• 
  Second European Conference on Speech Communication and Technology, EUROSPEECH 1991, Genova, Italy, September 24-26, 1991. ISCA 1991

Plenary

• 
  Sadaoki Furui: Recent advances in speech recognition.
• 
  Frank Fallside: On the acquisition of speech by machines, ASM.

Continuous Speech Recognition

• 
  Padma Ramesh, Jay G. Wilpon, Maureen A. McGee, David B. Roe, Chin-Hui Lee, Lawrence R. Rabiner: Speaker independent recognition of spontaneously spoken connected digits.
• 
  P. S. Gopalakrishnan, David Nahamoo: Immediate recognition of embedded command words.
• 
  Lynn Wilcox, Marcia A. Bush: HMM-based wordspotting for voice editing and indexing.
• 
  Janet M. Baker: Large vocabulary speaker-adaptive continuous speech recognition research overview at dragon systems.
• 
  Victoria Sgardoni, Dimitrios A. Gaganelis, Eleftherios D. Frangoulis: Continuous density HMM context dependent phones for speech recognition over the telephone.

Segmental Speech Synthesis

• 
  Katsuhiko Shirai, Kazuo Hashimoto, Tetsunori Kobayashi: Text-to-speech synthesizer using superposition of sinusoidal waves generated by synchronized oscillators.
• 
  M. Guerti, G. Bailly: Synthesis-by-rule using compost: modelling resonance trajectories.
• 
  Yasushi Ishikawa, Kunio Nakajima: Neural network based spectral interpolation method for speech synthesis by rule.
• 
  Martine Garnier-Rizet: A rule-based segmental synthesis module for French.

Human Factors

• 
  Norman M. Fraser, G. Nigel Gilbert: Effects of system voice quality on user utterances in speech dialogue systems.
• 
  P. Day, Andreas Grünupp, Klaus-Peter Muthig: A human factors study of speech-to-text technology: consequences of discrete speech.
• 
  Iain R. Murray, John L. Arnott, Alan F. Newell: A comparison of document composition using a listening typewriter and conventional office systems.
• 
  Paulus H. Vossen: Evaluating speech input and output in a CAD-system using the hidden-operator method.
• 
  Mary Zajicek, Jill Hewitt: Mixed mode input for a standard wordprocessor. investigating links between input mode, speech and keyboard, and specific task areas.

Robust Isolated Word Recognition

• 
  Philip Lockwood, Jérôme Boudy: Experiments with a non-linear spectral subtractor (NSS), hidden Markov models and the projection, for robust speech recognition in cars.
• 
  Philip Lockwood, C. Baillargeat, J. M. Gillot, Jérôme Boudy, Gérard Faucon: Noise reduction for speech enhancement in cars: non-linear spectral subtraction / kalman filtering.
• 
  Klaus Fellbaum, Dieter Becker: Isolated word recognition with integrated noise reduction.
• 
  Javier Hernando, Climent Nadeu: A comparative study of parameters and distances for noisy speech recognition.

Neural Nets: Phonetic Features, Phoneme Recognition, and Time Alignment

• 
  Jorma Laaksonen: A new reliability-based phoneme segmentation method for the "neural" phonetic typewriter.
• 
  Bruno Apolloni, Francesco Pazienti, Vincenzo Trotta: Isolated word adaptive recognizer based on neural networks.
• 
  Nobuo Hataoka, Alex Waibel: Evaluation of speaker-independent phoneme recognition on TIMIT database using TDNNs.
• 
  Nelson Morgan, Hervé Bourlard, Chuck Wooters, Phil Kohn, Michael Cohen: Phonetic context in hybrid HMM/MLP continuous speech recognition.
• 
  E. C. Andrews, John S. Mason: Neural network classification of complex-valued speech features.
• 
  Dennis Norris: Rewiring lexical networks on the fly.
• 
  Kjell Elenius, G. Takacs: Phoneme recognition with an artificial neural network.
• 
  Jianxin Jiang, Kechu Yi, Zheng Hu: A new self-organization algorithm of forming a phoneme map.
• 
  Shuping Ran, J. Bruce Millar: Phoneme classification using neural networks based on acoustic-phonetic structure.
• 
  Nigel Dodd, Donald MacFarlane, Chris Marland: Networks for speech recognition structurally optimised by genetic techniques implemented on parallel hardware.

Phonetics I, II

• 
  Jeff Pittam, John Ingram: Influence of vietnamese tone and prosody on the acquisition of English stress patterns.
• 
  Walter F. Sendlmeier: The voiced/unvoiced distinction of initial stops by normal and hearing impaired listeners.
• 
  Krishna S. Nathan: Comparison of formant transition based stop classifiers: time-varying and time-invariant signal models.
• 
  Christian Benoît, Christian Abry, L. J. Roe: The effect of context on labiality in French.
• 
  A. K. Datta, N. R. Ganguli, B. Mukherjee: Nasalisation in bengali speech sounds acoustic-phonetic study.
• 
  N. R. Ganguli: Vowel formant frequency distribution of a major indian language.
• 
  Bernard Harmegnies, Marielle Bruyninckx, Joaquim Llisterri, Dolors Poch: Effects of language change on voice quality in bilingual speakers, corpus content effect.
• 
  T. I. Shevchenko, T. S. Skopintseva: Effects of social and regional backgrounds on LTAS in british English.
• 
  Henk van den Heuvel, Bert Cranen, Toni C. M. Rietveld: Speaker related variability in the durations of dutch speech segments.
• 
  Johan Liljencrants: Numerical simulations of glottal flow.
• 
  Joop Jansen, Bert Cranen, Louis Boves: Modelling of source characteristics of speech sounds by means of the LF-model.
• 
  Hanspeter Herzel, J. Wendler: Evidence of chaos in phonatory samples.
• 
  Van Loan Trinh, Bernard Guérin, Eric Castelli: Source-tract coupling and the subglottal system in an articulatory synthesizer.

Multilingual Speech Recognition Systems (Special Session)

• 
  Paul G. Bamberg, Anne Demedts, John Elder, Caroline B. Huang, Charles Ingold, Mark A. Mandel, Linda Manganaro, Stijn Van Even: Phoneme-based training for large-vocabulary recognition in six european languages.
• 
  Helene Cerf-Danon, Steven DeGennaro, Marco Ferretti, Jorge Gonzalez, Eric Keppel: 1.0 TANGORA - a large vocabulary speech recognition system for five languages.
• 
  Hermann Ney, Roberto Billi: Prototype systems for large-vocabulary speech recognition: polyglot and spicos.

Spoken Language Parsing

• 
  J. H. Wright: Adaptation of grammar-based language models for continuous speech recognition.
• 
  Keh-Yih Su, Tung-Hui Chiang, Yi-Chung Lin: A robustness and discrimination oriented score function for integrating speech and language processing.
• 
  Paolo Baggia, Lorenzo Fissore, Elisabetta Gerbino, Egidio P. Giachin, Claudio Rullent: Improving speech understanding performance through feedback verification.
• 
  Anna Corazza, Renato de Mori, Roberto Gretter, Giorgio Satta: Computation of upper-bounds for island-driven stochastic parsers.
• 
  François Andry, J. H. Simon Thornton: A parser for speech lattices using a UCG grammar.
• 
  Sheryl Young, Michael Matessa: Using pragmatic and semantic knowledge to correct parsing of spoken language utterances.

Speech Coding I-IV

• 
  Arnaldo J. Abrantes, Jorge S. Marques, Isabel Trancoso: Hybrid sinusoidal modeling of speech without voicing decision.
• 
  Jorge S. Marques, Isabel Trancoso, Arnaldo J. Abrantes: Harmonic coding of speech: an experimental study.
• 
  David Rowe, William Cowley, Andrew Perkis: A multiband excitation linear predictive speech coder.
• 
  Shu Hung Leung, K. L. Lai, O. Y. Wong, Andrew Luk: A new coded excitation model using multifrequency decomposition.
• 
  Daniele Sereno: Frame substitution and adaptive post-filtering in speech coding.
• 
  S. A. Atungsiri, R. Soheili, Ahmet M. Kondoz, Barry G. Evans: Effective lost speech frame reconstruction for CELP coders.
• 
  Hiromi Nagabuchi, Nobuhiko Kitawaki: Evaluation and improvement of coded speech quality degraded by cell loss in ATM networks.
• 
  Alain J. Vigier: Combined source-channel coding for a very noisy channed.
• 
  G. Rosina, M. Sant' Agostino, E. Turco, Luigi Vetrano: Testing and quality enhancement of the GSM full rate voice channel.
• 
  U. Kipper, Herbert Reininger, Dietrich Wolf: Low bit rate speech coding using CELP with adaptive excitation codebook.
• 
  Arild Fuldseth, E. Harborg, F. T. Johansen, J. E. Knudsen: A real-time implementable 7 khz speech coder at 16 kbit/s.
• 
  D. J. Zarkadis: Adaptive spectral weighting for vector predictive coding of the LPC-spectra.
• 
  Samir Saoudi, Jean-Marc Boucher, Alain Le Guyader: Medium band speech coding using optimal scalar quantization of LSP.
• 
  Philip Secker, Andrew Perkis: Joint source and channel coding of line spectrum pairs.
• 
  C. F. Chan, K. W. Law: An algorithm for computing LSP frequencies directly from the reflection coefficients.
• 
  Peter Meyer, W. Peters, J. Paulus: Variable rate speech coding using perceptive thresholds and adaptive VUS detection.
• 
  M. R. Suddle, S. A. Atungsiri, Ahmet M. Kondoz, Barry G. Evans: A secure and robust CELP coder for land and satellite mobile systems.
• 
  Carlos M. Ribeiro, Isabel Trancoso: A 4.8 kbps celp coder with post-processing.
• 
  K. W. Law, O. Y. Wong, C. F. Chan: A real-time high quality joint-excitation linear predictive coder at 8 kbps.
• 
  Rosario Drogo Deiacovo, Roberto Montagna: Some experiments in perceptual masking of quantizing noise in analysis-by-synthesis speech coders.
• 
  Gao Yang, Henri Leich, René Boite: A very high-quality CELP coder at the rate of 2400 bps.
• 
  Z. Yong Liu: An effective pulse adaptive code-excited linear predictive coder at 4kb/S.
• 
  C. F. Chan, S. H. Leung: A vocoder using high-order LPC filter with very few non-zero coefficients.

Assessment, Intelligibility and Aids for Disabled

• 
  Mario Rossi, Robert Espesser, Chaslav Pavlovic: The effects of in internal reference system and cross-modality matching on the subjective rating of speech synthesisers.
• 
  H. A. Sydeserff, R. J. Caley, Stephen D. Isard, Mervyn A. Jack, Alex I. C. Monaghan, J. Verhoeven: Evaluation of speech synthesis techniques in a comprehension task.
• 
  P. A. Howard-Jones: 'SOAP' - a speech output assessment package for controlled multilingual evaluation of synthetic speech.
• 
  Tammo Houtgast, Jan A. Verhave: A physical approach to speech quality assessment: correlation patterns in the speech spectrogram.
• 
  H. Miyata, Tammo Houtgast: Weighted MTF for predicting speech intelligibility in reverberant sound fields.
• 
  Ute Jekosch: Speech intelligibility studies for the european hermes spaceplane.
• 
  Jianing Wei, Andrew Faulkner, Adrian Fourcin: An application of speech processing and encoding scheme for Chinese lexical tone and consonant perception by hearing impaired listeners.
• 
  Dimitri Kanevsky, P. Gopalakrishan, Catalina Danis, G. Daggett, Edward A. Epstein, David Nahamoo: On the development of a phone communication aid for the hearing impaired.
• 
  Yolande Anglade, Jean-Marie Pierrel, Jean-Claude Junqua: A spoken language interface for a telephone switchboard operator center.
• 
  Iain R. Murray, John L. Arnott, Norman Alm, Alan F. Newell: A communication system for the disabled with emotional synthetic speech produced by rule.

Speech Synthesis: Techniques and Applications

• 
  Thomas Portele, Birgit Steffan, Rainer Preuß, Wolfgang Hess: German speech synthesis by concatenation of non-parametric units.
• 
  Giuseppe Abbattista, Antonello Riccio, Enzo Mumolo: Automatic document reader with speech output capabilities.
• 
  R. W. King: Tools and processes for developing low-cost and high-quality text-to-speech synthesis for communication aids.
• 
  Hynek Hermansky, Louis Anthony Cox Jr.: Perceptual linear predictive (PLP) analysis-resynthesis technique.
• 
  Reinhold Greisbach, Bernd J. Kröger, O. Esser, G. Plaßmann: A display technique for measurements of natural and synthetic articulatory dynamics.
• 
  Yueh-Chin Chang, Yi-Fan Lee, Bang-Er Shia, Hsiao-Chuan Wang: Statistical models for the Chinese text-to-speech system.
• 
  P. A. Taylor, I. A. Nairn, Andrew M. Sutherland, Mervyn A. Jack: A realtime speech synthesis system.
• 
  Hélène Valbret, Eric Moulines, Jean-Pierre Tubach: Voice tranformation using PSOLA technique.
• 
  Massimo Giustiniani, Piero Pierucci: Phonetic ergodic HMM for speech synthesis.
• 
  Cristina Delogu, P. Paoloni, Paolo Pocci, Ciro Sementina: Quality evaluation of text-to-speech synthesizers using magnitude estimation, categorical estimation, pair comparison and reaction time methods.
• 
  H. Zingte, Cl. Hennebois: Helping young children to associate sounds and letters through speech synthesis.
• 
  Hervé Bourlard: Neural nets and hidden Markov models: review and generalizations.
• 
  N. S. Jayant, J. D. Johnston, Y. Shoham: Coding of wideband speech.

Probabilistic Language Models for Speech Recognition

• 
  Roberto Pieraccini, Esther Levin: Stochastic representation of semantic structure for speech understanding.
• 
  Colin Matheson, Fergus R. McInnes: Incorporating probabilities into the dualgram language model.
• 
  Egidio P. Giachin: A dynamic programming based framework for stochastic spoken language understanding.
• 
  Natividad Prieto, Enrique Vidal: Learning language models through the ECGI method.
• 
  Roberto Cremonini, Marco Ferretti, M. C. Galimberti, Giulio Maltese, Federico Mancini: Using a generative grammar to train a probabilistic language model for speaker-independent speech recognition.

Speech Recognition and Phonetic Modelling

• 
  Katsuhiko Shirai, E. Kitagawa, T. Endo: Optimal construction of context sensitive quantizer for phoneme recognition in continuous speech.
• 
  Mary O'Kane, P. E. Kenne, D. Landy, S. Atkins: Generalising from single-speaker recognition in a feature-based recogniser.
• 
  H. G. Hirsch, Peter Meyer, Hans-Wilhelm Rühl: Improved speech recognition using high-pass filtering of subband envelopes.
• 
  Yifan Gong, Jean Paul Haton: Comparing two phoneme identification methods using a continuous speech recognizer.
• 
  D. Ederveen, Louis Boves: Knowledge-based phoneme recognition.

Speaker Identification and Verification

• 
  J. Kraayeveld, A. C. M. Rietveld, Vincent J. van Heuven: Speaker characterization in dutch using prosodic parameters.
• 
  Alan K. Hunt: New commercial applications of telephone-network-based speech recognition and speaker verification.
• 
  Jean-François Bonastre, Henri Meloni, Philippe Langlais: Analytical strategy for speaker identification.
• 
  L. Xu, John S. Mason: Optimization of perceptually-based spectral transforms in speaker identification.

Pitch Determination and Voice Separation

• 
  Alain de Cheveigné: A mixed speech F0 estimation algorithm.
• 
  Edward Jones, Eliathamby Ambikairajah: A perceptually-based pitch extractor for band-limited speech.
• 
  Yu-Hua Gu: A robust pseudo perceptual pitch estimator.
• 
  Neviano Dal Degan, Marco Fratti: Pitch estimation based on a "narrowed" autocorrelation function.

Speech Recognition: Understanding Systems

• 
  Seiichi Nakagawa, Yoshimitsu Hirata, Isao Murase: The syntax-oriented spoken Japanese understanding system SPOJOS-SYNO II.
• 
  Henning Bergmann, Hans-Hermann Hamer, Andreas Noll, Annedore Paeseler, Horst Tomaschewski: An adaptable man-machine interface using connected-word recognition.
• 
  M. J. Poza, C. de la Torre, Daniel Tapias, Luis Villarrubia: An approach to automatic recognition of keywords in unconstrained speech using parametric models.
• 
  I. Lee Hetherington, Hong C. Leung, Victor W. Zue: Toward vocabulary-independent recognition of telephone speech.
• 
  Ronald A. Cole, Krist Roginski, Mark A. Fanty: English alphabet recognition with telephone speech.
• 
  J.-Y. Fiset, Jean-Marc Robert, Raymond Descout: Evolutionary language models in air traffic control training.
• 
  Gareth J. F. Jones, Jeremy H. Wright, E. N. Wrigley, Michael J. Carey, Eluned S. Parris: Isolated-word sentence recognition using probabilistic context-free grammar.
• 
  Mitchell Hood: Lexical access in a speech understanding and dialogue system.
• 
  Reinhold Haeb-Umbach, Hermann Ney: A look-ahead search technique for large vocabulary continuous speech recognition.
• 
  Carlos Teixeira, Isabel Trancoso: Spectral subtraction for front-end noise reduction in a speech recognizer.

Speech Databases, Analysis And Assessment

• 
  Lori F. Larnel, Jean-Luc Gauvain, Maxine Eskenazi: BREF, a large vocabulary spoken corpus for French.
• 
  Luc Mathan, Dominique Morin: Speech field databases: development and analysis.
• 
  Shuichi Itahashi: Large scale Japanese dialect speech corpora.
• 
  Paulus H. Vossen: Outline of a design-oriented evaluation framework for speech-driven applications.
• 
  Richard Winski, Kamran Kordi: Assessment of continuous speech recognisers using recogniser sensitivity analysis.
• 
  C. Bourjot, A. Boyer, D. Fohr: A tool for assessment of acoustic phonetic lattices.
• 
  Herman J. M. Steeneken, Jeroen G. van Velden: Ramos - recognizer assessment by means of manipulation of speech applied to connected speech recognition.
• 
  Paul van Alphen, Louis C. W. Pols: Comparing various feature vectors in automatic speech recognition.
• 
  Victor W. Zue, James R. Glass, David Goodine, Lynette Hirschman, Hong C. Leung, Michael S. Phillips, Joseph Polifroni, Stephanie Seneff: The MIT ATIS system; preliminary development, spontaneous speech data collection, and performance evaluation.
• 
  S. Benaouicha, A. Rajouani, M. Zyoute: Construction of an Arabic speech data base - duration model of Arabic vowels.
• 
  P. N. Denbigh, J. Zhao: Pitch extraction and separation of overlapping speech.

Neural Nets I, II

• 
  Yoshua Bengio, Renato de Mori, Giovanni Flammia, Ralf Kompe: Phonetically motivated acoustic parameters for continuous speech recognition using artificial neural networks.
• 
  Michael J. Carey, Eluned S. Parris: Adapting input transformations using alpha-nets for whole word speech recognition.
• 
  Les T. Niles: TIMIT phoneme recognition using an HMM-derived recurrent neural network.
• 
  P. O. Husoy, Torbjørn Svendsen: ANN-based speech recognition using a preprocessor for non-linear time compression.
• 
  Helge B. D. Sørensen, Uwe Hartmann: A self-structuring neural noise reduction model.
• 
  Bojan Petek, Alex Waibel, Joseph M. Tebelskis: Integrated phoneme-function word architecture of hidden control neural networks for continuous speech recognition.
• 
  X. Zhang, John S. Mason, E. C. Andrews: Multiple dynamic features to enhance neural net based speaker verification.
• 
  Patrick Haffner, Alex Waibel: Time-delay neural networks embedding time alignment: a performance analysis.
• 
  Yohji Fukuda, Haruya Matsumoto: Phoneme recognition using recurrent neural networks.
• 
  Yasuhiro Komori, Kaichiro Hatazaki: An integration of knowledge and neural networks toward a phoneme typewriter without a language model.

Parsing and Lexical Access

• 
  Junko Hosaka, Toshiyuki Takezawa, Terumasa Ehara: Utilizing empirical data for postposition classification toward spoken Japanese speech recognition.
• 
  Michael S. Phillips, James R. Glass, Victor W. Zue: Automatic learning of lexical representations for sub-word unit based speech recognition systems.
• 
  Roxane Lacouture, Renato de Mori: Lexical tree compression.
• 
  Michael D. Riley, Andrej Ljolje: Lexical access with a statistically-derived phonetic network.
• 
  Giuliano Antoniol, Fabio Brugnara, Diego Giuliani: Admissible strategies for acoustic matching with a large vocabulary.

Modelling Duration in Speech

• 
  Alejandro Macarrón, J. Gregorio Escalada, Miguel Ángel Rodríguez: Generation of duration rules for a Spanish text-to-speech synthesizer.
• 
  L. Mortamet: Implementing duration expert rules into a text-to-speech synthesis system.
• 
  Nobuyoshi Kaiki, Katsuhiko Mimura, Yoshinori Sagisaka: Statistical modeling of segmental duration and power control for Japanese.
• 
  W. Nick Campbell: Phrase-level factors affecting timing in speech.
• 
  Matti Karjalainen, Toomas Altosaar: Phoneme duration rules for speech synthesis by neural networks.

Automatic Speech Recognition: Algorithms I-III

• 
  Fergus R. McInnes: Context-sensitive phoneme lattice generation using interpolated demi-diphone and triphone models.
• 
  J. M. Song, T. Thomas, M. Patel: Experiments of 991-word speaker independent continuous speech recognition on DARPA RM task.
• 
  Henri Meloni, Frédéric Béchet, Philippe Gilles: Bottom-up acoustic-phonetic decoding for the selection of word cohorts from a large vocabulary.
• 
  Antonio M. Peinado, Ramon Román, José C. Segura, Antonio J. Rubio, Pedro García, Jesús E. Díaz-Verdejo: Entropic training for HMM speech recognition.
• 
  Patrick Kenny, S. Parthasarathy, Vishwa Gupta, Matthew Lennig, Paul Mermelstein, Douglas D. O'Shaughnessy: Energy, duration and Markov models.
• 
  J. J. Nijtmans: A new recursive Markov model with a new state pruning approach for large vocabulary continuous speech recognition.
• 
  Fergus R. McInnes: Context-sensitive phoneme lattice generation using interpolated demi-diphone and triphone models.
• 
  Peter Nowell, Henry S. Thompson: An efficient implementation of the n-best algorithm for lexical access.
• 
  Alessandro Falaschi, Massimo Pucci: Automatic derivation of HMM alternative pronunciation network topologies.
• 
  Isabel Galiano, Francisco Casacuberta, Emilio Sanchis: On the structure of subword units for a speaker independent continuous speech task.
• 
  Yunxin Zhao, Hisashi Wakita, Xinhua Zhuang: Generate word transcription dictionary from sentence utterances and evaluate its effect on speaker-independent continuous speech recognition.
• 
  A. P. Varga, Roger K. Moore: Simultaneous recognition of concurrent speech signals using hidden Markov model decomposition.
• 
  I. A. Ballantyne, Andrew M. Sutherland, J. M. Hannah, Mervyn A. Jack: A large vocabulary parallel processing continuous speech recognition system.
• 
  Richard C. Rose, Edward M. Hofstetter: Techniques for robust word spotting in continuous speech messages.
• 
  Alessandro Falaschi, Alfredo Micozzi: Word spotting by CSR through vector quantized background models.
• 
  Jean-Claude Junqua, Hisashi Wakita: Towards an artificial laboratory for the design and simulation of cooperative speech processing algorithms.
• 
  Keith Edwards, Fergus R. McInnes, Mervyn A. Jack: Accent specific modifications for continuous speech recognition based on a sub-word lattice approach.
• 
  Eduardo Lleida, José B. Mariño, Climent Nadeu, Albert Oliveras: Two level continuous speech recognition using demisyllable-based HMM word spotting.
• 
  Ted H. Applebaum, Brian A. Hanson: Tradeoffs in the design of regression features for word recognition.
• 
  Lalit R. Bahl, Peter F. Brown, Peter V. de Souza, Robert L. Mercer, David Nahamoo: A fast algorithm for deleted interpolation.
• 
  Michael A. Franzini, Alex Waibel, Kai-Fu Lee: Recent work in continuous speech recognition using the connectionist viterbi training procedure.
• 
  Volker Steinbiss: A search organization for large-vocabulary recognition based on n-best decoding.
• 
  Yifan Gong, Jean Paul Haton: VINICS: a continuous speech recognizer based on a new robust formulation.
• 
  Shigeki Sagayama: A matrix representation of HMM-based speech recognition algorithms.

Segmentation

• 
  Paul Dalsgaard, Ove Andersen, William J. Barry: Multi-lingual acoustic-phonetic features for a number of european languages.
• 
  Harouna Kabré, Guy Perennou, Nadine Vigouroux: A non-linear filtering method applied to automatic segmentation of multilingual speech corpora.
• 
  Piero Cosi, Daniele Falavigna, Maurizio Omologo: A preliminary statistical evaluation of manual and automatic segmentation discrepancies.
• 
  James M. McQueen, Edward John Briscoe: A computational tool for examining lexical segmentation in continuous speech.
• 
  M. S. Schmidt, G. S. Watson: The evaluation and optimization of automatic speech segmentation.
• 
  G. Feng, N. Achab, R. Combescure: On-line speech segmentation using adaptive models: application to variable rate speech coding.
• 
  P. A. Taylor, Stephen D. Isard: Automatic diphone segmentation.
• 
  Georg Ottesen: An automatic diphone segmentation system.
• 
  Richard Brierton, Barry M. G. Cheetham: An evaluation oof spectral transitivity functions for speech segmentation in variable frame-rate speech vocoding.

Automatic Speech Recognition: Applications

• 
  Dirk Van Compernolle, J. Smolders, P. Jaspers, T. Hellemans: Speaker clustering for dialectic robustness in speaker independent recognition.
• 
  Dina Yashchin, William C. G. Ortel: Experience with speech recognition in automating telephone operator functions.
• 
  F. Canavesio, Lorenzo Fissore, Mario Oreglia, P. Ruscitti: HMM modeling in the public telephone network environment: experiments and results.
• 
  Dominique Morin: Influence of field data in HMM training for a vocal server.
• 
  Alberto Ciaramella, Lorenzo Fissore, Alberto Pacchiotti, Roberto Pacifici: An isolated word speech recognizer prototype for mobile-radio applications.

Natural Language Processing

• 
  James Monaghan, Christine Cheepen: Linguistic modelling for a speech interface in the office context.
• 
  Andrea Di Carlo, Rino Falcone: Ill-formedness problem in the spoken language processing.
• 
  Giulio Maltese, Federico Mancini: A technique to automatically assign parts-of-speech to words taking into account word-ending information through a probabilistic model.
• 
  Marcello Pelillo, Mario Refice: Syntactic category disambiguation through relaxation processes.
• 
  E. N. Wrigley, Jeremy H. Wright: Computational requirements of probabilistic LR parsing for speech recognition using a natural language grammar.

Symbolic Processing in Speech Synthesis

• 
  J. Tiboni, G. Perennon: Phonotypical transcription through the GEPH expert system.
• 
  Briony Williams, Franziska Maier: A spelling corrector for use in text-to-speech synthesis for English.
• 
  Thomas Russi: Robust and efficient parsing for applications such as text-to-speech conversion.
• 
  Robert W. P. Luk, Robert I. Damper: Stochastic transduction for English text-to-phoneme conversion.

Sub-Lexical Unit Modelling

• 
  Mei-Yuh Hwang, Xuedong Huang: Acoustic distribution clustering in phonetic hidden Markov models.
• 
  Mats Blomberg: Modelling articulatory inter-timing variation in a speech recognition system based on synthetic references.
• 
  Kari Torkkola, Mikko Kokkonen, Mikko Kurimo, Pekka Utela: Improving short-time speech frame recognition results by using context.
• 
  Panagiotis A. Rentzepopoulos, George K. Kokkinakis: Phoneme to grapheme conversion using HMM.
• 
  S. H. Parfitt, R. A. Sharman: A bi-directional model of English pronunciation.

Speech Understanding and Dialogue

• 
  David Goodine, Stephanie Seneff, Lynette Hirschman, Michael S. Phillips: Full integration of speech and language understanding in the MIT spoken language system.
• 
  Takayuki Yamaoka, Hitoshi Iida: Dialogue interpretation model and its application to next utterance prediction for spoken language processing.
• 
  W. Boogers: Dialogue construction by compilation.
• 
  Izuru Nogaito, Masahiko Takahashi, Shingo Kuroiwa, Fumihiro Yato: Dialogue management in an extension number guidance system.
• 
  Encarna Segarra, Pedro Garcia: Automatic learning of acoustic and syntactic-semantic levels in continuous speech understanding.
• 
  Paolo Baggia, Alberto Ciaramella, Davide Clementino, Lorenzo Fissore, Elisabetta Gerbino, Egidio P. Giachin, Giorgio Micca, Luciano Nebbia, Roberto Pacifici, G. Pirani, Claudio Rullent: A man-machine dialogue system for speech access to e-mail information using the telephone: implementation and first results.

Assessment

• 
  Renée van Bezooijen, Louis C. W. Pols: 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 paragraph.
• 
  Christian Benoît, Françoise Emerard, Betina Schnabel, A. Tseva: Quality comparisons of prosodic and of acoustic components of various synthesisers.
• 
  Martine Griee, Kiki Vagges, Daniel Hirst: Assessment of intonation in text-to-speech synthesis systems - a pilot test in English and Italian.
• 
  Alex I. C. Monaghan: Evaluation of the naturalness of prosody generated by the CSTR TTS system.
• 
  Ulrich Halka: Speech-model processes for objective quality measurements of speech-coding systems.

Speech Recognition: Stochastic Modelling

• 
  Stephan Euler: Adaptation techniques in tied density hidden Markov models.
• 
  Denis Jouvet, Katarina Bartkova, Jean Monné: On the modelization of allophones in an HMM based speech recognition system.
• 
  Denis Jouvet, Laurent Mauuary, Jean Monné: Automatic adjustments of the structure of Markov models for speech recognition applications.
• 
  Hong C. Leung, I. Lee Hetherington, Victor W. Zue: Speech recognition using stochastic explicit-segment modeling.
• 
  D. Dubois: Comparison of time-dependent acoustic features for a speaker-independent speech recognition system.
• 
  Jean-Luc Gauvain, Chin-Hui Lee: Bayesian learning for hidden Markov model with Gaussian mixture state observation densities.

Speech Interfaces: Systems and Applications

• 
  Hans-Wilhelm Rühl: Voice controlled mail ordering via telephone using SPREIN.
• 
  Stefan Dobler, Werner Armbruester, Peter Meyer, Hans-Wilhelm Rühl: A voice dialling device for mobile radio.
• 
  Kamel Smaïli, François Charpillet, Jean-Marie Pierrel, Jean Paul Haton: A continuous speech recognition approach for the design of a dictation machine.
• 
  David L. Thomson, Jay G. Wilpon, Rafid A. Sukkar, Dimitrios P. Prezas: Automatic speech recognition in the Spanish telephone network.
• 
  Roberto Billi, P. Buttafava, P. De Stefani, M. Gamba, D. Voltolini: Computer-aided, voice-based, medical report preparation: an application to radiology.
• 
  Filipe N. Carlos, Jose P. Carmona, Pedro M. Chagas, Luís C. Oliveira, António Joaquim Serralheiro, Isabel Trancoso: A recognition / synthesis system applied to database access through the telephone network.
• 
  Seppo Helle: An experiment in using a hypertext system in phonetics and speech processing education.
• 
  Giuliano Antoniol, Fabio Brugnara, F. Dalla Palma, Gianni Lazzari, E. Moser: A. RE. s. : an interface for automatic reporting by speech.
• 
  U. Schultheiß, Bernd Lochschmidt: COGNITO - an experimental voice-controlled telecommunication system.
• 
  Jared Bernstein, Dimitry Rtischev: A voice interactive language instruction system.
• 
  Edmund Rooney, Steven M. Hiller, John Laver, Maria-Gabriella Di Benedetto: Macro and micro features for automated pronunciation improvement in the spell system.

Neural Nets: Comparative Studies, Lexical Recognition

• 
  Laurence Devillers, Christian Dugast: Comparison of continuous mixture densities and TDNN in a viterbi-framework: experiments on speaker dependent DARPA RM1+.
• 
  Peter Thurston, Dennis Norris: A comparison of two compression functions used for noisy vowel detection with back-propagation networks.
• 
  Javier Ferreiros, A. Castro, José M. Pardo: Comparison between two different approaches in speaker - independent isolated digit recognition.
• 
  Franck Poirier: DVQ: dynamic vector quantization application to speech processing.
• 
  Yoshua Bengio, Renato de Mori, Giovanni Flammia, Ralf Kompe: A comparative study on hybrid acoustic phonetic decoders based on artificial neural networks.
• 
  Hidefumi Sawai, Satoru Nakamura: Time-delay neural network architectures for high-performance speaker-independent recognition.
• 
  Peter Wittenburg, R. Couwenberg: Recurrent neural nets as building blocks for human word recognition.
• 
  Fisseha Mekuria, Tore Fjällbrant: A neural net model for vector quantization.
• 
  N. H. Russell, Frank Fallside, A. J. Robinson, Richard W. Prager: Lexical access using a recurrent error propagation network.
• 
  Peter Brauer, Per Hedelin, Dieter Huber, Petter Knagenhjelm, Johan Molno: Model or non-model based classifiers.
• 
  Toomas Altosaar, Matti Karjalainen: Event-based recognition and analysis of speech by neural networks.
• 
  Frederick Jelinek: Up from trigrams! - the struggle for improved language models.
• 
  Rolf Carlson: Synthesis: modelling variability and constraints.

Dialogue and Translation

• 
  Marc Guyomard, Jacques Siroux, Alain Cozannet: The role of dialogue in speech recognition the case of the yellow.
• 
  Elisabetta Gerbino, Paolo Baggia: Interpretation of context-dependent utterances in man-machine dialogue.
• 
  S. Eggins, Julie Vonwiller, Christian Matthiessen, P. Sefton: The description of minor clauses in information-seeking telephone dialogues.
• 
  David B. Roe, Fernando Pereira, Richard Sproat, Michael D. Riley, Pedro J. Moreno, Alejandro Macarrón: Toward a spoken language translator for restricted-domain context-free languages.
• 
  N. Venkata Subramaniam, Narayanan Alwar, G. Mallikarjuna, P. Prabhakar Rao, Subramanian Raman: Bidirectional machine translation in indian languages.

Speech Analysis and Signal Representation

• 
  Constantin Papaodysseus, Elias Koukoutsis, C. Triantafillou, C. Vasilatos: Exact monitoring of the numerical error in various speech algorithms.
• 
  Jacques C. Koreman, Bert Cranen, Louis Boves: Automatic computation and comparison of dynamically varying voice source parameters.
• 
  Paavo Alku: Glottal wave analysis with pitch synchronous iterative adaptive inverse filtering.
• 
  Thierry Galas, Xavier Rodet: Generalized functional approximation for source-filter system modeling.
• 
  Frédéric Bimbot, Bishnu S. Atal: An evaluation of temporal decomposition.

Discriminant Training and Speaker Adaptation

• 
  Klaus Zünkler: A discriminative recognizer for isolated and continuous speech using statistical separability measures.
• 
  Otto Schmidbauer, Harald Höge: Speaker adaptation based on articulatory features.
• 
  Fabio Brugnara, Renato de Mori, Diego Giuliani, Maurizio Omologo: A parallel HMM approach to speech recognition.
• 
  Tsuneo Nitta, Jun'ichi Iwasaki, Hiroshi Matsu'ura: Speaker independent word recognition using HMMs with an orthogonalized phonetic segment codebook.
• 
  Pascale Fung, Tatsuya Kawahara, Shuji Doshita: Unsupervised speaker normalization by speaker Markov model converter for speaker-independent speech recognition.

Perception I

• 
  R. J. J. H. van Son, Louis C. W. Pols: The influence of formant track shape on the perception of synthetic vowels.
• 
  P. A. Howard-Jones: Fluctuation of noise background: measurement and significance in relation to speech masking.
• 
  C. Ma, L. F. Willems: The audibility of narrow band noise in fiat spectral complex sounds.
• 
  Gitta P. M. Laan, Dick R. van Bergem, Florien J. Koopmans-van Beinum: The importance of spectral quality of vowels for the intelligibility of sentences.
• 
  Herman J. M. Steeneken, Tammo Houtgast: On the mutual dependency of octave-band-specific contributions to speech intelligibility.
• 
  Brit van Ooyen, Anne Cutler, Dennis Norris: Detection times for vowels versus consonants.
• 
  Dick R. van Bergem: The influence of sentence accent, word stress, and word class on the quality of vowels.
• 
  Florien J. Koopmans-van Beinum: A peak-and-level model for focus words in read and spontaneous natural speech and in synthetic speech.
• 
  John Ingram, Jeff Pittam: Connected speech processes in second language learning.

Speech Synthesis and Prosody

• 
  Rodmonga K. Potapova: Modification of acoustic features in Russian connected speech.
• 
  Helmer Strik, Louis Boves: On the relation between voice source characteristics and prosody.
• 
  Sverre Stensby: Prosody in a rule-based norwegian text-to-speech system.
• 
  A. S. Madhukumar, S. Rajendran, C. Chandra Sekhar, B. Yegnanarayana: Synthesizing intonation for speech in hindi.
• 
  James Hieronymus, Briony J. Williams: An investigation of the relation between perceived pitch accent and automatically-located accent in british English.
• 
  Silvia Quazza: Modelling Italian intonation in a text-to-speech system.
• 
  Michael H. O'Malley, Howard Resnick, Michelle Caisse: An analysis of strategies for finding prosodic clues in text.
• 
  Marcello Balestri: A coded dictionary for stress assignment rules in Italian.

Text-to-Speech Synthesis Systems

• 
  Enrico te Lindert, Hugo van Leeuwen: Speech maker: text-to-speech conversion based on a multi-level, synchronized data structure.
• 
  Eric Lewis, Mark Tatham: A new text-to-speech synthesis system.
• 
  Luís C. Oliveira, Céu Viana, Isabel Trancoso: DIXI - portuguese text-to-speech system.
• 
  P. Molbaek Hansen, N. Reinholt Petersen, Jørgen Rischel, Carsten Henriksen: Higher-level linguistic information in a text-to-speech system for danish.
• 
  Gábor Olaszy: Adaptation of the multivox text-to-speech system to Italian.

Phonetic Modelling

• 
  Partha Niyogi, Victor W. Zue: Correlation analysis of vowels and their application to speech recognition.
• 
  John N. Holmes: Use of phonetic knowledge when designing and training stochastic models for speech recognition.
• 
  Bernhard Kaspar, Karlheinz Schuhmacher: Modelling phones by microsegments in a phonetically oriented recognition system.
• 
  Il K. Kim, H. S. Lee: An extended LVQ2 algorithm and its application to phoneme classification.
• 
  Paul J. Dix, G. J. Vernooij, Gerrit Bloothooft: A hierarchical broad phonetic classification scheme.

Generation of Prosody

• 
  Julia Hirschberg: Using text analysis to predict intonational boundaries.
• 
  Merle Horne: Why do speakers accent 'given' information ?
• 
  Julie Vonwiller, R. W. King, R. W. T. Lloyd: Automatic prosody assignment for interactive synthesized dialogue systems.
• 
  NickYoud NickYoud, Jill House: Generating intonation in a voice dialogue system.
• 
  Rodolfo Delmonte, Roberto Dolci: Computing linguistic knowledge for text-to-speech systems with PROSO.

Speech Processing and Analysis

• 
  C. Acker, Peter Vary, H. Ostendarp: Acoustic echo cancellation using prediction residual signals.
• 
  H. S. Dabis, Alan Wrench: An evaluation of adaptive noise cancelling for speech recognition.
• 
  Enzo Mumolo, Antonello Riccio, Giuseppe Abbattista: An efficient algorithm for real-time voiced/unvoiced decision.
• 
  Tim Aarset, Ben Gold: Models of pitch perception.
• 
  P. Corney, John S. Mason: A new perspective on LPC excitation using singular value decomposition.
• 
  Werner Verhelst, Marcel Borger: Intra-speaker transplantation of speech characteristics an application of waveform vocoding techniques and DTW.
• 
  S. H. Leung, O. Y. Wong, K. L. Lai: Decomposition of the LPC excitation using wavelet functions.
• 
  Eliathamby Ambikairajah, Liam Kilmartin: An adaptive cochlear model for speech recognition.
• 
  Gianni Jacovitti, Piero Pierucci, Alessandro Falaschi: Speech segmentation and classification using higher order moments.

Automatic Speech Recognition: Hardware and Noise Reduction

• 
  Alberto Ciaramella, Davide Clementino, Roberto Pacifici: A PC-housed speaker independent large vocabulary continuous telephonic speech recognizer.
• 
  Abdulmesih Aktas, Klaus Zünkler: Speaker independent continuous HMM-based recognition of isolated words on a real-time multi-DSP system.
• 
  Anastasios Tsopanoglou, Efstathios D. Kyriakis-Bitzaros, J. Mourjopoulos, George K. Kokkinakis: A real time speech decoder using instantaneous frequency and energy.
• 
  M. Schultheiß, Arild Lacroix: Fast hardware for efficient parallel processing of speech signals.
• 
  Jan Sedivý, Jiff Filcev, Jan Uhlír, Tomas Vanek, Václav Hanzl, Zdenek Oliva, Petr Kotek: The one chip speech recognition system.
• 
  Luis Villarrubia, M. J. Poza, C. Crespo: Influence of the telephone line on automatic speech recognition.
• 
  Hynek Hermansky, Nelson Morgan, Aruna Bayya, Phil Kohn: Compensation for the effect of the communication channel in auditory-like analysis of speech (RASTA-PLP).
• 
  Jean-Claude Junqua, Ben Reaves, Brian Mak: A study of endpoint detection algorithms in adverse conditions: incidence on a DTW and HMM recognizer.
• 
  Susanne Dvorak, Thomas Hormann: High-performance speech recognition in noise by continuously updated reference templates.
• 
  Klára Vicsi: Speech enhancement in the case of speech recognizers.
• 
  Juan Gómez-Mena, J. Santos-Suarez, Ramón García Gómez: A robust feature extraction method for automatic speech recognition in noisy environments.

Sub-Word Units for Automatic Speech Recognition

• 
  Lorenzo Fissore, Egidio P. Giachin, Pietro Laface, Giorgio Micca: Selection of speech units for a speaker-independent CSR task.
• 
  Egidio P. Giachin, Chin-Hui Lee, Lawrence R. Rabiner, Aaron E. Rosenberg, Roberto Pieraccini: Word juncture modeling using inter-word context-dependent phone-like units.
• 
  Akito Nagai, Shigeki Sagayama, Kenji Kita: Phoneme-context-dependent LR parsing algorithms for HMM-based continuous speech recognition.
• 
  H. Drexler, R. Roddeman, Louis Boves, Helmer Strik: Optimizing lexical fast search in a large vocabulary isolated word speech recognition system.

Auditory Modelling

• 
  Tore Fjällbrant, Fisseha Mekuria: Signal processing using an auditory filter bank with side-lobes and phase-jumps.
• 
  J. S. C. van Dijk: Notes on auditive coding of sophisticated signals.
• 
  Manfred Beham: An auditorily based spectral transformation of speech signals.
• 
  Andrew C. Morris, Pierre Escudier, Jean-Luc Schwartz: On and off units detect information bottle-necks for speech recognition.
• 
  Jose A. Pozas-Alvarez: A new logic operator-based auditory system model.

Speech Interfaces: Dialogue and Human Factors

• 
  Jeremy Peckham: Speech understanding and dialogue over the telephone: an overview of progress in the sundial project.
• 
  Jean-Pierre Tubach, P. Doignon: A system for natural spoken language queries design, implementation and assessment.
• 
  Guy Deville, Pierre Mousel: Operational validation of syntactic-semantic models in a spoken man-machine dialogue system.
• 
  Bertrand Gaiffe, Laurent Romary, Jean-Marie Pierrel: References in a multimodal dialogue: towards a unified processing.
• 
  Pierre Lefebvre, G. Duncan, Frank Poirier: The user-unix dialogue: a novel integrated approach to enhancing the operating system interface.
• 
  Bodo Arndt: Adoption op verbal and visual dialogue behaviour in document handling systems.
• 
  Paula M. T. Smeele, Anne C. Sittig: The contribution of vision to speech perception.
• 
  Robin J. Lickley, R. C. Shillcock, Ellen Gurman Bard: Processing disfluent speech: how and when are disfluencies found?
• 
  A. Chointere, Jean-Marc Robert, Raymond Descout: Building a user interface for a speech recognition-based telephone application system.
• 
  A. C. Murray, Clive Frankish, Dylan M. Jones: System design and human factors in auditory interfaces.