Using full-rank spatial covariance models for noise-robust ASR - Archive ouverte HAL Access content directly
Conference Papers Year : 2013

Using full-rank spatial covariance models for noise-robust ASR

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

Abstract

We present a joint spatial and spectral denoising front-end for Track 1 of the 2nd CHiME Speech Separation and Recognition Challenge based on the Flexible Audio Source Separation Toolbox (FASST). We represent the sources by nonnegative matrix factorization (NMF) and full-rank spatial covariances, which are known to be appropriate for the modeling of small source movements. We then learn acoustic models for automatic speech recognition (ASR) on the enhanced training data. We obtain 40% average error rate reduction due to speech separation compared to multicondition training alone.
Fichier principal
Vignette du fichier
tran_CHiME13.pdf (42.02 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00801162 , version 1 (15-03-2013)

Identifiers

  • HAL Id : hal-00801162 , version 1

Cite

Dung T. Tran, Emmanuel Vincent, Denis Jouvet, Kamil Adiloglu. Using full-rank spatial covariance models for noise-robust ASR. CHiME - 2nd International Workshop on Machine Listening in Multisource Environments - 2013, Jun 2013, Vancouver, Canada. pp.31-32. ⟨hal-00801162⟩
255 View
311 Download

Share

Gmail Facebook Twitter LinkedIn More