Method, apparatus, and system for building a compact language model for large vocabulary continuous speech recognition (lvcsr) system
作者： Chunrong Lai , Jielin Pan , Qingwei Zhao
DOI:
关键词: Probabilistic logic 、 Set (abstract data type) 、 Computer science 、 Language model 、 Vocabulary 、 Centroid 、 Class (philosophy) 、 Pattern recognition 、 Cluster analysis 、 Artificial intelligence 、 Speech recognition 、 Process (computing)
摘要: According to one aspect of the invention, a method is provided in which set probabilistic attributes an N-gram language model classified into plurality classes. Each resultant class clustered segments build code-book for respective using modified K-means clustering process dynamically adjusts size and centroid each segment during iteration process. A attribute then represented by corresponding belongs.
google.de 参考文章(19)
Carson S. Cumbee, Method of identifying script of line of text ,(2002)
Takao Watanabe, Pattern recognition with a tree structure used for reference pattern feature vectors or for HMM ,(1996)
Biing-Hwang Juang, Filipp E. Korkmazskiy, Methods and apparatus for discriminative training and adaptation of pronunciation networks Journal of the Acoustical Society of America. ,vol. 109, pp. 455- ,(1998)
Raymond Lau, Salim Roukos, Ronald Rosenfeld, Building scalable N-gram language models using maximum likelihood maximum entropy N-gram models ,(1995)
Kenichi Iso, Speech recognition method and apparatus ASAJ. ,vol. 109, pp. 863- ,(1998)
Luca Rigazio, Discriminative clustering methods for automatic speech recognition Journal of the Acoustical Society of America. ,vol. 114, pp. 1719- ,(1999) , 10.1121/1.1627548
Stephen C. Austin, Adam B. Fineberg, Cepstral correction vector quantizer for speech recognition The Journal of the Acoustical Society of America. ,vol. 102, pp. 2482- ,(1997) , 10.1121/1.420378
Safdar M. Asghar, Lin Cong, Speech recognition system having a quantizer using a single robust codebook designed at multiple signal to noise ratios Journal of the Acoustical Society of America. ,vol. 108, pp. 887- ,(1997) , 10.1121/1.1319434
J. Wilpon, L. Rabiner, A modified K-means clustering algorithm for use in isolated work recognition IEEE Transactions on Acoustics, Speech, and Signal Processing. ,vol. 33, pp. 587- 594 ,(1985) , 10.1109/TASSP.1985.1164581
Yoshiharu Abe, Method of boundary estimation for voice recognition and voice recognition device The Journal of the Acoustical Society of America. ,vol. 104, pp. 618- ,(1998) , 10.1121/1.423398