Speech recognition method and apparatus utilizing multi-unit models

作者: Hsaio-Wuen Hon , Kuansan Wang

DOI: 10.1121/1.1697777

关键词:

摘要: A speech recognition method and system utilize an acoustic model that is capable of providing probabilities for both a large unit sub-unit. Each these describes the likelihood set feature vectors from series representing signal. The formed plurality sub-units. At least one sub-unit probability at on are used by decoder to generate score sequence hypothesized words. When combined, sub-units associated with all determine span fewer than in vectors. An overlapping decoding technique also provided.

参考文章(11)
Franco Ravera, Roberto Gemello, Luciano Fissore, A method of and a device for speech recognition employing neural network and markov model recognition techniques Journal of the Acoustical Society of America. ,vol. 110, pp. 1721- ,(1999)
Hiroaki Hattori, Speaker recognition device Journal of the Acoustical Society of America. ,vol. 109, pp. 864- ,(1998)
Vassilios Digalakis, Mitchel Weintraub, Patti Price, Horacio Franco, Leonardo Neumeyer, Method and system for automatic text-independent grading of pronunciation for language instruction ,(1997)
Laurence Gillick, Method for deriving acoustic models for use in speech recognition Journal of the Acoustical Society of America. ,vol. 91, pp. 2306- 2306 ,(1986) , 10.1121/1.403611
John P. Kroeker, Robert L. Powers, Speech recognition circuitry employing nonlinear processing speech element modeling and phoneme estimation Journal of the Acoustical Society of America. ,vol. 95, pp. 1706- 1706 ,(1990) , 10.1121/1.408504
Xuedong D. Huang, Milind V. Mahajan, Method and system for speech recognition using continuous density hidden Markov models Journal of the Acoustical Society of America. ,vol. 107, pp. 2951- ,(1997) , 10.1121/1.429384
William D. Goldenthal, James R. Glass, Segment-based apparatus and method for speech recognition by analyzing multiple speech unit frames and modeling both temporal and spatial correlation The Journal of the Acoustical Society of America. ,vol. 102, pp. 3253- ,(1997) , 10.1121/1.420247
Vladimir Sejnoha, Speech recognition system accommodating different sources Journal of the Acoustical Society of America. ,vol. 102, pp. 684- ,(1994) , 10.1121/1.419931
William M. Kushner, Method, apparatus, and radio optimizing hidden Markov model speech recognition The Journal of the Acoustical Society of America. ,vol. 102, pp. 3252- ,(1997) , 10.1121/1.420243