基于DDBHMM的LVCSR系统的单步搜索算法  

One-stage search algorithm for large vocabulary continuous speech recognition based on DDBHMM

作　　者：孙健[1] 王作英[1] 

机构地区：[1]清华大学电子工程系,北京100084

出　　处：《清华大学学报（自然科学版）》2006年第10期1735-1738,共4页Journal of Tsinghua University(Science and Technology)

基　　金：国家"八六三"高技术项目(2001AA114071)

摘　　要：为了在大词汇量连续语音识别(LVCSR)系统中能够利用段长信息,该文按树状组织发音词典,利用语言模型预测技术,基于最大似然状态序列(M LSS)算法,给出了采用基于段长分布的隐含M arkov模型(DDBHMM)的LVCSR系统的二元文法语言模型的单步搜索算法。实验结果表明,尽管单步搜索的替代错误率高于双步搜索,但单步搜索的插入和删除错误率都比双步搜索要低,总体性能上单步搜索要好于双步搜索。同时,DDBHMM能较准确地利用了语音信号中的状态段长信息,采用DDBHMM的LVCSR系统比采用经典的齐次HMM的系统有更好的识别性能。In order to use duration information in a large vocabulary continuous speech recognition （LVCSR） system, the pronunciation dictionary is organized as a tree and the language model look-ahead technique is adopted. Based on the maximum likelihood states sequence algorithm, the one-stage search algorithm for the LVCSR using the duration distribution-based hidden Markov model （DDBHMM） in proposed when the Bigram language model is used. Tests show that, although the two-stage search algorithm has a lower substitute error rate than the single stage one, the insertion errors and deletion errors are both higher than that of the single-stage search. The one-stage search algorithm is, therefore, better than the two-stage search in terms of overall performance. Since the DDBHMM accurately describes the state duration of the speech signals, the DDBHMM system has better performance than system using homogeneous HMM.

关 键 词：大词汇量连续语音识别 单步搜索 段长分布 最大似然状态序列 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]