Exploiting models intrinsic robustness for noisy speech recognition

Christophe Cerisara; Dominique Fohr; Odile Mella; Irina Illina

Exploiting models intrinsic robustness for noisy speech recognition

Christophe Cerisara ¹ Dominique Fohr ¹ Odile Mella ¹ Irina Illina ¹

1 PAROLE - Analysis, perception and recognition of speech

INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications

Abstract : We propose in this paper an original approach to build masks in the framework of missing data recognition. The proposed soft masks are estimated from the models themselves, and not from the test signal as it is usually the case. They represent the intrinsic robustness of model's log-spectral coefficients. The method is validated with cepstral models, on two synthetic and two real-life noises, at different signal-to-noise ratios. We further discuss how such masks can be combined with other signal-based masks and noise compensation techniques.

Mots-clés : reconnaissance de la parole missing data speech recognition robustness robustesse données manquantes

Document type :

Conference papers

Domain :

Computer Science [cs] / Other [cs.OH]

Complete list of metadatas

Cited literature [10 references] Display Hide Download

https://hal.inria.fr/inria-00099890
Contributor : Publications Loria <>
Submitted on : Tuesday, September 26, 2006 - 10:03:33 AM
Last modification on : Tuesday, September 24, 2019 - 4:00:13 PM
Long-term archiving on : Wednesday, March 29, 2017 - 12:53:10 PM

Exploiting models intrinsic robustness for noisy speech recognition

Files

Identifiers

Collections

Citation

Export

Metrics

207

60

Contact

Exploiting models intrinsic robustness for noisy speech recognition

Files

Identifiers

Collections

Citation

Export

Share

Metrics

207

60

Contact