Abstract : Uncertainty propagation has been successfully employed for speech recognition in nonstationary noise environments. The uncertainty about the features is typically represented as a diagonal covariance matrix for static features only. We present a framework for estimating the uncertainty over both static and dynamic features as a full covariance matrix. The estimated covariance matrix is then multiplied by scaling coefficients optimized on development data. We achieve 21\% relative error rate reduction on the 2nd CHiME Challenge with respect to conventional decoding without uncertainty, that is five times more than the reduction achieved with diagonal uncertainty covariance for static features only.
Type de document :
Communication dans un congrès
2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2014, Florence, Italy. 2014
https://hal.inria.fr/hal-00954654
Contributeur : Dung Tran
<>
Soumis le : mardi 11 mars 2014 - 15:55:32
Dernière modification le : jeudi 21 mars 2019 - 14:20:12
Document(s) archivé(s) le : mercredi 11 juin 2014 - 12:51:23
Dung Tien Tran, Emmanuel Vincent, Denis Jouvet. Extension of uncertainty propagation to dynamic MFCCs for noise robust ASR. 2014 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2014, Florence, Italy. 2014. 〈hal-00954654v2〉
