| HAL-Inria | Publications, software ... of Inria's scientists |
Conference papers
Using full-rank spatial covariance models for noise-robust ASR
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.
Cited literature [5 references]
https://hal.inria.fr/hal-00801162
Contributor : Emmanuel Vincent <>
Submitted on : Friday, March 15, 2013 - 10:59:07 AM
Last modification on : Monday, May 4, 2020 - 11:39:00 AM
Document(s) archivé(s) le : Monday, June 17, 2013 - 2:22:18 PM
Contributor : Emmanuel Vincent <>
Submitted on : Friday, March 15, 2013 - 10:59:07 AM
Last modification on : Monday, May 4, 2020 - 11:39:00 AM
Document(s) archivé(s) le : Monday, June 17, 2013 - 2:22:18 PM
File
tran_CHiME13.pdf
Files produced by the author(s)