文章摘要
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,(6):863~866
独立分量分析在说话人识别技术中的应用
Application of independent component analysis to speaker recognition technique
投稿时间:2008-04-10  修订日期:2008-07-23
DOI:
中文关键词: 独立分量分析  说话人识别  矢量量化  高斯混合模型
英文关键词: independent component analysis  speaker recognition  vector quantization  Gaussian mixture model
基金项目:国家自然科学基金资助项目(60272038);广西自治区研究生教育创新计划项目
作者单位E-mail
邱作春  qiuzch@163.com 
曾庆宁   
摘要点击次数: 1025
全文下载次数: 1014
中文摘要:
      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。
英文摘要:
      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.
查看全文   查看/发表评论  下载PDF阅读器
关闭