THE USE OF RECURRENT NEURAL NETWORKS IN CONTINUOUS SPEECH RECOGNITION

This chapter describes a use of recurrent neural networks (i.e., feedback is incorporated in the computation) as an acoustic model for continuous speech recognition. The form of the recurrent neural network is described along with an appropriate parameter estimation procedure. For each frame of acoustic data, the recurrent network generates an estimate of the posterior probability of of the possible phones given the observed acoustic signal. The posteriors are then converted into scaled likelihoods and used as the observation probabilities within a conventional decoding paradigm (e.g., Viterbi decoding). The advantages of using recurrent networks are that they require a small number of parameters and provide a fast decoding capability (relative to conventional, large-vocabulary, HMM systems)3.

[1]  Frederick Jelinek,et al.  Interpolated estimation of Markov source parameters from sparse data , 1980 .

[2]  T. H. Crystal,et al.  Segmental durations in connected speech signals , 1981 .

[3]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[4]  Sadaoki Furui,et al.  Speaker-independent isolated word recognition using dynamic features of speech spectrum , 1986, IEEE Trans. Acoust. Speech Signal Process..

[5]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[6]  Eric B. Baum,et al.  Supervised Learning of Probability Distributions by Neural Networks , 1987, NIPS.

[7]  Anthony J. Robinson,et al.  Static and Dynamic Error Propagation Networks with Application to Speech Coding , 1987, NIPS.

[8]  Robert A. Jacobs,et al.  Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[9]  T. Crystal,et al.  Segmental durations in connected‐speech signals: Current results , 1988 .

[10]  John Scott Bridle,et al.  Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition , 1989, NATO Neurocomputing.

[11]  Kai-Fu Lee,et al.  Automatic Speech Recognition , 1989 .

[12]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[13]  Harvey F. Silverman,et al.  Combining hidden Markov model and neural network classifiers , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[14]  S. Young.  Competitive training in hidden Markov models , 1990 .

[15]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[16]  D.P. Morgan,et al.  The application of dynamic programming to connected speech recognition , 1990, IEEE ASSP Magazine.

[17]  H. Gish,et al.  A probabilistic approach to the understanding and training of neural network classifiers , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[18]  John S. Bridle,et al.  Alpha-nets: A recurrent 'neural' network architecture with a hidden Markov model interpretation , 1990, Speech Commun..

[19]  Hervé Bourlard,et al.  Continuous speech recognition using multilayer perceptrons with hidden Markov models , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[20]  H. Bourlard,et al.  Links Between Markov Models and Multilayer Perceptrons , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Richard Lippmann,et al.  Neural Network Classifiers Estimate Bayesian a posteriori Probabilities , 1991, Neural Computation.

[22]  J. S. Bridle,et al.  An Alphanet approach to optimising input transformations for continuous speech recognition , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

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

[24]  Bart Kosko,et al.  Neural networks for signal processing , 1992 .

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

[26]  S. W. Beet,et al.  Visual representations of speech signals , 1993 .

[27]  Wj Fitzgerald,et al.  Optimization schemes for neural networks , 1993 .

[28]  T. Robinson.  The state space and “ideal input” representations of recurrent networks , 1993 .

[29]  P.S. Gopalakrishnan,et al.  A channel-bank-based phone detection strategy , 1994, Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing.

[30]  Hervé Bourlard,et al.  Connectionist probability estimators in HMM speech recognition , 1994, IEEE Trans. Speech Audio Process..

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

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

[33]  Wolfram Schiffmann,et al.  Optimization of the Backpropagation Algorithm for Training Multilayer Perceptrons , 1994 .

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