Implementation of Cepstral Voice Activity Detector
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F17%3A00315575" target="_blank" >RIV/68407700:21230/17:00315575 - isvavai.cz</a>
Result on the web
<a href="http://radio.feld.cvut.cz/conf/poster/proceedings/Poster_2017/Section_IC/IC_070_Kosek.pdf" target="_blank" >http://radio.feld.cvut.cz/conf/poster/proceedings/Poster_2017/Section_IC/IC_070_Kosek.pdf</a>
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Implementation of Cepstral Voice Activity Detector
Original language description
Analysis of Cepstral Voice Activity Detector (VAD) behavior in different acoustic conditions is presented in this paper. The analyzed VADs use computation of shorttime signal energy and cepstral distance as a criterion value (characteristic) for detecting speech activity and also several different methods of heuristic thresholding are used for a decision about speech and non-speech activity in current shorttime frame. The implementation of described VADs was written in C++ programming language and integrated into CtuCopy speech processing tool as an internal module and it also allows the application of VAD in speech feature extraction. Implemented VADs were tested on the QUT-NOISETIMIT corpus and their behavior under different acoustic conditions is studied and discussed in the experimental part.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20201 - Electrical and electronic engineering
Result continuities
Project
—
Continuities
S - Specificky vyzkum na vysokych skolach
Others
Publication year
2017
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the International Student Scientific Conference Poster – 21/2017
ISBN
978-80-01-06153-4
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
1-4
Publisher name
Czech Technical University in Prague
Place of publication
Praha
Event location
Praha
Event date
May 23, 2017
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—