Integrating induced probability into decoding for large vocabulary continuous speech recognition  

作　　者：YANG Zhanlei LIU Wenju CHAO Hao 

机构地区：[1]National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences Beijing 100190

出　　处：《Chinese Journal of Acoustics》2012年第3期338-352,共15页声学学报（英文版）

基　　金：supported by the National Nature Science Foundation of China(91120303,90820011, 90820303);the 863 National High Technology Development Project of China(20060101Z4073,2006AA01Z194);the National Grand Fundamental Research 973 Program of China(2004CB318105)

摘　　要：This paper integrates location information of frames into conventional acoustic model （AM） and language model （LM） likelihoods, in order to distinguish potential path can- didates more precisely at decoding stage. This paper proposes an induced probability, which represents location information of frames within the whole acoustic space. By integrating the induced probability, the decoder is directed to search within the most promising regions of acoustic space. Promising paths are enhanced and unlikely paths are weakened. Experiments conducted on Chinese Putonghua show that the character error rate is reduced by 10.95% rel- atively without increasing decoding complexity significantly. Finally, pruning analysis shows that integrating location information of frames into traditional decoding framework is helpful for improving system performance.This paper integrates location information of frames into conventional acoustic model （AM） and language model （LM） likelihoods, in order to distinguish potential path can- didates more precisely at decoding stage. This paper proposes an induced probability, which represents location information of frames within the whole acoustic space. By integrating the induced probability, the decoder is directed to search within the most promising regions of acoustic space. Promising paths are enhanced and unlikely paths are weakened. Experiments conducted on Chinese Putonghua show that the character error rate is reduced by 10.95% rel- atively without increasing decoding complexity significantly. Finally, pruning analysis shows that integrating location information of frames into traditional decoding framework is helpful for improving system performance.

分 类 号：TN912.34[电子电信—通信与信息系统] U469.11[电子电信—信息与通信工程]