An Improved Signal Subspace Algorithm for Speech Enhancement

Abstract : Most of the algorithms for speech enhancement are designed to improve the speech listening comfort. However the frequency spectrum character is destroyed seriously after the speech enhancement. To achieve better speech listening comfort with less frequency spectral damages, we present an improved signal subspace algorithm for speech enhancement. Compared with the traditional signal space method, the improved algorithm can decrease the Mel-frequency Cepstral Coefficients (MFCC) distance, an evaluation measure which means less frequency spectral damages to the voice and keep the voices’ intelligence at the same time. Besides, the method can enlarge the distance of the easily confused voices, which means the improvement of the voice recognition ratio. Thus we get the purpose of the speech enhancement. The improved algorithm is used in a speech recognition program and has a good performance.
Type de document :
Communication dans un congrès
Hongxiu Li; Matti Mäntymäki; Xianfeng Zhang. 13th Conference on e-Business, e-Services and e-Society (I3E), Nov 2014, Sanya, China. Springer, IFIP Advances in Information and Communication Technology, AICT-445, pp.104-114, 2014, Digital Services and Information Intelligence. 〈10.1007/978-3-662-45526-5_10〉
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01342134
Contributeur : Hal Ifip <>
Soumis le : mardi 5 juillet 2016 - 14:38:19
Dernière modification le : dimanche 17 décembre 2017 - 09:50:02

Fichier

978-3-662-45526-5_10_Chapter.p...
Fichiers produits par l'(les) auteur(s)

Licence


Distributed under a Creative Commons Paternité 4.0 International License

Identifiants

Citation

Xuzheng Dai, Baoxian Yu, Xianhua Dai. An Improved Signal Subspace Algorithm for Speech Enhancement. Hongxiu Li; Matti Mäntymäki; Xianfeng Zhang. 13th Conference on e-Business, e-Services and e-Society (I3E), Nov 2014, Sanya, China. Springer, IFIP Advances in Information and Communication Technology, AICT-445, pp.104-114, 2014, Digital Services and Information Intelligence. 〈10.1007/978-3-662-45526-5_10〉. 〈hal-01342134〉

Partager

Métriques

Consultations de la notice

47

Téléchargements de fichiers

34