| 基于临界小波参数和新序列核支持向量机的说话人识别 |
| |
| 引用本文： | 李鉴,李杰.基于临界小波参数和新序列核支持向量机的说话人识别[J].信阳师范学院学报(自然科学版),2012,25(3):398-401. |
| |
| 作者姓名： | 李鉴 李杰 |
| |
| 作者单位： | 1. 北京科技大学自动化学院,北京100083;南阳理工学院电子与电气工程学院,河南南阳473000
2. 北京科技大学自动化学院,北京,100083 |
| |
| 基金项目： | 国家自然科学基金项目(10671011);北京市教委重点学科共建项目(XK10008053) |
| |
| 摘 要： | 在研究可再生希尔伯特空间框架的基础之上,构建出一个新的序列核来对语音序列间的相似性进行度量.特征提取部分针对传统语音短时分析技术容易出现丢失信息的现状,提出了一种基于临界带宽的小波包变换算法.用美国国家标准与技术研究所(NIST)2004年评测数据集进行实验,结果表明该方法可以大幅度提高识别率.
|
| 关 键 词： | 小波包变换 临界频带 支持向量机 说话人识别 |
A Sequence Kernel Support Vector Machine Based on the Critical Bandwidth Wavelet Packet Feature for Speaker Recognition |
| |
| LI Jian
,
LI Jie.A Sequence Kernel Support Vector Machine Based on the Critical Bandwidth Wavelet Packet Feature for Speaker Recognition[J].Journal of Xinyang Teachers College(Natural Science Edition),2012,25(3):398-401. |
| |
| Authors: | LI Jian LI Jie |
| |
| Institution: | 1(1.School of Automation,University of Science and Technology Beijing,Beijing 100083,China; 2.Department of Electronics and Electrical Engineering,Nanyang Institute of Technology,Nanyang 473000,China) |
| |
| Abstract: | By using the framework of Reproducing Kernel Hilbert Space,a new sequence kernel was developed to measure similarity between sequences of observations.In the feature extraction,a new wavelet packet transform algorithm was presented based on the critical bandwidth.Testing on the National Institute of Standards and Technology(NIST) 2004 evaluation database was performed and the experiment results show that this method can greatly improve the recognition rate. |
| |
| Keywords: | wavelet packet critical bandwidth support vector machine speaker recognition |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
