1000 [doi]
• Effects of time pressure on the choice of accent-lending and boundary-marking pitch configurations in dutchJohanneke Caspers, Vincent J. van Heuven. 1001-1004 [doi]
• Analysis and synthesis of prosodic features in spoken dialogue of JapaneseMayumi Sakata, Keikichi Hirose. 1007-1010 [doi]
• Prosodic influence on segmental qualityNick Campbell. 1011-1014 [doi]
• Towards voice-interactive telephone services in slovenia: on prosody of digits using the sociolinguistic frameworkBojan Petek. 1015-1018 [doi]
• Test environment for the two level model of Germanic prominenceGregor Möhler, Grzegorz Dogil. 1019-1022 [doi]
• Linguistic and acoustic characteristics of pause intervals in spontaneous speechNancy A. Daly-Kelly. 1023-1026 [doi]
• Interpolation properties of linear prediction parametric representationsKuldip K. Paliwal. 1029-1032 [doi]
• Interpolation of spectral information for low bit rate speech codingH. B. Choi, W. T. K. Wong, Barry M. G. Cheetham, C. C. Goodyear. 1033-1036 [doi]
• Adaptive flux interpolation, flow-based prediction, delta or delta-delta coefficients: which is best?Ladan Baghai-Ravary, Steve W. Beet, Osman Tokhit. 1037-1040 [doi]
• LSP Markov model for reducing the complexity of vector quantizationBalázs Kövesi, Samir Saoudi, Jean-Marc Boucher, Z. Reguly. 1041-1044 [doi]
• Predictive delta adaptive scalar quantization: an efficient method for coding the short-term speech spectrumHamid Reza Sadegh Mohammadi, W. H. Holmes. 1045-1048 [doi]
• Conditional split vector quantization of LSP parameterswith multiple searchDong-Il Chang, KyungMin Na, SouGuil Ann. 1049-1052 [doi]
• MATRIX PRODUCT QUANTIZATION FOR VERY-LOW-RATE MOBILE SPEECH COMMUNICATIONSStefan Bruhn. 1053-1056 [doi]
• Robust vector quantization for low bit rate speech codingUlrich Balss, Herbert Reininger, Holger Schalk, Dietrich Wolf. 1057-1060 [doi]
• Scalar quantization of LSF parameters at 28 bits/frameH. C. Ng, S. H. Leung. 1061-1064 [doi]
• Utterance verification improves closed-set recognition and out-of-vocabulary rejectionDon Colton, Mark A. Fanty, Ronald A. Cole. 1067-1071 [doi]
• A comparison of two exact algorithms for finding the n-best sentence hypotheses in continuous speech recognitionVíctor M. Jiménez, Andrés Marzal, Jean Monné. 1071-1074 [doi]
• Top-down speech detection and n-best meaning search in a voice activated telephone extension systemKazuya Takeda, Shingo Kuroiwa, Masaki Naito, Seiichi Yamamoto. 1075-1078 [doi]
• Fast likelihood computation for continuous-mixture densities using a tree-based nearest neighbor searchFrank Seide. 1079-1083 [doi]
• Hamming distance approximation for a fast log-likelihood computation for mixture densitiesPeter Beyerlein, Meinhard Ullrich. 1083-1086 [doi]
• An efficient output probability computation for continuous HMM using rough and detail modelsYasuhiro Komori, Masayuki Yamada, Hiroki Yamamoto, Yasunori Ohora. 1087-1090 [doi]
• Speeding up the score computation of HMM speech regognizers with the bucket voronoi intersection algorithmJürgen Fritsch, Ivica Rogina, Tilo Sloboda, Alex Waibel. 1091-1094 [doi]
• Improvement of the quality of speech synthesis by analysis using segmentation and modeling of the excitation signalJuana M. Gutiérrez-Arriola, Francisco M. Gimenez de los Galanes, Mohammed H. Savoji. 1097-1100 [doi]
• A text-to-speech synthesizer for the Polish languagePrzemyslaw Dymarski, Slawomir Kuklinski, Siawomir Kula. 1101-1104 [doi]
• A comparison of different speech units for the German TTS-system tubsyC. Jürgens, M. Wunderlich. 1105-1108 [doi]
• Confusions among Italian consonants in good and in telephone conditions: differences between text-to-speech systems and natural speech with noiseCristina Delogu, Andrea Paoloni, Paola Ridolfi. 1109-1112 [doi]
• Text-to-speech synthesis for welsh and welsh EnglishBriony Williams. 1113-1117 [doi]
• Multi-lingual testing of a self-learning approach to phonemic transcription of orthographyOve Andersen, Paul Dalsgaard. 1117-1120 [doi]
• An integrated multi-dialect speech recognition system with optional speaker adaptationV. Beattie, S. Edmondson, D. Miller, Y. Patel, G. Talvola. 1123-1126 [doi]
• A comparative study of speaker adaptation techniquesLeonardo Neumeyer, Ananth Sankar, Vassilios Digalakis. 1127-1130 [doi]
• Adaptation algorithms for large scale HMM recognizersGeorge Zavaliagkos, Richard M. Schwartz, John W. McDonough, John Makhoul. 1131-1135 [doi]
• Speaking-style and speaker adaptation for the recognition of spontaneous dialogue speechShoichi Matsunaga, Tetsuo Kosaka, Tohru Shimizu. 1135-1138 [doi]
• Speaker adaptation for telephone based speech dialogue systemsStefan Dobler, Hans-Wilhelm Rühl. 1139-1143 [doi]
• Speaker adaptation with autonomous control using tree structureKoichi Shinoda, Takao Watanabe. 1143-1146 [doi]
• Speaker adaptation fitting training data size and contentsMasahiro Tonomura, Tetsuo Kosaka, Shoichi Matsunaga, Akito Monden. 1147-1150 [doi]
• Direct and joint-space approaches to the use of spectral transformation for speaker adaptation in continuous speech recognitionH. C. Choi, R. W. King. 1151-1154 [doi]
• Flexible speaker adaptation for large vocabulary speech recognitionC. J. Leggetter, Philip C. Woodland. 1155-1158 [doi]
• Faust - a directory assistance demonstratorBernhard Kaspar, Georg Fries, Karlheinz Schuhmacher, Antje Wirth. 1161-1164 [doi]
• Some signals of emotional arousal: analysis of conversations using a multimodal interaction databaseKeiko Watanuki, Fumio Togawa. 1165-1168 [doi]
• Speech synthesis in spoken dialogue researchGösta Bruce, Björn Granström, Marcus Filipsson, Kjell Gustafson, Merle Horne, David House, Birgitta Lastow, Paul Touati. 1169-1172 [doi]
• Dynamically created dialogues for automated telephone answering using uncertain reasoning and linguistic theoryMary Zajicek, Ken Brownsey, Simon Lippmann, Patrice Palau, Phyl Greenhead. 1173-1176 [doi]
• Modeling dialogue control strategies to relieve speech recognition errorsYasuhisa Niimi, Yutaka Kobayashi. 1177-1180 [doi]
• Constraining of input media in a spoken dialogue systemAnders Baekgaard. 1181-1184 [doi]
• An Automatic Creation of the Language Model for the Spontaneous Czech Speech RecognizerJana Klecková, Václav Matousek, Jana Netrvalova. 1185-1188 [doi]
• A grammar of conversational EnglishMary O Kane, P. E. Kenne, Hamish G. Pearcy. 1189-1192 [doi]
• Robust comprehension in a spoken dialog systemEric Brison, Nadine Vigouroux. 1193-1196 [doi]
• Korean-Japanese speech translation system for hotel reservation - Korean front desk sideYoungJik Lee, Young-Sum Kim, Jung-Chul Lee, Joon-Hyung Ryoo, Jae-Woo Yang. 1197-1200 [doi]
• Unconstrained speech retrieval for Chinese document databases with very large vocabulary and unlimited domainsSung-Chien Lin, Lee-Feng Chien, Keh-Jiann Chen, Lin-Shan Lee. 1203-1206 [doi]
• Integrating partial syntactical analysis and plan recognition for understanding DB natural language queriesCristina Delogu, Andrea Di Carlo, Rino Falcone. 1207-1211 [doi]
• Communicative language model: structure and functioningYuri A. Kosarev. 1211-1214 [doi]
• Integrating heuristic preferences into a neural understanding systemAdelaide Stevenur, Patrick Gallinari. 1215-1218 [doi]
• A language interface to a polyphone-based speech synthesizerBjörn Gambäck, Martin Eineborg, Mikael Eriksson, Barbro Ekholm, Bertil Lyberg, Tomas Svensson. 1219-1223 [doi]
• Using two-level morphology as a generator-synthesizer interface for concept-to-speechGeorg Niklfeld, Hannes Pirker, Harald Trost. 1223-1226 [doi]
• KT-STS: a speech translation system for hotel reservation and a continuous speech recognition system for speech translationMyoung-Wan Koo, Il-Hyun Sohn, Woosung Kim, Du-Seong Chang. 1227-1230 [doi]
• Learning language translation in limited domains using finite-state models: some extensions and improvementsJuan Miguel Vilar, Andrés Marzal, Enrique Vidal. 1231-1234 [doi]
• The effect of context on the intelligibility of dialogueDavid G. Novick, Karen Ward, Benjamin Corliss. 1235-1238 [doi]
• Representation of a finite state grammar as bigram language model for continuous speech recognitionUte Kilian, Fritz Class, Alfred Kaltenmeier, Peter Regel-Brietzmann. 1241-1244 [doi]
• Extensions of absolute discounting for language modelingM. Generet, Hermann Ney, Frank Wessel. 1245-1248 [doi]
• Automatic clustering of words for probabilistic language modelsLoreia Moisa, Egidio P. Giachin. 1249-1253 [doi]
• Algorithms for bigram and trigram word clusteringSven C. Martin, Jörg Liermann, Hermann Ney. 1253-1256 [doi]
• More efficient clustering of n-grams for statistical language modelingJoerg P. Ueberla. 1257-1260 [doi]
• Consistency of inter-transcribers transcriptionSatoshi Kobayashi, Shigeyoshi Kitazawa. 1263-1266 [doi]
• Comparison of reference system approaches for the quality assessment of synthesized speechH. Klaus, A. Niebank. 1267-1270 [doi]
• Multi-lingual assessment of speaker independent large vocabulary speech-recognition systems: THE SQALE-PROJECTHerman J. M. Steeneken, David A. van Leeuwen. 1271-1274 [doi]
• Error analysis on field data and improved garbage HMM modellingKatarina Bartkova, D. Dubois, Denis Jouvet, Jean Monné. 1275-1278 [doi]
• Interference of speech recognition feedback during diagnostic tasksE. J. A. Verheijen, F. L. Van Nes, L. M. de Bruyn, Arie Hasman, Jan Willem Arends. 1279-1282 [doi]
• Geometric and temporal constraints in the production of French consonant sequences x-ray and acoustic data for FrenchBéatrice Vaxelaire. 1285-1288 [doi]
• On the biomechanical control variables of the tongue during speech movementsRafael Laboissière, Vittorio Sanguineti, Yohan Payan. 1289-1292 [doi]
• Multipulse LPC modeling of articulatory movements: analysis and interpretationSoumya Bouabana, Shinji Maeda. 1293-1296 [doi]
• Numerical simulations of fluid flow in the vocal tractGaël Richard, M. Liu, D. Snider, H. Duncan, Qiguang Lin, James L. Flanagan, Stephen Levinson, D. Davis, S. Slimon. 1297-1300 [doi]
• 3-d fem analysis of sound propagation in the nasal tractHisayoshi Suzuki, Takayoshi Nakai, Hiroshi Sakakibara. 1301-1304 [doi]
• Effects of tonal clash on downstepped h* accents in SpanishPilar Prieto, Chilin Shih. 1307-1310 [doi]
• The effect of two factors related to speaking tempo on vowel devoicing in JapaneseMariko Kondo. 1311-1314 [doi]
• Duration perception in subsyllabic constituentsRob Goedemans, Vincent J. van Heuven. 1315-1318 [doi]
• Experimental evidence for a comprehensive theory of vowel reductionDick R. van Bergem. 1319-1322 [doi]
• Clear speech does not exaggerate phonemic contrastJohn J. Ohala. 1323-1326 [doi]
• Modeling the contextual effects on prosody in dialogY. Yamashita, R. Mizoguchi. 1329-1332 [doi]
• Prosodic scoring of word hypotheses graphsRalf Kompe, Andreas Kießling, Heinrich Niemann, Elmar Nöth, Ernst Günter Schukat-Talamazzini, A. Zottmann, Anton Batliner. 1333-1336 [doi]
• Robust pitch period detection using dynamic programming with an ANN cost functionStefan Harbeck, Andreas Kießling, Ralf Kompe, Heinrich Niemann, Elmar Nöth. 1337-1340 [doi]
• Automatic detection of major phrase boundaries using statistical properties of superpositional F0 control model parametersToshio Hirai, Norio Higuchi, Yoshinori Sagisaka. 1341-1344 [doi]
• Using neural networks to locate pitch accentsPaul Taylor. 1345-1348 [doi]
• An approach to language identification with enhanced language modelYongHong Yan, Etienne Barnard. 1351-1354 [doi]
• The application of dynamic programming techniques to non-word based topic spottingP. Nowell, Roger K. Moore. 1355-1358 [doi]
• Two novel language model estimation techniques for statistical language identificationMichael A. Lund, Herbert Gish. 1363-1366 [doi]
• Recognized phoneme-based N-gram modeling in automatic language identificationHingKeung Kwan, Keikichi Hirose. 1367-1370 [doi]
• On the use of the derivative of the pole trajectories of the LPC analysis parameter sequence as an alternative to delta parametersFelix Freitag, Enric Monte, Javier Hernando Pericas. 1373-1376 [doi]
• On the dual role of sequence directionality and coherence in a spectral predictive discrimination modelP. V. S. Rao, R. Raveendran. 1377-1380 [doi]
• On the decorrelation of filter-bank energies in speech recognitionCliment Nadeu, Javier Hernando, Mónica Gorricho. 1381-1384 [doi]
• Time derivatives, cepstrai normaiization, and spectral parameter filtering for continuously spelled names over the telephoneJean-Claude Junqua, Dominique Fohr, Jean-François Mari, Ted H. Applebaum, Brian A. Hanson. 1385-1388 [doi]
• Some new considerations about the spectral form of French stop burstsLinda Djezzar. 1389-1392 [doi]
• Characterization of spectral transition region by various prediction approaches for discriminating stop consonantsP. V. S. Rao, R. Raveendran. 1393-1396 [doi]
• Fast automatic segmentation and labeling: results on TIMIT and EUROMOA. Vorstermanst, Jean-Pierre Martens, Bert Van Coile. 1397-1400 [doi]
• Maximum-likelihood estimation for articulatory speech recognition using a stochastic target modelGordon Ramsay, Li Deng. 1401-1404 [doi]
• A comparison of several speech parameters for speaker independent speech recognition and speaker recognitionJohn Sirigos, Nikos Fakotakis, George Kokkinakis. 1407-1410 [doi]
• Speech parameterization based on phonetic features: application to speech recognitionNabil N. Bitar, Carol Y. Espy-Wilson. 1411-1414 [doi]
• Experiments with linear feature extraction in speech recognitionKlaus Beulen, Lutz Welling, Hermann Ney. 1415-1418 [doi]
• NONLINEAR FEATURE TRANSFORMATION BASED ON STATISTICAL PHONEME MODELINGChristian-Michael Westendorf. 1419-1422 [doi]
• Skewness and nonstationarity measures applied to reliable speech endpoint detectionJuan L. Navarro-Mesa, Asunción Moreno. 1423-1426 [doi]
• The distance set representation of speech segmentsRamesh R. Sarukkai, Dana H. Ballard. 1427-1430 [doi]
• Multi-variate mixture probability density modelling of VQ codebook using gradient descent algorithmSimon Dobrisek, R. Mihelic, Nikola Pavesic. 1431-1434 [doi]
• Collecting and analyzing spoken utterances for a speech controlled applicationJohannes Müller, Holger Stahl. 1437-1440 [doi]
• Speech intelligibility and loudness assessment in a wireless personal communicationHiromi Nagabuchi, Akira Takahashi, Mineyoshi Ogawa. 1441-1444 [doi]
• An experimental investigation of the input and error correction strategies used by subjects entering digits with the AURIX speech recogniserKate S. Hone, R. W. Series, Chris Baber. 1445-1448 [doi]
• Goal-directed generation of intelligibility test vocabularies in the framework of names synthesisKarim Belhoula. 1449-1452 [doi]
• Human factors of a voice-controlled car stereoReinhold Haeb-Umbach, Stephan Gamm. 1453-1456 [doi]
• Exploring the limits of system-directed dialogue, dialogue evaluation of the danish dialogue systemNiels Ole Bernsen, Hans Dybkjær, Laila Dybkjær. 1457-1460 [doi]
• Human benchmarks for speaker independent large vocabulary recognition performanceDavid A. van Leeuwen, Leo-Geert van den Berg, Herman J. M. Steeneken. 1461-1464 [doi]
• Discriminative-transitional/steady units for Spanish continuous speech recognitionAmparo Varona, Inés Torres, Francisco Casacuberta. 1471-1474 [doi]
• An HMM with optimized segment-dependent observations for speech recognitionJi Mingy, Peter O Boyle, F. Jack Smith. 1475-1478 [doi]
• Improving recognition performances on field data with an a-priori segmentation of the speech signalThierry Moudenc, Denis Jouvet, Jean Monné. 1479-1482 [doi]
• Connected digit recognition using statistical template matchingLutz Welling, Hermann Ney, A. Eiden, C. Forbrig. 1483-1486 [doi]
• Calculation of distance measures between hidden Markov modelsMarkus Falkhausen, Herbert Reininger, Dietrich Wolf. 1487-1490 [doi]
• A chernoff distance based segmental probability model (CD-SPM) approach for Mandarin syllable recognitionJia-lin Shen, Lin-Shan Lee. 1491-1494 [doi]
• Geometric pattern recognition techniques for acoustic-phonetic decoding of Spanish continuous speechMaría José Castro, Federico Prat, Pablo Aibar, Francisco Casacuberta. 1495-1498 [doi]
• State tying of triphone HMM s for the 1994 AT&t ARPA ATIS recognizerEnrico Bocchieri, Giuseppe Riccardi. 1499-1502 [doi]
• A shared-distribution approach in a hidden Markov model-based continuous speech recognition systemAzarshid Farhat, Douglas D. O Shaughnessy. 1503-1506 [doi]
• Preliminary experimentation of different methods for continuous speech recognition in SpanishJavier Ferreiros, José M. Pardo. 1507-1510 [doi]
• Computationally efficient speech enhancement by spectral minima tracking in subbandsGerhard Doblinger. 1513-1516 [doi]
• Robust hos-based techniques applied to speech recognition and enhancementJosep M. Salavedra, Javier Hernando, Enrique Masgrau, Asunción Moreno. 1517-1520 [doi]
• A maximum likelihood equalization technique for robust speech recognition in adverse environmentsKuldip K. Paliwal. 1521-1524 [doi]
• Joint system for acoustic echo cancellation and noise reductionGérard Faucon, Régine Le Bouquin-Jeannès. 1525-1528 [doi]
• A study of speech recognition system robustness to microphone variationsJane Chang, Victor Zue. 1529-1532 [doi]
• A feature-space transformation for telephone based speech recognitionAlexandros Potamianos, Li Lee, Richard C. Rose. 1533-1536 [doi]
• Development and improvement of a real-time ASR system for isolated digits in Spanish over the telephone lineRicardo de Córdoba, Xavier Menéndez-Pidal, Javier Macías Guarasa, Ascensión Gallardo-Antolín, José Manuel Pardo. 1537-1540 [doi]
• Channel estimation for reference model adaptation in telephone speech recognitionJen-Tzung Chien, Lee-Min Lee, Hsiao-Chuan Wang. 1541-1544 [doi]
• Enhancement of telephone speech quality by simple spectrum extrapolation methodHiroshi Yasukawa. 1545-1548 [doi]
• Low-distortion spectral subtraction for speech enhancementPeter Handel. 1549-1552 [doi]
• Transition-based feature extraction within frame-based recognitionZhihong Hu, Etienne Barnard, Ronald A. Cole. 1555-1558 [doi]
• Noisy speech enhancement with filters estimated from the speaker s lipsLaurent Girin, Gang Feng, Jean-Luc Schwartz. 1559-1562 [doi]
• Audio-visual speech recognition compared across two architecturesAli Adjoudani, Christian Benoît. 1563-1566 [doi]
• Noise effects on landmark detection in a speech recognition systemSharlene A. Liu. 1567-1570 [doi]
• AR identification of the vocal filter from noisy hyperbaric speech signalsLaure Charonnat, Joel Crestel, Michel Glutton, Herve Chuberre. 1571-1574 [doi]
• The study of speech/pause detectors for speech enhancement methodsPavel Sovka, Petr Pollák. 1575-1578 [doi]
• Neural-fuzzy network for phonetic features recognitionRobert Sokol, Guy Mercier. 1579-1582 [doi]
• A system for speech separationA. Shamsoddini, P. N. Denbigh. 1583-1586 [doi]
• Hierarchical mixture models and phonological rules in open-vocabulary speech recognitionYunxin Zhao. 1587-1590 [doi]
• Flexible speech recognitionSadaoki Furui. 1595-1604 [doi]
• Study of subword units for Spanish speech recognitionAntonio Bonafonte, Rafael Estany, Eugenio Vives. 1607-1610 [doi]
• Speech recognition using a linear dynamic segmental HMMWendy J. Holmes, Martin J. Russell. 1611-1614 [doi]
• Comparative evaluation of segmental unit input HMM and conditional density HMMKazumasa Yamamoto, Seiichi Nakagawa. 1615-1618 [doi]
• Continuous speech recognition using non-uniform unit based acoustic and language modelsShoichi Matsunaga, Takeshi Matsumura, Harald Singer. 1619-1622 [doi]
• Towards improved speech recognition using a speech production modelC. S. Blackburn, Steve J. Young. 1623-1626 [doi]
• A vocabulary independent discriminatively trained method for rejection of non-keywords in sub word based speech recognitionRafid A. Sukkar, Chin-Hui Lee, Biing-Hwang Juang. 1629-1632 [doi]
• Rejection techniques based on context independent subword unitsJuan Carlos Torrecilla, Daniel Tapias Merino, F. Javier Caminero-Gil, Luis Villarrubia. 1633-1636 [doi]
• Detection of unknown words in spontaneous speechPablo Fetter, Fritz Class, Udo Haiber, Alfred Kaltenmeier, Ute Kilian, Peter Regel-Brietzmann. 1637-1640 [doi]
• A minimum error training of garbage model for keyword spotter with artificially generated training dataAtsushi Nakamura. 1641-1644 [doi]
• New words: effect on recognition performance and incorporation issuesI. Lee Hetherington. 1645-1648 [doi]
• Improving speech recognition using speaker classificationDavid O. Baldwin, Georg F. Meyer. 1651-1654 [doi]
• Modular neural networks with task-specific input parameters for speakerindependent speech recognitionAxel Glaeser. 1655-1658 [doi]
• Large vocabulary speaker-independent continuous speech recognition with a new hybrid system based on MMI-neural networksGerhard Rigoll, Christoph Neukirchen, Jörg Rottland. 1659-1662 [doi]
• REMAP: recursive estimation and maximization of a posteriori probabilities in connectionist speech recognitionHervé Bourlard, Yochai Konig, Nelson Morgan. 1663-1666 [doi]
• An RNN based speech recognition system with discriminative trainingTan Lee, P. C. Ching, Lai-Wan Chan. 1667-1670 [doi]
• Preliminary experiments for automatic speech understanding through simple recurrent networksM. Asunción Castaño, Enrique Vidal, Francisco Casacuberta. 1673-1676 [doi]
• A neural network using non-uniform units for continuous speech recognitionHa-Jin Yu, Yung-Hwan Oh. 1677-1680 [doi]
• Temporal correlation modeling in a hybrid neural network/hidden Markov model speech recognizerHoracio Franco, Vassilios Digalakis. 1681-1684 [doi]
• Continuous speech segmentation with the gamma memory modelLaurent Buniet, Dominique Fohr. 1685-1688 [doi]
• Incorporating fuzzy modelling in a hybrid HMM-ANNs system for CSR tasksXavier Menéndez-Pidal, Ricardo de Córdoba, Javier Ferreiros, José Manuel Pardo. 1689-1692 [doi]
• The role of linguistic stress in the time course of word recognition in stress-accent languagesWilly Jongenburger, Vincent J. van Heuven. 1695-1698 [doi]
• Inter-language differences in the mcgurk effect for dutch and Cantonese listenersBéatrice de Gelder, Paul Bertelson, Jean Vroomen, Hsuan Chin Chen. 1699-1702 [doi]
• Listeners representations of within-word structure: a cross-linguistic and cross-dialectal investigationTakashi Otake, Sally M. Davis, Anne Cutler. 1703-1706 [doi]
• The use of phonotactic constraints in the segmentation of dutchJames M. McQueen, Ethan Cox. 1707-1710 [doi]
• Lexical inhibition in spoken word recognitionJean Vroomen, Béatrice de Gelder. 1711-1714 [doi]
• Portable speech rate conversion systemNobumasa Seiyama, Akira Nakamura, Atsushi Imai, Tohru Takagi, Eiichi Miyasaka. 1717-1720 [doi]
• A field test of sivo aid in ChinaJialu Zhang. 1721-1724 [doi]
• Analysis for palatalized articulation of [s] sounds using synthetic speechTakayuki Arai, Keiko Okazaki, Setsuko Imatomi, Yuichi Yoshida. 1725-1728 [doi]
• An attempt to classify LX signalsKrzysztof Marasek. 1729-1732 [doi]
• Time series analysis of glottal cycle lengths of healthy and dysphonic speakersJean Schoentgen, Raoul De Guchteneere. 1733-1736 [doi]
• Generation of language models using the results of image analysisUta Naeve, Gudrun Socher, Gernot A. Fink, Franz Kummert, Gerhard Sagerer. 1739-1742 [doi]
• Modelling pronunciation variability for special domainsGudrun Flach. 1743-1746 [doi]
• On the use of pronunciation rules for improved word recognitionNick Cremelie, Jean-Pierre Martens. 1747-1750 [doi]
• Reducing memory requirements and computational costs for the baum-welch algorithm and application to automatic stochastic network grammar acquisitionJin ichi Murakami. 1751-1754 [doi]
• Language model speaker adaptationStefan Besling, Hans-Günter Meier. 1755-1758 [doi]
• Sentence hypothesisation using NG-gram modelsJerneja Gros, R. Mihelic, Nikola Pavesic. 1759-1762 [doi]
• Optimizing lexical and N-gram coverage via judicious use of linguistic dataRonald Rosenfeld. 1763-1766 [doi]
• A language model for compound words in speech recognitionMarcus Spies. 1767-1770 [doi]
• Permugram language modelsErnst Günter Schukat-Talamazzini, R. Hendrych, Ralf Kompe, Heinrich Niemann. 1773-1776 [doi]
• GLR-parsing of word lattices using a beam search methodSteffen Staab. 1777-1780 [doi]
• Integrating natural language into the word graph search for simultaneous speech recognition and understandingStephanie Seneff, Michael K. McCandless, Victor Zue. 1781-1784 [doi]
• A statistical approach to language modelling for the ATIS taskJoshua Koppelman, Stephen Della Pietra, Mark Epstein, Salim Roukos, Todd Ward. 1785-1788 [doi]
• Lattice parsing and application of integrated language models for speech recognitionGareth J. F. Jones, Harvey Lloyd-Thomas, Jeremy H. Wright. 1789-1792 [doi]
• Robust parsing of n-best speech hypothesis lists using a general grammar-based language modelManny Rayner, Peter J. Wyard. 1793-1796 [doi]
• Improvements in tree-based language model representationFabio Brugnara, Mauro Cettolo. 1797-1800 [doi]
• Language modeling of spontaneous speech in a court contextP. E. Kenne, Mary O Kane, Hamish G. Pearcy. 1801-1804 [doi]
• Study of vowel variations for a Mandarin speech synthesizerChilin Shih. 1807-1810 [doi]
• Using statistical models to predict phrase boundaries for speech synthesisEric Sanders, Paul Taylor. 1811-1814 [doi]
• Naturalness in a high-level synthetic speech systemMark Tatham, Eric Lewis. 1815-1818 [doi]
• Pragmatic effects in speech synthesisKatherine Morton, Mark Tatham. 1819-1822 [doi]
• A scheme for a model-based synthesis by rule of F0 contours of German utterancesHansjörg Mixdorff, Hiroya Fujisaki. 1823-1826 [doi]
• Speech synthesis by rule based on synthesis units considering prosodic featuresYasushi Ishikawa, Kunio Nakajima. 1827-1830 [doi]
• The generation of prosody in the nijmegen rule oriented speech synthesis systemJoop Kerkhoff, Toni C. M. Rietveld. 1831-1834 [doi]
• Phonological rules modelling style variations of e caduc in French parisian spontaneous speech for text-to-speech synthesisVincent Pean, Anne Lacheret-Dujour. 1835-1838 [doi]
• Voiced diphone synthesis using a parametric model and formant based mappingDongbing Wei, J. W. Devaney, C. C. Goodyear. 1841-1844 [doi]
• Robust automatic extraction of diphones with variable boundariesDebra Yarrington, H. Timothy Bunnell, Gene Ball. 1845-1848 [doi]
• Generation of articulatory synthesiser parameters from formant frequencies using a cubic mapping functionAndrew Richard Greenwood. 1849-1852 [doi]
• Two-mass models for speech synthesisR. N. J. Veldhuis, I. J. M. Bogaert, N. J. C. Lous. 1853-1856 [doi]
• Introducing a parametric consonantal model to the articulatory speech synthesiserMats Båvegård. 1857-1860 [doi]
• High-quality Japanese text-to-speech system: NARSYSNobuyuki Katae, Tatsuro Matsumoto, Shinta Kimura, Mitsuko Kaseda, Takayuki Ohyama. 1861-1864 [doi]
• Methodological aspects in a multimedia database of vocal fold pathologiesMaurílio Nunes Vieira, Fergus R. McInnes, Mervyn A. Jack, Arnold G. D. Maran, Colin Watson, Moira Little. 1867-1870 [doi]
• The application of volterra LMS adaptive filtering to speech enhancement for the hearing impairedV. Udayashankara, A. P. Shivaprasad. 1871-1874 [doi]
• CAPDA: managing intelligibility in children and young adults with down s syndrome or speech disordersP. Rosso, J. H. Wright, M. Smith. 1875-1878 [doi]
• Evaluation of a system for segmental speech quality assessment: voiceless fricativesAlan Wrench, Mary S. Jackson, David S. Soutar, A. Gerry Robertson, Janet MacKenzie Beck. 1879-1882 [doi]
• A diagnostic and rehabilitation aid workstation for speech and voice pathologiesBernard Teston, Benoit Galindo. 1883-1886 [doi]
• Improvement, evaluation and testing of a low cost multilingual portable speaking aid for the speech impairedGéza Németh, Gábor Olaszy, Laszlo Pataki, Luis A. Hernández Gómez, Diamantino Freitas. 1887-1890 [doi]
• Empirical study to test the independence of different acoustic voice parameters on a large voice databaseDirk Michaelis, Hans Werner Strube. 1891-1894 [doi]
• The spectral analysis of infant cry: an initial approximationSergio Daniel Cano-Ortiz, Daniel I. Escobedo Beceiro, Manuel Socarras Reyes. 1895-1898 [doi]
• An investigation of locus equations as a source of information for consonantal placeMohamed Yeou. 1901-1904 [doi]
• Automatic labelling of multi-sensor speech database: issues and perspectivesNathalie Parlangeau, Régine André-Obrecht, Alain Marchal. 1905-1908 [doi]
• What does consonant reduction look like, if it exists?R. J. J. H. van Son, Louis C. W. Pols. 1909-1912 [doi]
• Articulatori-acoustic vowel prototypes for speech productionGérard Bailly, Louis-Jean Boë, Nathalie Vallée, Pierre Badin. 1913-1916 [doi]
• Experimental study of the target theory of vowel productionMichel Pitermann, Jean Schoentgen. 1917-1920 [doi]
• Comparing tongue kinematic and acoustic phasing patterns for vowel quantity contrasts in WOLOFRudolph Sock, Pascal Perrier, Anders Löfqvist. 1921-1924 [doi]
• Evaluation of a vowel normalisation procedure based on speech production knowledgePascal Perrier, Lian Apostol, Yohan Payan. 1925-1928 [doi]
• Adaptation of a two-mass model of the vocal cords to a particular speakerChristophe Vescovi, Eric Castelli, Xavier Pelorson. 1933-1936 [doi]
• The money talks interactive speech technology assessment: a report from the fieldStephen Springer, Sara Basson, Ashok Kalyanswamy, Edward Man, Dina Yashchin. 1939-1942 [doi]
• Speech and tactile-based georal systemJacques Siroux, Marc Guyomard, Y. Jolly, Franck Multon, Christophe Remondeau. 1943-1946 [doi]
• Vocalist: a robust, portable spoken language dialogue system for telephone applicationsNorman M. Fraser, J. H. Simon Thornton. 1947-1950 [doi]
• A prototype of a Japanese-Korean realtime speech translation systemMasami Suzuki, Naomi Inoue, Fumihiro Yato, Kazuya Takeda, Seiichi Yamamoto. 1951-1954 [doi]
• Query-response relationships in the oasis speech-recognition systemB. L. Zeigler, Baruch Mazor. 1955-1958 [doi]
• Development of spoken language corpora for travel informationLori Lamel, Sophie Rosset, Samir Bennacef, Hélène Bonneau-Maynard, Laurence Devillers, Jean-Luc Gauvain. 1961-1964 [doi]
• Empirical evaluation of human performance and agreement in parsing discourse constituents in spoken dialogueGiovanni Flammia, Victor Zue. 1965-1968 [doi]
• Multimodal spoken dialogue systems and rapid-prototypingTsuneo Nitta, Mika Amamiya, Hiroyuki Kamio, Hiroshi Matsu ura, Arisa Uchiyama, Masafumi Tamura. 1969-1972 [doi]
• Development and evaluation of a spoken dialogue for a telephone based transaction systemLars Bo Larsen. 1973-1976 [doi]
• Integrating spelling into spoken dialogue recognitionHermann Hild, Alex Waibel. 1977-1980 [doi]
• The application of parallel model combination to a large vocabulary dictation taskMark J. F. Gales, Steve J. Young. 1983-1986 [doi]
• Blind equalization using adaptive filtering for improving speech recognition over telephoneChafic Mokbel, Denis Jouvet, Jean Monné. 1987-1990 [doi]
• Speech-seeking microphone array with multi-stage processingYuchang Cao, Sridha Sridharan, Miles Moody. 1991-1994 [doi]
• Recognition of noisy speech using an auditory modelHalewijn Vereecken, Jean-Pierre Martens. 1995-1998 [doi]
• Stress independent robust HMM speech recognition using neural network stress classificationBrian D. Womack, John H. L. Hansen. 1999-2002 [doi]
• Speech enhancement using two versions of the noisy speech signalKlaus Linhard. 2005-2008 [doi]
• Design and optimization of a two microphone speech enhancement systemRainer Martin. 2009-2012 [doi]
• Time delay estimation for microphone array speech enhancement systemsMartin Drews. 2013-2016 [doi]
• Speech enhancement by eigen decomposition with two-channel observationsYuchang Cao, Sridha Sridharan, Miles Moody. 2017-2020 [doi]
• Robust continuous speech recognition using a microphone arrayDiego Giuliani, Marco Matassoni, Maurizio Omologo, Piergiorgio Svaizer. 2021-2024 [doi]
• The relation between physiological signals and F0: a quantitative analysis methodHelmer Strik. 2027-2030 [doi]
• Analysis of prosodic characteristics in speech advisories and their application to speech outputMasanobu Abe. 2031-2034 [doi]
• Pitch and elocution rate of diverts speechMichel Guitton, F. Javier Caminero-Gil, Joel Crestel, Laure Charonnat. 2035-2038 [doi]
• Detection of accents, phrase boundaries and sentence modality in German with prosodic featuresVolker Strom. 2039-2042 [doi]
• Synthesis and evaluation of intonation with a superposition modelYann Morlec, Gérard Bailly, Véronique Aubergé. 2043-2046 [doi]
• Pitch accent classification of fundamental frequency contours by hidden Markov modelsMarcus L. Fach, Wolfgang Wokurek. 2047-2050 [doi]
• Measuring the perceptual similarity of pitch contoursDik J. Hermes. 2051-2054 [doi]
• Microprosodic study of isolated French word corporaPhilippe Langlais. 2055-2058 [doi]
• Factors affecting F0 peak displacement in SpanishJoaquim Llisterri, Rafael Mann, Carme de la Mota, Antonio Rios. 2061-2064 [doi]
• Generation of intonation: a global approachVéronique Aubergé, Gérard Bailly. 2065-2068 [doi]
• Prevocalic consonant duration in Swedish: effects of vowel quality and postvocalic place of articulationPeter E. Czigler, Dawn M. Behne. 2069-2072 [doi]
• Intonation gesture of slovene: first indicationsP. Vitez, Véronique Aubergé. 2073-2076 [doi]
• Intrinsic prosodic values and segmental contextBarbara Heuft, Thomas Portele. 2077-2080 [doi]
• Describing speech styles using prosody: a pilot studyAndy Tams, Mark Tatham, Julian H. Page. 2081-2084 [doi]
• Statistical methods for the automatic labelling of German prosodyMichael Lehning. 2089-2092 [doi]
• Investigation on unknown word processing and strategies for spontaneous speech understandingAtsuhiko Kai, Seiichi Nakagawa. 2095-2098 [doi]
• New n-best based rejection techniques for improving a real-time telephonic connected word recognition systemF. Javier Caminero-Gil, Celinda de la Torre-Munilla, Luis A. Hernández Gómez, Cesar Martín del Alamo. 2099-2102 [doi]
• Detection of unknown words using garbage cluster models for continuous speech recognitionHiroyuki Sakamoto, Shoichi Matsunaga. 2103-2106 [doi]
• Detection of unknown words and its evaluationA. Jusek, Gernot A. Fink, Franz Kummert, Heike Rautenstrauch, Gerhard Sagerer. 2107-2110 [doi]
• Minimum duration constrained non-keyword modeling and rejection for word spottingSeung-Bae Lee, Lag-Yong Kim, Min-Seong Kim, Jong-Seok Lee, Shin-Wook Kang. 2111-2114 [doi]
• Rejection capabilities for HMM-based speech recognizersSari Accaino, Bart D hoore, Johan Vantieghem, Dirk Van Compernolle. 2115-2118 [doi]
• Multi-lingual connected digits recognitionJoan Salavedra, Claus Jacobsen, Mazin G. Rahim, Ilija Zeljkovic, Jay G. Wilpon. 2119-2122 [doi]
• Recognition of spontaneously spoken connected numbers in Spanish over the telephone lineCelinda de la Torre-Munilla, Luis A. Hernández Gómez, F. Javier Caminero-Gil, Cesar Martín del Alamo. 2123-2126 [doi]
• Lexical fillers for task-independent-training based keyword spotting and detection of new wordsRachida El Méliani, Douglas D. O Shaughnessy. 2129-2132 [doi]
• Topic spotting with task independent modelsMichael J. Carey, Eluned S. Parris. 2133-2136 [doi]
• Phrase spotting using pitch pattern informationToshiyuki Hanazawa, Yoshiharu Abe, Kunio Nakajima. 2137-2140 [doi]
• Speech understanding and speech retrieval for TV news by using connected word spottingYoshiaki Itoh, Jiro Kiyama, Ryuichi Oka. 2141-2144 [doi]
• Talker-independent keyword spotting for information retrievalJ. T. Foote, Gareth J. F. Jones, Karen Sparck Jones, Steve J. Young. 2145-2148 [doi]
• Large vocabulary word scoring as a basis for transcription generationPhilippe Jeanrenaud, M. Siu, Herbert Gish. 2149-2152 [doi]
• New word spotting algorithm based on forward decodingJin ichi Murakami. 2153-2156 [doi]
• Word- and phrase spotting with syllable-based garbage modellingH. Klemm, Fritz Class, Ute Kilian. 2157-2160 [doi]
• Neural networks for nonlinear discriminant analysis in continuous speech recognitionWolfgang Reichl, S. Harengel, Franz Wolfertstetter, Günther Ruske. 2163-2166 [doi]
• Speech recognition experiments with a new multilayer LVQ network (MLVQ)Gerhard Rigoll. 2167-2170 [doi]
• Speaker-adaptation for hybrid HMM-ANN continuous speech recognition systemJoão Paulo Neto, Luís B. Almeida, Mike Hochberg, Ciro Martins, Luís Nunes, Steve Renals, Tony Robinson. 2171-2174 [doi]
• Distributed binary representations for word recognition by TDNN-DTW hybrid systemsPremysl Puzrla, Frédéric Bimbot, Christoph Windheuser. 2175-2178 [doi]
• A robust discrimination method based on selectively trained neural networks for confusable words in noisy conditionsYolande Anglade. 2179-2182 [doi]
• Connectionist speaker normalization and adaptationVictor Abrash, Horacio Franco, Ananth Sankar, Michael Cohen. 2183-2186 [doi]
• A competitive algorithm for training HMM for speech recognitionPedro L. Galindo. 2187-2190 [doi]
• Predictive connectionist speech recognition with a new discriminant learning algorithmMartin Paping, Hans Marti, Mark Renfer. 2193-2196 [doi]
• Preliminary results on speech signal segmentation with recurrent neural networksAntonio J. Rubio, Ronan G. Reilly. 2197-2200 [doi]
• Text independent neural network/rule based hybrid, continuous speech recognitionKlára Vicsi, Attila Vig. 2201-2204 [doi]
• Automatic recognition of Cantonese lexical tones in connected speech by multi-layer perceptronAlfred Ying Pang Ng, P. C. Ching, Lai-Wan Chan. 2205-2208 [doi]
• Combining HMM processing and formant measurements in automatic speech recognitionDave Abberley, Phil Green. 2209-2212 [doi]
• Recurrent neural prediction models for speech recognitionKyungMin Na, Jekwan Ryu, Dong-Il Chang, Soo-Ik Chae, SouGuil Ann. 2213-2216 [doi]
• Exploiting acoustic-phonetic knowledge and neural networks for stop recognitionLinda Djezzar, Jean-Paul Haton. 2217-2220 [doi]
• Estimation of speech formant-dynamics using neural networksPedro Gómez Vilda, Victoria Rodellar, A. Alvarez, Jesús Bobadilla, Jesus Bernal, Victor Nieto Lluis, Mercedes Pérez. 2221-2224 [doi]
• The pronunciation of unfamiliar native and non-native town namesSusan Fitt. 2227-2230 [doi]
• Using two-level morphology to transcribe Swedish namesJoakim Gustafson. 2231-2234 [doi]
• An MRI study of French vowelsDidier Demolin, Jean-Marie Hombert, Véronique Lecuit, Christoph Segebarth, Alain Soquet. 2235-2238 [doi]
• Variable-length sequence matching for phonetic transcription using joint multigramsSabine Deligne, François Yvon, Frédéric Bimbot. 2243-2246 [doi]
• Building multiple pronunciation models for novel words using exploratory computational phonologyGary Tajchman, Eric Foster, Daniel Jurafsky. 2247-2250 [doi]
• Pragmatic factors affecting the phonetic properties of diphthongsLourdes Aguilar, Maria Machuca. 2251-2254 [doi]
• The spatial and the temporal dimensions of consonant reduction in conversational ItalianEdda Farnetani. 2255-2258 [doi]
• Neutralization of consonant length: the case of dutch intervocalic stopsSteven Gillis, Georges De Schutter, J. Verhoeven. 2259-2262 [doi]
• Sound perception between two languages based on analyses of onomatopoeic expressionManabu Kotani, Haruya Matsumoto. 2263-2266 [doi]
• Influence of short-time phase on the perception of stop consonantsLi Liu, Jialong He, Günther Palm. 2269-2272 [doi]
• Enhancing the perceptual salience of information-rich regions of natural intervocalic consonantsAndrew Simpson, Valérie Hazan. 2273-2276 [doi]
• A method to quantify the error distribution in confusion matricesR. J. J. H. van Son. 2277-2280 [doi]
• Speech and nonspeech signal densities for the perception of temporal orderLuis E. López-Bascuas. 2281-2284 [doi]
• Researching the processing structures of human phoneme recognition by analysis of natural stop-consonant-vowel utterances that elicit correct recognition through unusual acoustic patternsEduardo Sá Marta, Fernando Perdigão, Luis Vieira de Sá. 2285-2288 [doi]
• On phonetic boundaries across categories for synthetic and natural vocalic speech soundsFrancesco Cutugno, Renata Savy. 2297-2300 [doi]
• Effects of syllabic position in the perception of spoken EnglishAthanassios Protopapas, Steven Finney, Peter D. Eimas. 2301-2304 [doi]