Voice activity detection in nonstationary noise

被引：123

作者：

Tanyer, SG ^{[1
]}

Özer, H ^{[1
]}

机构：

[1] UEKAE, TUBITAK, TR-06100 Ankara, Turkey

来源：

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING | 2000年 / 8卷 / 04期

关键词：

nonspectral analysis; speech analysis; statistical methods; voice activity detection;

D O I：

10.1109/89.848229

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

A new fusion method for voice activity detection in additive nonstationary noise is suggested. A performance study of the methods: fusion, the recently developed geometrically adaptive energy level, periodicity measure, and zero crossings rates, is presented. The new method is shown to operate reliably down to -5 dB SNR.

引用

页码：478 / 482

页数：5

共 17 条

[1]

BULLINGTON K, 1959, B SYST TECH J MAR, P353

[2]

Freeman D.K., 1989, P INT C AC SPEECH SI, P369

[3]

HAIGH JA, 1993, TENCON'93: 1993 IEEE REGION 10 CONFERENCE ON COMPUTER, COMMUNICATION, CONTROL AND POWER ENGINEERING, VOL 3, P321, DOI 10.1109/TENCON.1993.327987

[4] ROBUST ESTIMATION AND SIGNAL-DETECTION WITH DEPENDENT NONSTATIONARY DATA [J].