基于相位调制特征的语音活动检测

吉林大学学报(信息科学版) ›› 2016, Vol. 34 ›› Issue (1): 29-33.

基于相位调制特征的语音活动检测

尚永强, 殷未来, 姜双双, 王金芳

吉林大学通信工程学院, 长春130012

收稿日期:2014-12-01 出版日期:2016-01-25 发布日期:2016-05-10
作者简介:尚永强(1991— ), 男, 山东菏泽人, 吉林大学硕士研究生, 主要从事智能语音信号处理研究, (Tel)86-431-85152021 (E-mail)shangyq13@163. com; 通讯作者: 王金芳(1969— ), 男, 长春人, 吉林大学副教授, 硕士生导师, 主要从事智能语音信号处理研究, (Tel)86-431-85152021(E-mail)jinfangw@163. com。

Voice Activity Detection Based on Phase Modulation Feature

SHANG Yongqiang, YIN Weilai, JIANG Shuangshuang, WANG Jinfang

College of Communications Engineering, Jilin University, Changchun 130012, China

Received:2014-12-01 Online:2016-01-25 Published:2016-05-10

摘要/Abstract

摘要：

针对现有语音活动检测特征易受各种环境噪声影响而导致检测性能恶化的问题, 提出基于相位调制特征的语音活动检测算法。相位调制特征能充分表征语音动态特性, 与静态特征相比, 更能体现语音和噪声间的差异, 从而保证良好检测性能。与传统美尔频率倒谱系数特征的检测对比实验结果表明, 相位调制特征明显优于美尔频率倒谱系数。

关键词: 语音活动检测, 修正群时延函数谱, 调制谱, 相位调制

Abstract:

Addressing the problems that the existing features of voice activity detection is susceptible to interference of various environmental noise, this paper proposes an algorithm using PM(Phase-Modulation) based feature. The feature of phase modulation is capable of fully characterizing the speech dynamic. And compared with the static features, it can more efficiently presents the difference between speech and noise to a higher degree which is the key for the well performed detection. The experimental results of voice activity detection using phase modulation feature and MFCC(Mel Frequency Cepstrum Coefficient) show that phase modulation feature is obviously better than MFCC.

Key words: voice activity detection, modified group delay function spectrum ( MODGDF), modulation spectrum, phase modulation

中图分类号:

TN912. 3

尚永强, 殷未来, 姜双双, 王金芳. 基于相位调制特征的语音活动检测[J]. 吉林大学学报(信息科学版), 2016, 34(1): 29-33.

SHANG Yongqiang, YIN Weilai, JIANG Shuangshuang, WANG Jinfang. Voice Activity Detection Based on Phase Modulation Feature[J]. Journal of Jilin University(Information Science Ed, 2016, 34(1): 29-33.