Improved MO-LRT VAD based on bispectra Gaussian model

被引:17
作者
Górriz, JM
Ramírez, J
Segura, JC
Puntonet, CG
机构
[1] Periodista Daniel Saucedo Aranda, Dpto Teoria Senal Telemat & Commun, Granada 1871, Spain
[2] Periodista Daniel Saucedo Aranda, Dpto Arquitectura & Tecnol Computadores, Granada 18071, Spain
关键词
D O I
10.1049/el:20051761
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
A robust algorithm for voice activity detection (VAD) is presented. It defines a likelihood ratio test (LRT) involving multiple and independent observations of the bispectra. The proposed VAD provides significant improvements in speech/pause discrimination when compared to standardised and recently reported VADs.
引用
收藏
页码:877 / 879
页数:3
相关论文
共 9 条
[1]  
*ETSI EN, 1999, 301708 ETSI EN
[2]  
ITU-T, 1996, G729 ITU T
[3]   Robust endpoint detection and energy normalization for real-time speech and speaker recognition [J].
Li, Q ;
Zheng, JS ;
Tsai, A ;
Zhou, QR .
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2002, 10 (03) :146-157
[4]   Speech pause detection for noise spectrum estimation by tracking power envelope dynamics [J].
Marzinzik, M ;
Kollmeier, B .
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2002, 10 (02) :109-118
[5]  
RAMIREZ J, 2005, IN PRESS IEEE SIGNAL
[6]   A statistical model-based voice activity detection [J].
Sohn, J ;
Kim, NS ;
Sung, W .
IEEE SIGNAL PROCESSING LETTERS, 1999, 6 (01) :1-3
[7]  
SUBBARAO T, 1984, INTRO BISPECTRAL ANA
[8]  
SUBBARAO T, 1982, J TIME SER ANAL, V1, P145
[9]   Robust voice activity detection algorithm for estimating noise spectrum [J].
Woo, KH ;
Yang, TY ;
Park, KJ ;
Lee, C .
ELECTRONICS LETTERS, 2000, 36 (02) :180-181