Extension of uncertainty propagation to dynamic MFCCs for noise robust ASR - Archive ouverte HAL Access content directly
Conference Papers Year : 2014

Extension of uncertainty propagation to dynamic MFCCs for noise robust ASR

(1) , (2) , (2)
1
2

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.
Fichier principal
Vignette du fichier
Icassp2014_extension.pdf (92.93 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00954654 , version 1 (03-03-2014)
hal-00954654 , version 2 (11-03-2014)

Identifiers

  • HAL Id : hal-00954654 , version 2

Cite

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. ⟨hal-00954654v2⟩
479 View
367 Download

Share

Gmail Facebook Twitter LinkedIn More