Abstract

roduction-based knowledge into the recognition framework. By using an explicit time-domain articulatory model of the mechanisms of co-articulation, it is hoped to obtain a more accurate model of contextual effects in the acoustic signal, while using fewer parameters than traditional acoustically-driven approaches. Separate articulatory and acoustic models are provided, and in each case the parameters of the models are automatically optimised over a training data set. A predictive statistically-based model of co-articulation is described, and found to yield improved articulatory modelling accuracy compared with X-ray articulatory traces. Parameterised acoustic vectors are synthesised by a set of artificial neural networks, and the resulting acoustic representations are used to re-score N-best recognition hypothesis lists produced by an HMM-based recogniser. The system is evaluated on two test databases, one including speaker-specific X-ray training data and the other aco

Citations

6231	Maximum likelihood from incomplete data via the EM algorithm - Dempster, Laird - 1977
3909	Neural networks for pattern recognition - Bishop - 1995
3116	A tutorial on hidden Markov models and selected applications in speech recognition - Rabiner - 1989
1530	Introduction to the theory of neural computation - Hertz, Krogh - 1991
874	Error bounds for convolutional codes and an asymptotically optimum decoding algorithm - Viterbi - 1967
634	Hierarchical mixtures of experts and the EM algorithm - Jordan, Jacobs - 1994
550	Comparison of parametric representations of monosyllabic word recognition in continuously spoken sentences - Davis, Mermelstein - 1980
505	A direct adaptive method for faster back-propagation learning: the RPROP algorithm - Riedmiller, Braun - 1993
377	Parallel distributed processing: Explorations in the microstructure of cognition - Rumelhart, McClelland - 1986
290	Connectionist Learning Procedures - Hinton - 1990
283	Introduction to Random Signals and Applied Kalman Filtering - Brown, Hwang - 1997
247	Forward models: Supervised learning with a distal teacher - Jordan, Rumelhart - 1992
227	Hidden Markov Models for Speech Recognition - Huang, Ariki, et al. - 1990
194	Probalistic interpretation of feedforward classification network outputs, with relationships to statistical pattern recognition - Bridle - 1990
165	An application to recurrent nets to phone probability estimation - Robinson - 1994
140	Acoustic Theory of Speech Production - Fant - 1960
139	Tree-based state tying for high accuracy acoustic modelling - Young, Odell, et al. - 1994
133	Bayesian Methods for Adaptive Models - MacKay - 1992
131	Review of text-to-speech conversion for English - Klatt - 1987
128	NETtalk: a parallel network that learns to read aloud - Sejnowski, Rosenberg - 1986
113	Multi–stream speech recognition - Bourlard, Dupont, et al. - 1996
95	Speech Analysis Synthesis and Perception - Flanagan - 1972
93	The use of context in large vocabulary speech recognition - Odell - 1995
71	A dynamical approach to gestural patterning in speech production - Saltzman, Munhall - 1989
70	Articulatory phonology: An overview - Browman, Goldstein - 1992
65	Regression analysis by examples - Chatterjee, Price - 1977
57	A Stochastic Segment Model for Phoneme-Based Continuous Speech Recognition - Ostendorf, Roukos - 1989
56	The 1994 HTK large vocabulary speech recognition system - Woodland, Leggetter, et al. - 1995
54	Towards increasing speech recognition error rates - BOURLARD - 1995
51	Techniques for Estimating Vocal-tract Shapes from the Speech Signal - Schroeter, Sondhi - 1994
49	On the role of spectral transition for speech perception - Furui - 1986
49	Effect of glottal pulse shape on the quality of natural vowels - Rosenberg - 1971
46	Flanagan Synthesis of Voiced Sounds from a Two-Mass Model of the Vocal - Ishizaka, L - 1972
39	Speech Synthesis and Recognition - Holmes - 1988
39	Articulatory model for the study of speech production - Mermelstein - 1973
37	Context-Dependent Classes in a Hybrid Recurrent Network-HMM Speech Recognition System - Kershaw, Hochberg, et al. - 1996
37	X-ray microbeam speech production database user’s handbook - Westbury - 1994
34	The challenge of spoken language systems: Research directions for the nineties - Cole, Hirschman, et al. - 1995
33	A statistical approach to automatic speech recognition using the atomic speech units constructed from overlapping articulatory features - Deng, Sun - 1994
32	The Waxholm system - a progress report - Bertenstam, Carlson, et al. - 1995
32	The SUMMIT speech recognition system: phonological modelling and lexical access - Zue, Glass, et al. - 1990
31	Trainable Speech Synthesis - Donovan - 1996
31	Considerations in dynamic time warping algorithms for discrete word recognition - Rabiner, Rosenberg, et al. - 1978
30	Automatic speech recognition - Lee - 1989
30	An articulatory synthesizer for perceptual research - Rubin, Baer, et al. - 1981
29	A model for articulatory dynamics and control - Coker - 1976
29	The window model of coarticulation: articulatory evidence - Keating - 1990
29	Integration of Diverse Recognition Methodologies Through Reevaluation of N-Best Sentence Hypotheses - Ostendorf, Kannan, et al. - 1991
26	Introduction to the Theory of Statistics. McGraw-Hill Companies - Mood, Graybill, et al. - 1974
25	Speech synthesis - Kelly, Lochbaum - 1962