Novel voice activity detection based on cepstrum moments

Citation

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).

Abstract

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.

Download File

Text (Abstract)
Novel voice activity detection based on cepstrum moments.pdf
Download (32kB)

Additional Metadata

Item Type:	Conference or Workshop Item (Paper)
Divisions:	Faculty of Engineering
DOI Number:	https://doi.org/10.1109/ICCAE.2010.5451357
Publisher:	IEEE
Keywords:	Voice activity detection; Cepstrum
Depositing User:	Nabilah Mustapa
Date Deposited:	10 Aug 2020 02:19
Last Modified:	10 Aug 2020 02:19
Altmetrics:	http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1109/ICCAE.2010.5451357
URI:	http://psasir.upm.edu.my/id/eprint/45790
Statistic Details:	View Download Statistic

Actions (login required)

View Item