| 基于Mel子带的鲁棒性说话人识别系统 |
| |
| 引用本文： | 张庆芳,吴迪.基于Mel子带的鲁棒性说话人识别系统[J].苏州大学学报(工科版),2007,27(4):4-7. |
| |
| 作者姓名： | 张庆芳 吴迪 |
| |
| 作者单位： | 1. 苏州经贸职业技术学院,江苏,苏州,215031
2. 苏州大学物理科学与技术学院,江苏,苏州,215006 |
| |
| 基金项目： | 江苏省高校自然科学基金 |
| |
| 摘 要： | 在分析各个Mel子带抗噪性能的基础上，提出了鲁棒性的说话人识别算法，经实验结果证明，在噪声环境下此算法能有效地提高说话人识别系统的识别率。
|
| 关 键 词： | 说话人识别 与文本无关 矢量量化 Mel子带 |
| 文章编号： | 1673-047X（2007）04-0004-04 |
| 收稿时间： | 2007-04-20 |
| 修稿时间： | 2007年4月20日 |
A Robust Mel-Subband Based Speaker Recognition System |
| |
| ZHANG Qing-fang,WU Di.A Robust Mel-Subband Based Speaker Recognition System[J].Journal of Suzhou University(Engineering Science Edition),2007,27(4):4-7. |
| |
| Authors: | ZHANG Qing-fang WU Di |
| |
| Affiliation: | 1. Suzhou Institute of Trade and Commerce, Suzhou 215031, China ; 2. College of Physical Science and Technology, Suzhou University, Suzhou 215006, China |
| |
| Abstract: | The text-independent speaker recognition is an important part of speaker recognition now, it plays a more and more important role because of its ease-to-use and highly popular application in the information technology. At present, the accuracy of recognition is very high in clean environment, but the performance in noisy environment needs to be improved. Based on the analysis of the noise robustness of each subband, a robust recognition algorithm was presented and the simulation shows the algorithm could increase the accuracy of recognition in noise environment. |
| |
| Keywords: | speaker recognition text-independent vector quantization Mel-Subband |
| 本文献已被 维普 万方数据 等数据库收录！ |
|
