Joint Soft Threshold and Statistical Estimation for Speech Enhancement

Van Khanh Mai 1, 2 Dominique Pastor 3, 1 Abdeldjalil Aissa El Bey 4, 1
3 Lab-STICC_IMTA_CID_TOMS
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
4 Lab-STICC_IMTA_CACS_COM
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
Abstract : This paper presents a novel method for speech enhancement based on the combination of sigmoid shrinkage and bayesian estimator. The main idea is to apply a joint detection and estimation to noisy speech before using a standard minimum-mean-squared-error (MMSE) estimator. Hence, the proposed method can take advantage of two basic approaches for improving the quality of noisy speech. Experiments performed on stationary and non-stationary noisy speech signals show that the proposed approach is promising when compared to classical methods, in terms of objective and pseudo-subjective measurements.
Type de document :
Communication dans un congrès
9th International Symposium on Signal, Image, Video and Communications (ISIVC), Nov 2018, Rabat, Morocco. Proceedings 9th International Symposium on Signal, Image, Video and Communications (ISIVC), 2018
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01893685
Contributeur : Bibliothèque Télécom Bretagne <>
Soumis le : jeudi 11 octobre 2018 - 16:08:41
Dernière modification le : mercredi 6 mars 2019 - 15:10:48
Document(s) archivé(s) le : samedi 12 janvier 2019 - 15:03:55

Fichier

PID5584289.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01893685, version 1

Citation

Van Khanh Mai, Dominique Pastor, Abdeldjalil Aissa El Bey. Joint Soft Threshold and Statistical Estimation for Speech Enhancement. 9th International Symposium on Signal, Image, Video and Communications (ISIVC), Nov 2018, Rabat, Morocco. Proceedings 9th International Symposium on Signal, Image, Video and Communications (ISIVC), 2018. 〈hal-01893685〉

Partager

Métriques

Consultations de la notice

40

Téléchargements de fichiers

31