System and method for tying variance vectors for speech recognition
作者： Xavier Menendez-Pidal , Ajay Patrikar
DOI:
关键词: Variance (accounting) 、 Mathematics 、 Pattern recognition 、 Learning vector quantization 、 Linde–Buzo–Gray algorithm 、 Vector quantization 、 Acoustic model 、 Speech recognition 、 Artificial intelligence 、 Block (data storage)
摘要: A system and method for implementing a speech recognition engine includes acoustic models that the utilizes to perform procedures. An model optimizer performs vector quantization procedure upon original variance vectors initially associated with models. In certain embodiments, may be performed as block or subgroup procedure. The produces reduced number of tied optimally
lens.org 参考文章(14)
Venkata Gadde, Ananth Sankar, Method and apparatus for improved probabilistic recognition ,(2001)
Asela J. Gunawardana, Adaptation of compressed acoustic models ,(2004)
Xuedong D. Huang, Mei-Yuh Hwang, Dynamically configurable acoustic model for speech recognition systems ASAJ. ,vol. 109, pp. 2553- ,(1999)
Lex S. Olorenshaw, Ruxin Chen, Duanpei Wu, Miyuki Tanaka, Method and apparatus for a parameter sharing speech recognition system Journal of the Acoustical Society of America. ,vol. 108, pp. 1382- ,(1997)
James F. Arnold, Method and apparatus for providing a dynamic speech-driven control and remote service access system Journal of the Acoustical Society of America. ,vol. 121, pp. 2493- ,(2001) , 10.1121/1.2739194
Laurence S Gillick, Francesco Scattone, Apparatuses and methods for developing and using models for speech recognition The Journal of the Acoustical Society of America. ,vol. 104, pp. 1900- ,(1998) , 10.1121/1.424201
Jean-Claude Junqua, Low complexity, high accuracy clustering method for speech recognizer Journal of the Acoustical Society of America. ,vol. 105, pp. 2555- ,(1996) , 10.1121/1.426931
Kenzo Itoh, Text-to-speech synthesis by concatenation using or modifying clustered phoneme waveforms on basis of cluster parameter centroids The Journal of the Acoustical Society of America. ,vol. 104, pp. 3158- ,(1998) , 10.1121/1.423978
Alejandro Acero, Michael D. Plumpe, Method for training of subspace coded gaussian models ,(2003)