Voice Activity Detector for Speech Enhancement Applications
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F10%3A00171022" target="_blank" >RIV/68407700:21230/10:00171022 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Voice Activity Detector for Speech Enhancement Applications
Original language description
This paper describes a study of noise robust voice activity detection (VAD) utilizing the periodicity of signal, full band signal energy and high band to low band signal/energy ratio. Conventional VADs are sensitive to variable noisy environment especially with low SNR, and also result in cutting off unvoiced regions of speech as well as random oscillating of output VAD decision. To overcome this problems proposed algorithm firstly identify voiced regions of speech and then differ unvoiced regions fromthe silence or background noise using energy ratio and total signal energy. The performance of the proposed VAD algorithm was examined on real speech signals. Comparisons confirmed that the proposed VAD algorithm outperforms the conventional VAD algorithms especially in the presence of background noise.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
JA - Electronics and optoelectronics
OECD FORD branch
—
Result continuities
Project
—
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2010
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
POSTER 2010 - Proceedings of the 14th International Conference on Electrical Engineering
ISBN
978-80-01-04544-2
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
—
Publisher name
ČVUT v Praze, FEL
Place of publication
Praha
Event location
Praha
Event date
May 6, 2010
Type of event by nationality
EUR - Evropská akce
UT code for WoS article
—