| 独立分量分析在说话人识别技术中的应用 |
| |
| 引用本文： | 邱作春,曾庆宁. 独立分量分析在说话人识别技术中的应用[J]. 声学技术, 2008, 27(6): 863-866 |
| |
| 作者姓名： | 邱作春 曾庆宁 |
| |
| 作者单位： | 1. 盐城师范学院物理科学与电子技术学院,江苏盐城,224002
2. 桂林电子科技大学信息与通信学院,广西桂林,541004 |
| |
| 基金项目： | 国家自然科学基金资助项目 ， 广西自治区研究生教育创新计划项目 |
| |
| 摘 要： | 独立分量分析方法能够将线性混合信号进行分离,得到统计独立的源信号,能用于提取组合语音的特征基函数。倒谱矢量符合ICA变换的假设条件,用ICA方法对MFCC特征进行转换得到ICA特征基,继而用于说话人识别,建立了一个基于独立分量分析的说话人识别系统。实验结果表明,在噪声环境下此系统具有更高的识别率。
|
| 关 键 词： | 独立分量分析 说话人识别 矢量量化 高斯混合模型 |
| 收稿时间： | 2008-04-10 |
| 修稿时间： | 2008-07-23 |
Application of independent component analysis to speaker recognition technique |
| |
| QIU Zuo-chun and ZENG Qing-ning. Application of independent component analysis to speaker recognition technique[J]. Technical Acoustics, 2008, 27(6): 863-866 |
| |
| Authors: | QIU Zuo-chun and ZENG Qing-ning |
| |
| Affiliation: | QIU Zuo-chun1,ZENG Qing-ning2 |
| |
| Abstract: | Independent Component Analysis(ICA) is a new method to separate the observed mixtures so as to estimate the independent components and can be used to extract the feature bases functions.The characteristic of the cepstrum vector agrees with the assumption of the ICA transformation.ICA bases is transformed from improved robust Mel Frequency Cepstrum Coefficients(MFCC) by ICA and then used in speaker recognition.A novel speaker recognition system based on ICA is presented.The results of experiments show that the proposed system has a higher recognition rate in noisy environments. |
| |
| Keywords: | independent component analysis speaker recognition vector quantization Gaussian mixture model |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《声学技术》浏览原始摘要信息 |
|
点击此处可从《声学技术》下载全文 |
