| 抗噪声的小波谱压缩特征提取算法在语音识别中的应用 |
| |
| 引用本文： | 付丽辉.抗噪声的小波谱压缩特征提取算法在语音识别中的应用[J].量子电子学报,2009,26(4):398-404. |
| |
| 作者姓名： | 付丽辉 |
| |
| 作者单位： | 江苏省淮阴工学院 电子信息工程系，江苏 淮安 223001 |
| |
| 摘 要： | 针对语音识别实际应用过程中的噪声问题，给出了一种新的抗噪声的特征提取算法，即先利用小波变换将语音信号进行小波子带分解，再根据人耳的听觉掩蔽效应，由谱压缩的技术，将小波变换后的子带语音信号进行压缩，从而提取其对应的语音特征。通过MATLAB软件建立实验平台，仿真实验结果表明该语音特征可以在噪声环境下得到较高的识别率。新的特征参数即充分利用了小波的抗噪声特性又有效地降低了语音识别中的训练环境和识别环境间的失配，具有抗噪声的特点。
|
| 关 键 词： | 语音识别 抗噪声 人工神经网络 谱压缩 |
| 收稿时间： | 2008/9/3 |
| 修稿时间： | 2009-01-12 |
Application of speech recognition about robust feature which combines wavelet with spectral compression scheme |
| |
| FU Li-hui.Application of speech recognition about robust feature which combines wavelet with spectral compression scheme[J].Chinese Journal of Quantum Electronics,2009,26(4):398-404. |
| |
| Authors: | FU Li-hui |
| |
| Affiliation: | Department of Electrical Engineering, Huaiyin Institute of Technology, Jiangsu Huaian 223001,China |
| |
| Abstract: | Aimed at the application of speech recognition, a new method of robust feature extraction is presented. The speech was decomposed by wavelet transformation, and then compressed by spectral compression scheme related to human hearing mask theory. Experimental results of MATLAB simulation show that high recognition rate can be obtained by using of the new feature in noise environment. It can make the best of robust characteristics of wavelet and reduce the difference between training and recognition environment. |
| |
| Keywords: | information processing speech recognition artificial neural networks spectral compression |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《量子电子学报》浏览原始摘要信息 |
|
点击此处可从《量子电子学报》下载全文 |
