Rank-1 Constrained Multichannel Wiener Filter for Speech Recognition in Noisy Environments - Archive ouverte HAL Access content directly
Journal Articles Computer Speech and Language Year : 2018

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

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

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.
Fichier principal
Vignette du fichier
wang_CSL17.pdf (903.86 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01634449 , version 1 (14-11-2017)

Identifiers

Cite

Ziteng Wang, Emmanuel Vincent, Romain Serizel, Yonghong Yan. Rank-1 Constrained Multichannel Wiener Filter for Speech Recognition in Noisy Environments. Computer Speech and Language, 2018, 49, pp.37-51. ⟨10.1016/j.csl.2017.11.003⟩. ⟨hal-01634449⟩
415 View
735 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More