A unified syntax direction mechanism for automatic speech recognition systems using hidden Markov models

Connected utterance speech recognition systems using hidden Markov models have traditionally been based on the Viterbi algorithm, an instance of Bellman's principle. This is a two-pass algorithm: the first pass makes local decisions on the direction of potential optimal paths, and the second generates a globally optimal path from the local information. This study eliminates the necessity for a second pass by associating separate objects, representing the history of the recognition, with each recognition score. As a result, it is possible to impose an arbitrary syntax direction mechanism on the recognition by examining these history objects at each frame of the recognized speech and predicting possible recognition paths. This technique presents a natural arrangement for implementing speech recognizers on parallel computing architectures. A demonstration recognizer using a push-down automation to implement a context-free grammar on a transputer network is described.<<ETX>>

[1]  Stephen E. Levinson,et al.  A speaker-independent, syntax-directed, connected word recognition system based on hidden Markov models and level building , 1985, IEEE Trans. Acoust. Speech Signal Process..

[2]  Hermann Ney,et al.  Dynamic programming speech recognition using a context-free grammar , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[3]  Jr. G. Forney,et al.  The viterbi algorithm , 1973 .

[4]  Stephen E. Levinson,et al.  Continuously variable duration hidden Markov models for speech analysis , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  Frederick Jelinek,et al.  The development of an experimental discrete dictation recognizer , 1985 .