Novel voice activity detection based on cepstrum moments

Statistical methods for voice activity detection (VAD) have shown impressive performance especially with respect to their ability to be tuned parametrically and adoptability with deferent environments. In this paper we propose a novel statistical VAD algorithm using Cepstrum coefficients and their m...

Full description

Bibliographic Details
Main Authors: Farzan, Ali, Nourmohammadi, Ali, Mashohor, Syamsiah, Sadra, Sarvin
Format: Conference or Workshop Item
Language:English
Published: IEEE 2010
Online Access:http://psasir.upm.edu.my/id/eprint/45790/
http://psasir.upm.edu.my/id/eprint/45790/1/Novel%20voice%20activity%20detection%20based%20on%20cepstrum%20moments.pdf
_version_ 1848850538088628224
author Farzan, Ali
Nourmohammadi, Ali
Mashohor, Syamsiah
Sadra, Sarvin
author_facet Farzan, Ali
Nourmohammadi, Ali
Mashohor, Syamsiah
Sadra, Sarvin
author_sort Farzan, Ali
building UPM Institutional Repository
collection Online Access
description Statistical methods for voice activity detection (VAD) have shown impressive performance especially with respect to their ability to be tuned parametrically and adoptability with deferent environments. In this paper we propose a novel statistical VAD algorithm using Cepstrum coefficients and their moments as features for classification. In this method, we use moment ratio of conversation part and silent part to evaluate a threshold measure for differentiating between silent and active (Speech) parts of conversation. To make it robust in noisy environments, we will gradually tune the threshold to adopt it with dynamic background noise. Simulation results show that our proposed method has good performance in noisy environments.
first_indexed 2025-11-15T10:07:52Z
format Conference or Workshop Item
id upm-45790
institution Universiti Putra Malaysia
institution_category Local University
language English
last_indexed 2025-11-15T10:07:52Z
publishDate 2010
publisher IEEE
recordtype eprints
repository_type Digital Repository
spelling upm-457902020-08-10T02:19:22Z http://psasir.upm.edu.my/id/eprint/45790/ Novel voice activity detection based on cepstrum moments Farzan, Ali Nourmohammadi, Ali Mashohor, Syamsiah Sadra, Sarvin Statistical methods for voice activity detection (VAD) have shown impressive performance especially with respect to their ability to be tuned parametrically and adoptability with deferent environments. In this paper we propose a novel statistical VAD algorithm using Cepstrum coefficients and their moments as features for classification. In this method, we use moment ratio of conversation part and silent part to evaluate a threshold measure for differentiating between silent and active (Speech) parts of conversation. To make it robust in noisy environments, we will gradually tune the threshold to adopt it with dynamic background noise. Simulation results show that our proposed method has good performance in noisy environments. IEEE 2010 Conference or Workshop Item PeerReviewed text en http://psasir.upm.edu.my/id/eprint/45790/1/Novel%20voice%20activity%20detection%20based%20on%20cepstrum%20moments.pdf Farzan, Ali and Nourmohammadi, Ali and Mashohor, Syamsiah and Sadra, Sarvin (2010) Novel voice activity detection based on cepstrum moments. In: 2nd International Conference on Computer and Automation Engineering (ICCAE 2010), 26-28 Feb. 2010, Singapore. (pp. 768-770). 10.1109/ICCAE.2010.5451357
spellingShingle Farzan, Ali
Nourmohammadi, Ali
Mashohor, Syamsiah
Sadra, Sarvin
Novel voice activity detection based on cepstrum moments
title Novel voice activity detection based on cepstrum moments
title_full Novel voice activity detection based on cepstrum moments
title_fullStr Novel voice activity detection based on cepstrum moments
title_full_unstemmed Novel voice activity detection based on cepstrum moments
title_short Novel voice activity detection based on cepstrum moments
title_sort novel voice activity detection based on cepstrum moments
url http://psasir.upm.edu.my/id/eprint/45790/
http://psasir.upm.edu.my/id/eprint/45790/
http://psasir.upm.edu.my/id/eprint/45790/1/Novel%20voice%20activity%20detection%20based%20on%20cepstrum%20moments.pdf