Block synchronous decoding
作者： William H. Rockenbeck , Julian J. Odell
DOI:
关键词: Cache language model 、 Block (data storage) 、 Decoding methods 、 Hidden Markov model 、 Artificial intelligence 、 Cache locality 、 CPU cache 、 Pattern recognition (psychology) 、 Pattern recognition 、 Computer science 、 Cache
摘要: A pattern recognition system and method are provided. Aspects of the invention particularly useful in combination with multi-state Hidden Markov Models. Pattern is effected by processing Model Blocks. This block-processing allows processor to perform more operations upon data while such cache memory. By so increasing locality, aspects provide significantly improved speed.
google.co.uk 参考文章(12)
Shigeki Sagayama, Jun-ichi Takami, Shoichi Matsunaga, Yasunage Miyazawa, Unsupervised Speaker Adaptation Using All-Phoneme Ergodic Hidden Markov Network IEICE Transactions on Information and Systems. ,vol. 78, pp. 1044- 1050 ,(1995)
Tian-Shu Wang, Heung-Yeung Shum, Ying-Qing Xu, Nan-Ning Zheng, Unsupervised Analysis of Human Gestures pacific rim conference on multimedia. pp. 174- 181 ,(2001) , 10.1007/3-540-45453-5_23
Yifan Gong, Decoding multiple HMM sets using a single sentence grammar ,(2001)
Hiroaki Hattori, Speaker recognition device Journal of the Acoustical Society of America. ,vol. 109, pp. 864- ,(1998)
Richard M. Schwartz, Long Nguyen, Single tree method for grammar directed, very large vocabulary speech recognizer The Journal of the Acoustical Society of America. ,vol. 102, pp. 3253- ,(1997) , 10.1121/1.420245
T. Robinson, J. Christie, Time-first search for large vocabulary speech recognition international conference on acoustics speech and signal processing. ,vol. 2, pp. 829- 832 ,(1998) , 10.1109/ICASSP.1998.675393
Quingwei Zhao, Qing Guo, Yonghong Yan, Zhiwei Lin, Baosheng Yuan, Method and system for generating and searching an optimal maximum likelihood decision tree for hidden markov model (hmm) based speech recognition ,(2000)
聖一 中川, Seiichi Nakagawa, Language discrimination device ,(1994)
Sagayama Shigeki, Miyazawa Yasunaga, ACOUSTING MODEL ADAPTION SYSTEM ,(1994)
Iso Kenichi, METHOD AND DEVICE FOR LARGE-VOCABULARY SPEECH RECOGNITION ,(1998)