HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Conference papers

On-Line Frame-Synchronous Compensation of Non-Stationary noise

Vincent Barreaud 1 Irina Illina 1 Dominique Fohr 1
1 PAROLE - Analysis, perception and recognition of speech
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : We present a frame-synchronous noise compensation algorithm that uses Stochastic Matching approach to cope with time-varying unknown noise. This method proposes to estimate simple mapping function in parallel with Viterbi alignment. The technique is entirely general since no assumption is made on the nature, level and variation of noise. Our algorithm is evaluated on the VODIS database recorded in a moving car. For various tasks, our technique outperforms significantly classical methods. For instance, using the affine transformation the proposed algorithm gives an error rate improvement of 13.3% compared to Parallel Model Combination (PMC), 15.5% on Spectral Subtraction (SS) and 27.8% on frame-synchronous Mean Cepstre Removal (MCR) for the numbers recognition task in real noise.
Keywords : parole stochastic matching speech compensation non-stationary hmm non-stationaire appariement stochastique
Document type :
Conference papers
Complete list of metadata
https://hal.inria.fr/inria-00099790
Contributor : Publications Loria Connect in order to contact the contributor
Submitted on : Tuesday, September 26, 2006 - 9:41:15 AM
Last modification on : Friday, February 26, 2021 - 3:28:06 PM

Identifiers

  • HAL Id : inria-00099790, version 1

Collections

INRIA | CNRS | INRIA2 | LORIA | UNIV-LORRAINE

Citation

Vincent Barreaud, Irina Illina, Dominique Fohr. On-Line Frame-Synchronous Compensation of Non-Stationary noise. The 2003 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP 2003, Apr 2003, Hong Kong, Chine, 4 p. ⟨inria-00099790⟩

Export

BibTeX TEI DC DCterms EndNote Datacite

Share

Metrics

Record views

72

 

Contact                    Legal Notice                    Personal Data