


Остановите войну!
for scientists:
ICSLP 1994: Yokohama, Japan
- The 3rd International Conference on Spoken Language Processing, ICSLP 1994, Yokohama, Japan, September 18-22, 1994. ISCA 1994
Plenary Lectures
- Ilse Lehiste:
Poetic metre, prominence, and the perception of prosody: a case of intersection of art and science of spoken language. - Shizuo Hiki:
Possibilities of compensating for defects in speech perception and production. - Willem J. M. Levelt:
On the skill of speaking: how do we access words?
Integration of Speech and Natural Language Processing
- Toshiyuki Takezawa, Tsuyoshi Morimoto:
An efficient predictive LR parser using pause information for continuously spoken sentence recognition. - Kyunghee Kim, Geunbae Lee, Jong-Hyeok Lee, Hong Jeong:
Integrating TDNN-based diphone recognition with table-driven morphology parsing for understanding of spoken Korean. - Frank O. Wallerstein, Akio Amano, Nobuo Hataoka:
Implementation issues and parsing speed evaluation of HMM-LR parser. - Kenji Kita, Yoneo Yano, Tsuyoshi Morimoto:
One-pass continuous speech recognition directed by generalized LR parsing. - Bernd Plannerer, Tobias Einsele, Martin Beham, Günther Ruske:
A continuous speech recognition system integrating additional acoustic knowledge sources in a data-driven beam search algorithm. - Michael K. Brown, Bruce Buntschuh:
A context-free grammar compiler for speech understanding systems. - Katashi Nagao, Kôiti Hasida, Takashi Miyata:
Probabilistic constraint for integrated speech and language processing. - William H. Edmondson, Jon P. Iles:
A non-linear architecture for speech and natural language processing.
Articulatory Motion
- Donna Erickson, Kevin A. Lenzo, Masashi Sawada:
Manifestations of contrastive emphasis in jaw movement in dialogue. - Sook-Hyang Lee, Mary E. Beckman, Michel Jackson:
Jaw targets for strident fricatives. - David J. Ostry, Eric Vatikiotis-Bateson:
Jaw motions in speech are controlled in (at least) three degrees of freedom. - Mark K. Tiede, Eric Vatikiotis-Bateson:
Extracting articulator movement parameters from a videodisc-based cineradiographic database. - Maureen L. Stone, Andrew J. Lundberg:
Tongue-palate interactions in consonants vs. vowels. - Philip Hoole, Christine Mooshammer, Hans G. Tillmann:
Kinematic analysis of vowel production in German. - Sarah Hawkins, Andrew Slater:
Spread of CV and v-to-v coarticulation in british English: implications for the intelligibility of synthetic speech. - Mariko Kondo:
Mechanisms of vowel devoicing in Japanese.
Cognitive Models for Spoken Language Processing
- Peter W. Jusczyk:
The development of word recognition. - Dennis Norris, James M. McQueen, Anne Cutler:
Competition and segmentation in spoken word recognition.
Semantic Interpretation of Spoken Messages
- Roland Kuhn, Renato de Mori:
Recent results in automatic learning rules for semantic interpretation. - Allen L. Gorin:
Semantic associations, acoustic metrics and adaptive language acquisition. - Wayne H. Ward:
Extracting information in spontaneous speech. - Megumi Kameyama, Isao Arima:
Coping with aboutness complexity in information extraction from spoken dialogues. - Otoya Shirotsuka, Ken'ya Murakami:
An example-based approach to semantic information extraction from Japanese spontaneous speech. - Akito Nagai, Yasushi Ishikawa, Kunio Nakajima:
A semantic interpretation based on detecting concepts for spontaneous speech understanding. - Akira Shimazu, Kiyoshi Kogure, Mikio Nakano:
Cooperative distributed processing for understanding dialogue utterances. - Michio Okada, Satoshi Kurihara, Ryohei Nakatsu:
Incremental elaboration in generating and interpreting spontaneous speech. - Wieland Eckert, Heinrich Niemann:
Semantic analysis in a robust spoken dialog system. - Hiroshi Kanazawa, Shigenobu Seto, Hideki Hashimoto, Hideaki Shinchi, Yoichi Takebayashi:
A user-initiated dialogue model and its implementation for spontaneous human-computer interaction.
Prosody
- Andreas Kießling, Ralf Kompe, Anton Batliner, Heinrich Niemann, Elmar Nöth:
Automatic labeling of phrase accents in German. - Kikuo Maekawa:
Intonational structure of kumamoto Japanese: a perceptual validation. - John F. Pitrelli, Mary E. Beckman, Julia Hirschberg:
Evaluation of prosodic transcription labeling reliability in the tobi framework. - Neil P. McAngus Todd, Guy J. Brown:
A computational model of prosody perception. - Kuniko Kakita:
Inter-speaker interaction in speech rhythm: some durational properties of sentences and intersentence intervals. - Bertil Lyberg, Barbro Ekholm:
The final lengthening phenomenon in Swedish - a consequence of default sentence accent? - Dawn M. Behne, Bente Moxness:
Concurrent effects of focal stress, postvocalic voicing and distinctive vowel length on syllable-internal timing in norwegian. - Kazuyuki Takagi, Shuichi Itahashi:
Prosodic pattern of utterance units in Japanese spoken dialogs. - Akira Ichikawa, Shinji Sato:
Some prosodical characteristics in spontaneous spoken dialogue.
Towards Natural Sounding Synthetic Speech
- Inger Karlsson, Johan Liljencrants:
Wrestling the two-mass model to conform with real glottal wave forms. - Helmer Strik, Lou Boves:
Automatic estimation of voice source parameters. - Wen Ding, Hideki Kasuya, Shuichi Adachi:
Simultaneous estimation of vocal tract and voice source parameters with application to speech synthesis. - Pierre Badin, Christine H. Shadle, Y. Pham Thi Ngoc, John N. Carter, W. S. C. Chiu, Celia Scully, K. Stromberg:
Frication and aspiration noise sources: contribution of experimental data to articulatory synthesis. - Nobuhiro Miki, Pierre Badin, Y. Pham Thi Ngoc, Yoshihiko Ogawa:
Vocal tract model and 3-dimensional effect of articulation. - Hisayoshi Suzuki, Jianwu Dang, Takayoshi Nakai, Akira Ishida, Hiroshi Sakakibara:
3-d FEM analysis of sound propagation in the nasal and paranasal cavities. - Kiyoshi Honda, Hiroyuki Hirai, Jianwu Dang:
A physiological model of speech production and the implication of tongue-larynx interaction. - Masaaki Honda, Tokihiko Kaburagi:
A dynamical articulatory model using potential task representation. - Kenneth N. Stevens, Corine A. Bickley, David R. Williams:
Control of a klatt synthesizer by articulatory parameters.
Statistical Methods for Speech Recognition
- Nobuaki Minematsu, Keikichi Hirose:
Speech recognition using HMM with decreased intra-group variation in the temporal structure. - Yukihiro Osaka, Shozo Makino, Toshio Sone:
Spoken word recognition using phoneme duration information estimated from speaking rate of input speech. - Yumi Wakita, Eiichi Tsuboka:
State duration constraint using syllable duration for speech recognition. - Satoru Hayamizu, Kazuyo Tanaka:
Statistical modeling and recognition of rhythm in speech. - Xinhui Hu, Keikichi Hirose:
Recognition of Chinese tones in monosyllabic and disyllabic speech using HMM. - Jun Wu, Zuoying Wang, Jiasong Sun, Jin Guo:
Chinese speech understanding and spelling-word translation based on the statistics of corpus. - Ren-Hua Wang, Hui Jiang:
State-codebook based quasi continuous density hidden Markov model with applications to recognition of Chinese syllables. - Eluned S. Parris, Michael J. Carey:
Estimating linear discriminant parameters for continuous density hidden Markov models. - Franz Wolfertstetter, Günther Ruske:
Discriminative state-weighting in hidden Markov models. - Takao Watanabe, Koichi Shinoda, Keizaburo Takagi, Eiko Yamada:
Speech recognition using tree-structured probability density function. - David B. Roe, Michael D. Riley:
Prediction of word confusabilities for speech recognition. - Li Zhao, Hideyuki Suzuki, Seiichi Nakagawa:
A comparison study of output probability functions in HMMs through spoken digit recognition. - Tomio Takara, Naoto Matayoshi, Kazuya Higa:
Connected spoken word recognition using a many-state Markov model. - Finn Tore Johansen:
Global optimisation of HMM input transformations. - Don X. Sun, Li Deng:
Nonstationary-state hidden Markov model with state-dependent time warping: application to speech recognition. - Jean-François Mari, Jean Paul Haton:
Automatic word recognition based on second-order hidden Markov models. - Xixian Chen, Yinong Li, Xiaoming Ma, Lie Zhang:
On the application of multiple transition branch hidden Markov models to Chinese digit recognition. - M. J. F. Gales, Steve J. Young:
Parallel model combination on a noise corrupted resource management task. - Jean-Baptiste Puel, Régine André-Obrecht:
Robust signal preprocessing for HMM speech recognition in adverse conditions. - Masaharu Katoh, Masaki Kohda:
A study on viterbi best-first search for isolated word recognition using duration-controlled HMM. - Satoshi Takahashi, Yasuhiro Minami, Kiyohiro Shikano:
An HMM duration control algorithm with a low computational cost. - Peter Beyerlein:
Fast log-likelihood computation for mixture densities in a high-dimensional feature space. - Nick Cremelie, Jean-Pierre Martens:
Time synchronous heuristic search in a stochastic segment based recognizer. - Maria-Barbara Wesenick, Florian Schiel:
Applying speech verification to a large data base of German to obtain a statistical survey about rules of pronunciation. - Denis Jouvet, Katarina Bartkova, A. Stouff:
Structure of allophonic models and reliable estimation of the contextual parameters. - Christoph Windheuser, Frédéric Bimbot, Patrick Haffner:
A probabilistic framework for word recognition using phonetic features. - Mohamed Afify, Yifan Gong, Jean Paul Haton:
Nonlinear time alignment in stochastic trajectory models for speech recognition. - David M. Lubensky, Ayman Asadi, Jayant M. Naik:
Connected digit recognition using connectionist probability estimators and mixture-Gaussian densities. - Kazuya Takeda, Tetsunori Murakami, Shingo Kuroiwa, Seiichi Yamamoto:
A trellis-based implementation of minimum error rate training. - Me Yi:
Concatenated training of subword HMMs using detected labels. - Chih-Heng Lin, Pao-Chung Chang, Chien-Hsing Wu:
An initial study on speaker adaptation for Mandarin syllable recognition with minimum error discriminative training.
Phonetics & Phonology I, II
- Yuko Kondo:
Phonetic underspecification in schwa. - Shin'ichi Tanaka, Haruo Kubozono:
Some remarks on the compound accent rule in Japanese. - Rodmonga K. Potapova:
Modifications of acoustic features in Russian connected speech. - Sun-Ah Jun, Mira Oh:
A prosodic analysis of three sentence types with "WH" words in Korean. - Kazue Hata, Heather Moran, Steve Pearson:
Distinguishing the voiceless fricatives f and TH in English: a study of relevant acoustic properties. - Kenzo Itoh:
Correlation analysis between speech power and pitch frequency for twenty spoken languages. - Jongho Jun:
On gestural reduction and gestural overlap in Korean and English /PK/ clusters. - Carlos Gussenhoven, Toni C. M. Rietveld:
Intonation contours and the prominence of F0 peaks. - Agnès Belotel-Grenié, Michel Grenié:
Phonation types analysis in standard Chinese. - Mitsuru Nakai, Hiroshi Shimodaira:
Accent phrase segmentation by finding n-best sequences of pitch pattern templates. - Bruce L. Derwing, Terrance M. Nearey:
Sound similarity judgments and segment prominence: a cross-linguistic study. - Hiroya Fujisaki, Sumio Ohno, Kei-ichi Nakamura, Miguelina Guirao, Jorge A. Gurlekian:
Analysis of accent and intonation in Spanish based on a quantitative model. - Edda Farnetani, Maria Grazia Busà:
Italian clusters in continuous speech. - Cynthia Grover, Jacques M. B. Terken:
Rhythmic constraints in durational control. - Kazutaka Kurisu:
Further evidence for bi-moraic foot in Japanese. - Yuji Sagawa, Masahiro Ito, Noboru Ohnishi, Noboru Sugie:
A model for generating self-repairs. - Christopher Cleirigh, Julie Vonwiller:
Accent identification with a view to assisting recognition (work in progress). - K. Nagamma Reddy:
Phonetic, phonological, morpho-syntactic and semantic functons of segmental duration in spoken telugu: acoustic evidence. - Zita McRobbie-Utasi:
Timing strategies within the paragraph. - Sotaro Sekimoto:
The effect of the following vowel on the frequency normalization in the perception of voiceless stop consonants. - Toshiko Muranaka, Noriyo Hara:
Features of prominent particles in Japanese discourse, frequency, functions and acoustic features. - Shuping Ran, J. Bruce Millar, Iain MacLeod:
Vowel quality assessment based on analysis of distinctive features. - Cristina Delogu, Stella Conte, Ciro Sementina:
Differences in the fluctuation of attention during the listening of natural and synthetic passages. - Barbara Heuft, Thomas Portele:
Production and perception of words with identical segmental structure but different number of syllables. - Caroline B. Huang, Mark A. Son-Bell, David M. Baggett:
Generation of pronunciations from orthographies using transformation-based error-driven learning. - Hidenori Usuki, Jouji Suzuki, Tetsuya Shimamura:
Characteristics of mispronunciation and hesitation in Japanese tongue twister. - Jean-Claude Junqua:
A duration study of speech vowels produced in noise. - Bert Van Coile, Luc Van Tichelen, Annemie Vorstermans, J. W. Jang, M. Staessen:
PROTRAN: a prosody transplantation tool for text-to-speech applications. - Klaus J. Kohler:
Complementary phonology a theoretical frame for labelling an acoustic data base of dialogues. - Sun-Ah Jun, Mary E. Beckman:
Distribution of devoiced high vowels in Korean. - Yeo Bom Yoon:
CV as a phonological unit in Korean. - Manjari Ohala:
Experiments on the syllable in hindi. - John J. Ohala:
Towards a universal, phonetically-based, theory of vowel harmony. - John Ingram, Tom Mylne:
Perceptual parsing of nasal vowels. - Oded Ghitza, M. Mohan Sondhi:
On the perceptual distance between speech segments. - Masato Akagi, Astrid van Wieringen, Louis C. W. Pols:
Perception of central vowel with pre- and post-anchors. - Mario Rossi, Evelyne Peter-Defare, Regine Vial:
Phonological mechanisms of French speech errors. - Mukhlis Abu-Bakar, Nick Chater:
Phonetic prototypes: modelling the effects of speaking rate on the internal structure of a voiceless category using recurrent neural networks. - William J. Hardcastle:
EPG and acoustic study of some connected speech processes. - Osamu Fujimura:
Syllable timing computation in the c/d model. - Tatiana Slama-Cazacu:
Contribution of psycholinguistic perspective for speech technologies.
Adaption and Training for Speech Recognition
- Yutaka Tsurumi, Seiichi Nakagawa:
An unsupervised speaker adaptation method for continuous parameter HMM by maximum a posteriori probability estimation. - Koichi Shinoda, Takao Watanabe:
Unsupervised speaker adaptation for speech recognition using demi-syllable HMM. - Wu Chou, C.-E. Lee, Biing-Hwang Juang:
Minimum error rate training of inter-word context dependent acoustic model units in speech recognition. - Jia-Lin Shen, Hsin-Min Wang, Ren-Yuan Lyu, Lin-Shan Lee:
Incremental speaker adaptation using phonetically balanced training sentences for Mandarin syllable recognition based on segmental probability models. - Lorenzo Fissore, Giorgio Micca, Franco Ravera:
Incremental training of a speech recognizer for voice dialling-by-name. - C. J. Leggetter, Philip C. Woodland:
Speaker adaptation of continuous density HMMs using multivariate linear regression. - Kazumi Ohkura, Hiroki Ohnishi, Masayuki Iida:
Speaker adaptation based on transfer vectors of multiple reference speakers. - Nikko Strom:
Experiments with a new algorithm for fast speaker adaptation. - Tung-Hui Chiang, Yi-Chung Lin, Keh-Yih Su:
A study of applying adaptive learning to a multi-module system. - Jun'ichi Nakahashi, Eiichi Tsuboka:
Speaker adaptation based on fuzzy vector quantization. - Myung-Kwang Kong, Seong-Kwon Lee, Soon-Hyob Kim:
A study on the simulated annealing of self organized map algorithm for Korean phoneme recognition. - Celinda de la Torre, Alejandro Acero:
Discriminative training of garbage model for non-vocabulary utterance rejection.
Science and Technology for Multimodal Interfaces
- Eric Vatikiotis-Bateson, Inge-Marie Eigsti, Sumio Yano:
Listener eye movement behavior during audiovisual speech perception. - Dominic W. Massaro, Michael M. Cohen:
Auditory/visual speech in multimodal human interfaces. - Tadahisa Kondo, Kazuhiko Kakehi:
Effects of phonological and semantic information of kanji and kana characters on speech perception. - Patricia K. Kuhl, Minoru Tsuzaki, Yoh'ichi Tohkura, Andrew N. Meltzoff:
Human processing of auditory-visual information in speech perception: potential for multimodal human-machine interfaces. - Alex Pentland, Trevor Darrell:
Visual perception of human bodies and faces for multi-modal interfaces.