Skip to Main content Skip to Navigation
Conference papers

Audio source separation with one sensor for robust speech recognition

Laurent Benaroya 1 Frédéric Bimbot 1 Guillaume Gravier 1 Rémi Gribonval 1 
1 METISS - Speech and sound data modeling and processing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : In this paper, we address the problem of noise compensation in speech signals for robust speech recognition. Several classical denoising methods in the field of speech and signal processing are compared on speech corrupted by music, which correspond to a frequent situation in broadcast news transcription tasks. We also present two new source separation techniques, namely adaptive Wiener filtering and adaptive shrinkage. These techniques rely on the use of a dictionary of spectral shapes to deal with the non stationarity of the signals. The algorithms are first compared on the source separation task and assessed in terms of average distortion. Their effect on the entire transcription system is eventually compared in terms of word error rate. Results show that the proposed adaptive Wiener filter approach yields a significant improvement of the transcription accuracy at signal/noise ratios greater than 15 dB.
Complete list of metadata

Cited literature [10 references]  Display  Hide  Download
Contributor : Rémi Gribonval Connect in order to contact the contributor
Submitted on : Sunday, March 13, 2011 - 4:34:08 PM
Last modification on : Friday, February 4, 2022 - 3:16:28 AM
Long-term archiving on: : Tuesday, June 14, 2011 - 2:31:21 AM


Files produced by the author(s)


  • HAL Id : inria-00576210, version 1


Laurent Benaroya, Frédéric Bimbot, Guillaume Gravier, Rémi Gribonval. Audio source separation with one sensor for robust speech recognition. ISCA Tutorial and Research Workshop on Non-Linear Speech Processing (NOLISP), IRISA, May 2003, Le Croisic, France. ⟨inria-00576210⟩



Record views


Files downloads