摘要
建立了普通话语音性别数据库,提出联合梅尔频率频谱系数(Mel-frequency CepstrumCoefficients,MFCC)的特征提取方法和支持向量机(Support Vector Machine,SVM)的分类方法进行说话人性别识别,并与其它分类方法进行比较,实验结果表明该方法的说话人性别识别准确率达到98.7%,明显优于其它分类器。
A Chinese speech (mandarin) database was established for speakers gender recognition. A combination method is proposed for gender recognition of speakers based on support vector machine and Mel-frequency cepstrum coefficients (MFCC) for classification and feature extraction respectively. The comparative result shows that the accuracy of SVM is 98.7%, which is better than other methods.
出处
《重庆大学学报(自然科学版)》
EI
CAS
CSCD
北大核心
2009年第7期770-774,共5页
Journal of Chongqing University
基金
国家自然科学基金资助项目(50877082)
重庆工学院青年教师科研基金资助项目(20062D39)
关键词
模式识别
分类器
性别识别
支持向量机
梅尔频率频谱系数
pattern recognition
classifiers
gender recognition
mel-frequency cepstrum coefficients
support vector machine