8th International Conference on Spoken Language Processing

Jeju Island, Korea
October 4-8, 2004

Exploiting Models Intrinsic Robustness for Noisy Speech Recognition

Christophe Cerisara, Dominique Fohr, Odile Mella, Irina Illina

LORIA, France

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.

Full Paper

Bibliographic reference.  Cerisara, Christophe / Fohr, Dominique / Mella, Odile / Illina, Irina (2004): "Exploiting models intrinsic robustness for noisy speech recognition", In INTERSPEECH-2004, 2101-2104.