Estimation of Speech Embedded in a Reverberant Environment with Multiple Sources of Noise - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2001

Estimation of Speech Embedded in a Reverberant Environment with Multiple Sources of Noise

Résumé

In this work we develop a system for enhancement of the speech signal with highest energy from a linear convolutive mixture of ☛ statistically independent sound sources recorded by ☞ microphones, where ☞✍✌✎☛. In this system we use the concept of independent component analysis (ICA) together with auditory filter banks, pitch tracking, adaptive band pass filters and masking. Computer simulations and real world experiments confirm the validity of the proposed algorithm.
Fichier non déposé

Dates et versions

hal-00802756 , version 1 (20-03-2013)

Identifiants

  • HAL Id : hal-00802756 , version 1

Citer

Barros Alan Kardec, Itakura Fumitada, Rutkowski Tomaz, Ali Mansour, Ohnishi Noboru. Estimation of Speech Embedded in a Reverberant Environment with Multiple Sources of Noise. International Conference on Speech and Signal Processing 2001, ICASSP 2001, May 2001, Salt Lake City, United States. ⟨hal-00802756⟩
115 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More