科研成果
  概况介绍  
  获奖  
  论文  
  学术报告  
  专著  
  专利  
您现在的位置:首页 > 科研成果 > 论文
论文题目  基于混合模型状态修正算法的非母语语音识别 
论文题目(英文)  
作者 张晴晴 
发表年度 2008 
27 
5 
页码 366-367 
期刊名称 声学技术 
摘要 非母语语音识别的性能较低,对于刚开始学习目标语言的说话人或者口音很重的说话人而言。性能下降更为明显。本文提出一种新型的双语模型修正算法用于提高非母语语音的识别性能。在该算法中,基线声学模型的每个状态都将被代表说话人母语特点的辅助模型状态所修正。文章给出了状态修正准则以及不同候选修正状态数下的性能比较。相比已用非母语训练数据自适应以后的基线声学模型,通过双语模型修正的声学模型在保证识别实时率的前提下,短语错误率相对下降了11.7%。
关键词:非母语语音识别;模型修正;混合模型 
摘要_英文 The performance of automatic speech recognition decreases drastically for normative speakers,especially those who are
justbeginning to learn foreign language or who have heavy accents.A novel bilingual model modification approach is presented to improve nonnative speech recognition accuracy.Each state of baseline nonnative acoustic model is modified with several candidate states from the auxiliary acoustic model,which is trained by speakers’mother tongue.State mapping criterion and n—best candidates are investigated.Using this bilingual model modification approach.compared to the non—
native acoustic model which has already been well trained by adaptation technique MAP,the phrase error rate further is re-
duced by 1 1.7%relatively.while only a small relative increase on real time factor occurs.
Key words:nonnative speech recognition;model modification;mixed model