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

Dung Tran; Emmanuel Vincent; Denis Jouvet; Kamil Adiloglu

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

Dung Tran ¹ Emmanuel Vincent ¹ Denis Jouvet ¹ Kamil Adiloglu ²

1 PAROLE - Analysis, perception and recognition of speech

Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery

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.

Keywords : noise-robust speech recognition speech separation FASST

Document type :

Conference papers

Domain :

Computer Science [cs] / Signal and Image Processing

Engineering Sciences [physics] / Signal and Image processing

Complete list of metadatas

Cited literature [5 references] Display Hide Download

https://hal.inria.fr/hal-00801162
Contributor : Emmanuel Vincent <>
Submitted on : Friday, March 15, 2013 - 10:59:07 AM
Last modification on : Thursday, June 6, 2019 - 3:40:03 PM
Long-term archiving on : Monday, June 17, 2013 - 2:22:18 PM

tran_CHiME13.pdf

Files produced by the author(s)

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

File

Identifiers

Collections

Citation

Export

Metrics

618

417

Contact

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

File

Identifiers

Collections

Citation

Export

Share

Metrics

618

417

Contact