| 基于小波包分析的特征参数提取 |
| |
| 引用本文： | 胡文吉,王让定.基于小波包分析的特征参数提取[J].宁波大学学报(理工版),2007,20(1):51-54. |
| |
| 作者姓名： | 胡文吉 王让定 |
| |
| 作者单位： | 宁波大学,纵横智能软件研究所,浙江,宁波,315211 |
| |
| 基金项目： | 浙江省自然科学基金
,
宁波市博上基金 |
| |
| 摘 要： | 在分析MFCC提取原理的基础上,结合小波包分析理论,得到新的特征参数.提出了一种新的特征参数提取方法,用动态时间规整法,分别测试了MFCC的识别率和新的特征参数的识别率.研究证明新的特征参数不仅具有较高的识别率,而且有一定的抗噪声能力.
|
| 关 键 词： | 小波包 美尔倒谱系数 特征参数 动态时间规整 小波包分析 特征参数提取 Wavelet Packet Analysis Based Coefficient Feature 能力 抗噪声 研究 识别率 测试 规整法 动态时间 方法 分析理论 结合 原理 MFCC |
| 文章编号： | 1001-5132(2007)01-0051-04 |
| 修稿时间： | 2006-06-11 |
Extraction of Feature Coefficient Based on Wavelet Packet Analysis |
| |
| HU Wen-ji,WANG Rang-ding.Extraction of Feature Coefficient Based on Wavelet Packet Analysis[J].Journal of Ningbo University(Natural Science and Engineering Edition),2007,20(1):51-54. |
| |
| Authors: | HU Wen-ji WANG Rang-ding |
| |
| Institution: | CKC Software Lab, Ningbo University, Ningbo 315211, China |
| |
| Abstract: | In the paper, a method of new feature factor extraction is proposed. Based on the MFCC extraction theory and combining with wavelet packet analysis, a new feature factor is obtained. Using DTW, we have tested the speech recognition rate of MFCC and the new feature factor. The experiment suggests that the new feature factor achieves not only high recognition rate, but also anti-noise capacity. |
| |
| Keywords: | wavelet packet Mel frequency cepstral coefficient feature coefficient dynamic time warping |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
