Exploiting Non-Target Region Information for Confidence Measure Based on Bayesian Information Criterion
ISCSLP(2008)
摘要
In this paper appropriate confidence measures (CMs) are investigated for Mandarin command word recognition, both in the so-called target region and non-target region, respectively. Here the target region refers to the recognized speech part of command word while the non-target region refers to the recognized silence part. It shows that exploiting extra information in the non-target region can effectively complement the traditional CM which usually focus on the target region. Furthermore, when analyzing the non-target region in a more theoretical way, where Bayesian information criterion (BIC) is employed to locate more precise boundary in the non-target region, even more improvement is achieved. In two different Mandarin telephone command word tasks, more than 20% relative reduction of equal error rate (EER) is obtained.
更多查看译文
关键词
bayesian information criterion,speech recognition,maximum likelihood estimation,equal error rate,index terms— speech recognition,non-target region information,word recognition,confidence measure,hidden markov models,indexing terms,speech,testing,bayesian methods,databases
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要