Voice Activity Detection for Speech Enhancement Applications
This paper describes a study of noise-robust voice activity detection (VAD) utilizing the periodicity of the signal, full band signal energy and high band to low band signal energy ratio. Conventional VADs are sensitive to a variably noisy environment especially with low SNR, and also result in cutt...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
CTU Central Library
2010-01-01
|
Series: | Acta Polytechnica |
Subjects: | |
Online Access: | https://ojs.cvut.cz/ojs/index.php/ap/article/view/1251 |
id |
doaj-70d001f82fb84437971a005ae21115b0 |
---|---|
record_format |
Article |
spelling |
doaj-70d001f82fb84437971a005ae21115b02020-11-24T20:53:50ZengCTU Central LibraryActa Polytechnica1210-27091805-23632010-01-015041251Voice Activity Detection for Speech Enhancement ApplicationsE. VerteletskayaK. SakhnovThis paper describes a study of noise-robust voice activity detection (VAD) utilizing the periodicity of the signal, full band signal energy and high band to low band signal energy ratio. Conventional VADs are sensitive to a variably noisy environment especially with low SNR, and also result in cutting off unvoiced regions of speech as well as random oscillating of output VAD decisions. To overcome these problems, the proposed algorithm first identifies voiced regions of speech and then differentiates unvoiced regions from silence or background noise using the energy ratio and total signal energy. The performance of the proposed VAD algorithm is tested on real speech signals. Comparisons confirm that the proposed VAD algorithm outperforms the conventional VAD algorithms, especially in the presence of background noise.https://ojs.cvut.cz/ojs/index.php/ap/article/view/1251voice activity detectionperiodicity measurementvoiced/unvoiced classificationspeech analysis |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
E. Verteletskaya K. Sakhnov |
spellingShingle |
E. Verteletskaya K. Sakhnov Voice Activity Detection for Speech Enhancement Applications Acta Polytechnica voice activity detection periodicity measurement voiced/unvoiced classification speech analysis |
author_facet |
E. Verteletskaya K. Sakhnov |
author_sort |
E. Verteletskaya |
title |
Voice Activity Detection for Speech Enhancement Applications |
title_short |
Voice Activity Detection for Speech Enhancement Applications |
title_full |
Voice Activity Detection for Speech Enhancement Applications |
title_fullStr |
Voice Activity Detection for Speech Enhancement Applications |
title_full_unstemmed |
Voice Activity Detection for Speech Enhancement Applications |
title_sort |
voice activity detection for speech enhancement applications |
publisher |
CTU Central Library |
series |
Acta Polytechnica |
issn |
1210-2709 1805-2363 |
publishDate |
2010-01-01 |
description |
This paper describes a study of noise-robust voice activity detection (VAD) utilizing the periodicity of the signal, full band signal energy and high band to low band signal energy ratio. Conventional VADs are sensitive to a variably noisy environment especially with low SNR, and also result in cutting off unvoiced regions of speech as well as random oscillating of output VAD decisions. To overcome these problems, the proposed algorithm first identifies voiced regions of speech and then differentiates unvoiced regions from silence or background noise using the energy ratio and total signal energy. The performance of the proposed VAD algorithm is tested on real speech signals. Comparisons confirm that the proposed VAD algorithm outperforms the conventional VAD algorithms, especially in the presence of background noise. |
topic |
voice activity detection periodicity measurement voiced/unvoiced classification speech analysis |
url |
https://ojs.cvut.cz/ojs/index.php/ap/article/view/1251 |
work_keys_str_mv |
AT everteletskaya voiceactivitydetectionforspeechenhancementapplications AT ksakhnov voiceactivitydetectionforspeechenhancementapplications |
_version_ |
1716796081842421760 |