The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Une nouvelle méthode de détection d'activité vocale (VAD) en ligne et non supervisée est proposée. La méthode est basée sur une fonctionnalité dérivée des statistiques d'ordre élevé (HOS), améliorée par une deuxième métrique basée sur des pics d'autocorrélation normalisés pour améliorer sa robustesse aux bruits non gaussiens. Cette fonctionnalité est également orientée vers la discrimination entre la parole rapprochée et la parole en champ lointain, fournissant ainsi une méthode VAD dans le contexte d'une interaction interhumaine indépendante du niveau d'énergie. La classification est effectuée par une variante en ligne de l'algorithme d'espérance-maximisation (EM), pour suivre et s'adapter aux variations de bruit dans le signal vocal. Les performances de la méthode proposée sont évaluées sur des données internes et sur CENSREC-1-C, une base de données accessible au public utilisée pour la VAD dans le contexte de la reconnaissance automatique de la parole (ASR). Sur les deux ensembles de tests, la méthode proposée surpasse un algorithme simple basé sur l'énergie et s'avère plus robuste face aux changements de rareté de la parole, de variabilité du SNR et du type de bruit.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
David COURNAPEAU, Tatsuya KAWAHARA, "Voice Activity Detection Based on High Order Statistics and Online EM Algorithm" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 12, pp. 2854-2861, December 2008, doi: 10.1093/ietisy/e91-d.12.2854.
Abstract: A new online, unsupervised voice activity detection (VAD) method is proposed. The method is based on a feature derived from high-order statistics (HOS), enhanced by a second metric based on normalized autocorrelation peaks to improve its robustness to non-Gaussian noises. This feature is also oriented for discriminating between close-talk and far-field speech, thus providing a VAD method in the context of human-to-human interaction independent of the energy level. The classification is done by an online variation of the Expectation-Maximization (EM) algorithm, to track and adapt to noise variations in the speech signal. Performance of the proposed method is evaluated on an in-house data and on CENSREC-1-C, a publicly available database used for VAD in the context of automatic speech recognition (ASR). On both test sets, the proposed method outperforms a simple energy-based algorithm and is shown to be more robust against the change in speech sparsity, SNR variability and the noise type.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.12.2854/_p
Copier
@ARTICLE{e91-d_12_2854,
author={David COURNAPEAU, Tatsuya KAWAHARA, },
journal={IEICE TRANSACTIONS on Information},
title={Voice Activity Detection Based on High Order Statistics and Online EM Algorithm},
year={2008},
volume={E91-D},
number={12},
pages={2854-2861},
abstract={A new online, unsupervised voice activity detection (VAD) method is proposed. The method is based on a feature derived from high-order statistics (HOS), enhanced by a second metric based on normalized autocorrelation peaks to improve its robustness to non-Gaussian noises. This feature is also oriented for discriminating between close-talk and far-field speech, thus providing a VAD method in the context of human-to-human interaction independent of the energy level. The classification is done by an online variation of the Expectation-Maximization (EM) algorithm, to track and adapt to noise variations in the speech signal. Performance of the proposed method is evaluated on an in-house data and on CENSREC-1-C, a publicly available database used for VAD in the context of automatic speech recognition (ASR). On both test sets, the proposed method outperforms a simple energy-based algorithm and is shown to be more robust against the change in speech sparsity, SNR variability and the noise type.},
keywords={},
doi={10.1093/ietisy/e91-d.12.2854},
ISSN={1745-1361},
month={December},}
Copier
TY - JOUR
TI - Voice Activity Detection Based on High Order Statistics and Online EM Algorithm
T2 - IEICE TRANSACTIONS on Information
SP - 2854
EP - 2861
AU - David COURNAPEAU
AU - Tatsuya KAWAHARA
PY - 2008
DO - 10.1093/ietisy/e91-d.12.2854
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 12
JA - IEICE TRANSACTIONS on Information
Y1 - December 2008
AB - A new online, unsupervised voice activity detection (VAD) method is proposed. The method is based on a feature derived from high-order statistics (HOS), enhanced by a second metric based on normalized autocorrelation peaks to improve its robustness to non-Gaussian noises. This feature is also oriented for discriminating between close-talk and far-field speech, thus providing a VAD method in the context of human-to-human interaction independent of the energy level. The classification is done by an online variation of the Expectation-Maximization (EM) algorithm, to track and adapt to noise variations in the speech signal. Performance of the proposed method is evaluated on an in-house data and on CENSREC-1-C, a publicly available database used for VAD in the context of automatic speech recognition (ASR). On both test sets, the proposed method outperforms a simple energy-based algorithm and is shown to be more robust against the change in speech sparsity, SNR variability and the noise type.
ER -