Rank-1 Constrained Multichannel Wiener Filter for Speech Recognition in Noisy Environments

Ziteng Wang 1 Emmanuel Vincent 2 Romain Serizel 2 Yonghong Yan 1
2 MULTISPEECH - Speech Modeling for Facilitating Oral-Based Communication
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : Multichannel linear filters, such as the Multichannel Wiener Filter (MWF) and the Generalized Eigenvalue (GEV) beamformer are popular signal processing techniques which can improve speech recognition performance. In this paper, we present an experimental study on these linear filters in a specific speech recognition task, namely the CHiME-4 challenge, which features real recordings in multiple noisy environments. Specifically, the rank-1 MWF is employed for noise reduction and a new constant residual noise power constraint is derived which enhances the recognition performance. To fulfill the underlying rank-1 assumption , the speech covariance matrix is reconstructed based on eigenvectors or generalized eigenvectors. Then the rank-1 constrained MWF is evaluated with alternative multichannel linear filters under the same framework, which involves a Bidirectional Long Short-Term Memory (BLSTM) network for mask estimation. The proposed filter outperforms alternative ones, leading to a 40% relative Word Error Rate (WER) reduction compared with the baseline Weighted Delay and Sum (WDAS) beamformer on the real test set, and a 15% relative WER reduction compared with the GEV-BAN method. The results also suggest that the speech recognition accuracy correlates more with the Mel-frequency cep-stral coefficients (MFCC) feature variance than with the noise reduction or the speech distortion level.
Type de document :
Article dans une revue
Computer Speech and Language, Elsevier, A Paraître
Liste complète des métadonnées

Littérature citée [38 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01634449
Contributeur : Emmanuel Vincent <>
Soumis le : mardi 14 novembre 2017 - 10:20:30
Dernière modification le : jeudi 11 janvier 2018 - 06:27:31

Fichier

wang_CSL17.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01634449, version 1

Citation

Ziteng Wang, Emmanuel Vincent, Romain Serizel, Yonghong Yan. Rank-1 Constrained Multichannel Wiener Filter for Speech Recognition in Noisy Environments. Computer Speech and Language, Elsevier, A Paraître. 〈hal-01634449〉

Partager

Métriques

Consultations de la notice

35

Téléchargements de fichiers

26