The 1994 Abbot hybrid connectionist-HMM large vocabulary recognition system.

ABBOT is the hybrid connectionist-hidden Markov model largevocabulary speech recognition system developed at Cambridge University. In this system, a recurrent network maps each acoustic vector to an estimate of the posterior probabilities of the phone classes. The maximum likelihood word string is then extracted using Markov models. As in traditional hidden Markov models, the Markov process is used to model the lexical and language model constraints. This paper describes the system which participated in the November 1994 ARPA evaluation of continuous speech recognition systems. The emphasis of the paper is on the differences between the 1993 and 1994 versions of the ABBOT system. This includes the utilization of a larger training corpus (SI284 versus SI84), the extension of the lexicon from 5,000 words to 65,000 words, the application of a trigram language model, and the development of a near-realtime single-pass decoder well suited for the hybrid approach. Experimental results are reported for various test and development sets from the November 1992, 1993 and 1994 ARPA benchmark tests.

[1]  Steve Renals,et al.  DECODER TECHNOLOGY FOR CONNECTIONIST LARGE VOCABULARY SPEECH RECOGNITION , 1995 .

[2]  Janet M. Baker,et al.  The Design for the Wall Street Journal-based CSR Corpus , 1992, HLT.

[3]  Jonathan G. Fiscus,et al.  Benchmark Tests for the DARPA Spoken Language Program , 1993, HLT.

[4]  Steve Renals,et al.  Efficient search using posterior phone probability estimates , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[5]  A. J. Robinson,et al.  Connectionist model combination for large vocabulary speech recognition , 1994, Proceedings of IEEE Workshop on Neural Networks for Signal Processing.

[6]  Daniel Jurafsky,et al.  Learning Phonological Rule Probabilities from Speech Corpora with Exploratory Computational Phonology , 1995, ACL.

[7]  Ciro Martins,et al.  Unsupervised Speaker-Adaptation For Hybrid Hmm-Mlp Continuous Speech Recognition System , 1995 .

[8]  H Hermansky,et al.  Perceptual linear predictive (PLP) analysis of speech. , 1990, The Journal of the Acoustical Society of America.

[9]  Steve Renals,et al.  THE USE OF RECURRENT NEURAL NETWORKS IN CONTINUOUS SPEECH RECOGNITION , 1996 .

[10]  Harris Drucker,et al.  Boosting and Other Ensemble Methods , 1994, Neural Computation.

[11]  S. Renals,et al.  Phone deactivation pruning in large vocabulary continuous speech recognition , 1996, IEEE Signal Processing Letters.

[12]  Lalit R. Bahl,et al.  A tree search strategy for large-vocabulary continuous speech recognition , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[13]  Herbert Gish,et al.  Methods and experiments for text-independent speaker recognition over telephone channels , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[14]  Steve Renals,et al.  Large vocabulary continuous speech recognition using a hybrid connectionist-HMM system , 1994, ICSLP.

[15]  Hynek Hermansky,et al.  RASTA processing of speech , 1994, IEEE Trans. Speech Audio Process..

[16]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[17]  Douglas B. Paul.  An Efficient A* Stack Decoder Algorithm for Continuous Speech Recognition with a Stochastic Language Model , 1992, HLT.

[18]  Ciro Martins,et al.  Speaker-adaptation for hybrid HMM-ANN continuous speech recognition system , 1995, EUROSPEECH.

[19]  P J Webros.  BACKPROPAGATION THROUGH TIME: WHAT IT DOES AND HOW TO DO IT , 1990 .

[20]  Hervé Bourlard,et al.  Continuous speech recognition by connectionist statistical methods , 1993, IEEE Trans. Neural Networks.

[21]  Douglas B. Paul,et al.  An Efficient A* Stack Decoder Algorithm for Continuous Speech Recognition with a Stochastic Language Model , 1992, HLT.

[22]  Hervé Bourlard,et al.  Connectionist Speech Recognition: A Hybrid Approach , 1993 .

[23]  Anthony J. Robinson,et al.  An application of recurrent nets to phone probability estimation , 1994, IEEE Trans. Neural Networks.