|
|||||
|
|
| 基于PMC方法的鲁棒声学模型研究 | |
| 引用本文： | 张明新,倪宏,张东滨,陈国平.基于PMC方法的鲁棒声学模型研究[J].中国科学院研究生院学报,2006,23(5):660-664. |
| 作者姓名： | 张明新 倪宏 张东滨 陈国平 |
| 作者单位： | 1. 中国科学院声学研究所,北京,100080;中国科学院研究生院,北京,100049 2. 中国科学院声学研究所,北京,100080 |
| 摘 要： | 在噪声鲁棒语音识别研究中，使用并行模型结合(parallel model combination, PMC)方法得到的模型理论上能够接近匹配噪声环境模型的性能，故成为噪声鲁棒语音识别的重要研究方向。本文首先提出了一种基于前后向差分动态参数的特征MFCC_FWD_BWD，该特征满足PMC对特征构造矩阵可逆的要求。在此基础上，提出了一种用于PMC的新模型——并行子状态隐马尔可夫模型(parallel sub-state hidden Markov model, PSSHMM)，该模型每个状态包含平行关系的子状态，且子状态间存在转移关系。实验表明，PSSHMM模型在各种噪声和SNR下取得了较好的识别效果，特别是对于非平稳噪声，其鲁棒性能非常显著。 |
| 关 键 词： | 并行子状态 语音识别 噪声鲁棒 并行模型结合 |
| 文章编号： | 1002-1175(2006)05-0660-05 |
| 修稿时间： | 2005年7月22日 |
Noise Robust Acoustic Model Research Based on PMC |
|
| ZHANG Ming-Xin,NI Hong,ZHANG Dong-Bin,CHEN Guo-Ping.Noise Robust Acoustic Model Research Based on PMC[J].Journal of the Graduate School of the Chinese Academy of Sciences,2006,23(5):660-664. | |
| Authors: | ZHANG Ming-Xin NI Hong ZHANG Dong-Bin CHEN Guo-Ping |
| Institution: | 1. Institute of Acoustics, Chinese Academy of Sciences, Beijing 100080, China;
2. Graduate School of the Chinese Academy of Sciences, Beijing 100039, China |
| Abstract: | In noise robust speech recognition, for PMC (parallel model combination) method, the performance of the combined model can approach that of the model matching the noisy environment theoretically, so it is an important noise robust speech recognition research field. In this paper, a novel feature MFCC_FWD_BWD, which is based on forward-backward difference dynamic parameters, is presented to satisfy the requirement that the feature construction matrix is invertible for PMC. On this condition, a novel structure model named parallel sub-state hidden Markov model (PSSHMM) is presented for PMC and each state of this model has parallel sub-states with transitions. In experiment, PSSHMM achieves good results under each kinds of noise and each levels of SNR, especially for non-stationary noise, its robust performance is also excellent. |
| Keywords: | parallel sub-state speech recognition noise robust PMC |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |
| 点击此处可从《中国科学院研究生院学报》浏览原始摘要信息 | |
| 点击此处可从《中国科学院研究生院学报》下载免费的PDF全文 | |