摘要
通过对语音解码的分析指出了基于似然概率解码的连续语音识别的局限性,并给出了三种基于后验概率段模型(Segment Model,SM)的语音解码方法.这三种方法成功地运用于随机段模型(Stochastic Segment Model,SSM),使误识率比基线系统下降了11%;与此同时还给出了段模型的快速算法,使算法的计算复杂度降到了与隐马尔可夫模型(Hidden Markov Model,HMM)相同的数量级,满足了实用要求.
The decoding algorithms of most continuous speech recognition systems are based on the likelihood score now. However, the likelihood score is only an approximate of the posterior probability and will lead to a suboptimal solution in continuous speech recognition task. In this paper, three Segment Model(SM) decoding methods based on posterior probability are introduced and successfully implemented on a Stochastic Segment Model(SSM) based system. SSM is one kind of segment models. The new decoding methods achieve 11% error rate reduction compared with the baseline system. In the meantime, a fast algorithm for SM is also proposed, which can reduce the computation complexity of the above algorithms to the same level as that of HMM and meet the requirement of real-time applications.
出处
《计算机学报》
EI
CSCD
北大核心
2006年第4期635-641,共7页
Chinese Journal of Computers
基金
国家自然科学基金(60172055
60121302)
北京市自然科学基金(4042025)
国家"九七三"重点基础研究发展规划项目基金(2004CB318105)资助
关键词
后验概率
段模型
汉语数字串
语音识别
模式识别
posterior probability
segment model
mandarin digit string
speech recognition
pattern recognition