| 母语与非母语语音识别声学建模 |
| |
| 引用本文： | 曾定,刘加.母语与非母语语音识别声学建模[J].计算机工程,2010,36(8):170-172. |
| |
| 作者姓名： | 曾定 刘加 |
| |
| 作者单位： | 清华大学电子工程系清华信息科学与技术国家实验室(筹)北京,100084 |
| |
| 基金项目： | 国家自然科学基金委员会与微软亚洲研究院联合基金资助项目(60776800);;国家“863”计划基金资助项目(2006AA010101,2007AA04Z223,2008AA02Z414) |
| |
| 摘 要： | 为了兼容母语与非母语说话人之间的发音变化，提出一种新的声学模型建模方法。分析中国人受母语影响产生的英语发音变化，利用中国人英语发音数据库自适应得到语音模型，采用声学模型融合技术构建融合2种发音规律的识别模型。实验结果证明，中国人英语发音的语音识别率提高了13.4%，但标准英语的语音识别率仅下降1.1%。
|
| 关 键 词： | 语音识别 非母语 模型融合 |
| 修稿时间： | |
Native and Non-native Speech Recognition Acoustic Modeling |
| |
| ZENG Ding,LIU Jia.Native and Non-native Speech Recognition Acoustic Modeling[J].Computer Engineering,2010,36(8):170-172. |
| |
| Authors: | ZENG Ding LIU Jia |
| |
| Affiliation: | (Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 100084) |
| |
| Abstract: | In order to tolerance the pronunciation changes between native speakers and non-native speakers, this paper proposes a new modeling method for acoustic model. By analyzing English pronunciation changes caused by Chinese, it uses non-native English pronunciation database to gain the corresponding speech model with adaptive method, and uses acoustic model merging technology to construct a recognition model merged two pronunciation rules. Experimental results show that recognition rate of non-native English increases by 13.4% and recognition rate on native English decreases by 1.1%. |
| |
| Keywords: | speech recognition non-native model merging |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程》浏览原始摘要信息 |
|
点击此处可从《计算机工程》下载全文 |
