%0 Journal Article
%T MFCC feature extraction of speech based on pitch period<br>基于基音周期的语音MFCC参数提取
%A CHEN Di
%A GONG Wei-guo
%A YANG Li-ping
%A <br>陈迪
%A 龚卫国
%A 杨利平
%J 计算机应用
%D 2007
%I 
%X This paper proposed a MFCC feature extraction method based on pitch period to improve the performance of speaker recognition.The original speech signals were decomposed into two parts: the speech within the length of multiple pitch periods and that out of the pitch period.The former part was reserved to minimize the spectral distortion.The improved MFCC feature extraction method was also used in the verification experiment of the text-independent speaker recognition.The result shows the recognition rate is improved.
%K speaker verification
%K pitch period
%K Mel-Frequency Cepstral Coefficients(MFCC)
%K spectral distance<br>说话人识别
%K 基音周期
%K MFCC参数
%K 频谱距离
%K 基音周期
%K MFCC
%K 参数提取
%K period
%K pitch
%K based
%K speech
%K 稳定性
%K 识别率
%K 说话人确认
%K 验证
%K 确认实验
%K 文本无关
%K 频谱失真
%K 测试语音
%K 训练
%K 长度
%K 整数倍
%K 语音分解
%K 基本原理
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=831E194C147C78FAAFCC50BC7ADD1732&aid=14E16CBD27430512751DAFBC78FE690C&yid=A732AF04DDA03BB3&vid=DB817633AA4F79B9&iid=94C357A881DFC066&sid=CBB937218406B640&eid=F5F3E44D7A429F27&journal_id=1001-9081&journal_name=计算机应用&referenced_num=0&reference_num=6