短语音噪声环境下说话人识别特征提取  

Recognition feature extraction based on little speech data for speaker under noisy conditions

作　　者：高会贤[1] 马全福[1] 郑晓势[2] 

机构地区：[1]济南工程职业技术学院现代教育技术中心,济南250200 [2]山东省计算中心,济南250014

出　　处：《计算机应用》2010年第10期2712-2714,共3页journal of Computer Applications

基　　金：山东省自然科学基金资助项目(Y2007G44;Y2007G62)

摘　　要：为了使说话人识别系统在语音较短和存在噪声的环境下也具有较高的识别率,基于矢量量化识别算法,对提取的特征参数进行研究。把小波变换与美尔频率倒谱系数(MFCC)的提取相结合,并将改进后的特征与谱质心特征进行了组合,建立了一种美尔频率小波变换系数+谱质心(MFWTC+SC)的新的组合特征参数。经实验表明,该组合特征可以有效地提高说话人识别系统的性能。To improve the performance of speaker recognition in the condition of noise and little speech data, feature parameters were studied based on the Vector Quantization （VQ）. An improved feature named WFWTC was proposed by combining extraction of Mel Frequency Cepstrum Coefficient （MFCC） with wavelet transform. After that, a new feature was established based on WFWTC and Spectral Centroid （SC）. The experimental results show that the feature is feasible for speaker identification.

关 键 词：短语音 说话人识别 噪声环境 组合特征 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]