Speech recognition employing a set of Markov models that includes Markov models representing transitions to and from silence

作者: Lalit R. Bahl

DOI: 10.1121/1.405760

关键词:

摘要: Apparatus and method for constructing word baseforms which can be matched against a string of generated acoustic labels. A set phonetic phone machines are formed, wherein each machine has (i) plurality states, (ii) transitions extends from state to state, (iii) stored probability transition, (iv) label output probabilities, corresponding the producing label. The is formed include subset onset machines. probabilities macine correspond at least one element being uttered beginning speech segment. trailing single end Word constructed by concatenating selected set.

参考文章(9)
Lawrence G. Bahler, Continuous speech recognition Journal of the Acoustical Society of America. ,vol. 80, pp. 1566- 1566 ,(1981) , 10.1121/1.394303
L. Bahl, R. Bakis, P. Cohen, A. Cole, F. Jelinek, B. Lewis, R. Mercer, Speech recognition of a natural text read as isolated words international conference on acoustics, speech, and signal processing. ,vol. 6, pp. 1168- 1171 ,(1981) , 10.1109/ICASSP.1981.1171115
Stephen E. Levinson, Syntactic word recognizer Journal of the Acoustical Society of America. ,vol. 73, pp. 2247- 2247 ,(1977) , 10.1121/1.389482
Lalit R. Bahl, Frederick Jelinek, Robert L. Mercer, A Maximum Likelihood Approach to Continuous Speech Recognition IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-5, pp. 179- 190 ,(1983) , 10.1109/TPAMI.1983.4767370
Frederick Jelinek, Continuous speech recognition by statistical methods Proceedings of the IEEE. ,vol. 64, pp. 532- 556 ,(1976) , 10.1109/PROC.1976.10159
Jean Albert Dreyfus, Speech recognition device for controlling a machine Journal of the Acoustical Society of America. ,vol. 71, pp. 1311- 1311 ,(1974) , 10.1121/1.387693
Stephen E. Levinson, Hidden Markov model speech recognition arrangement Journal of the Acoustical Society of America. ,vol. 86, pp. 2478- 2478 ,(1982) , 10.1121/1.398355
H. Bourlard, Y. Kamp, C. Wellekens, Speaker dependent connected speech recognition via phonetic Markov models international conference on acoustics, speech, and signal processing. ,vol. 10, pp. 1213- 1216 ,(1985) , 10.1109/ICASSP.1985.1168285
Moshier Stephen, Batteau Dwight W, Vocal pulse detector ,(1969)