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

07/01/2017
by   Ziteng Wang, et al.
0

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 reduction compared with the GEV-BAN method. The results also suggest that the speech recognition accuracy correlates more with the Mel-frequency cepstral coefficients (MFCC) feature variance than with the noise reduction or the speech distortion level.

READ FULL TEXT
research
09/21/2015

Noise Robust IOA/CAS Speech Separation and Recognition System For The Third 'CHIME' Challenge

This paper presents the contribution to the third 'CHiME' speech separat...
research
03/27/2018

Building state-of-the-art distant speech recognition using the CHiME-4 challenge with a setup of speech enhancement baseline

This paper describes a new baseline system for automatic speech recognit...
research
10/23/2019

Low-frequency compensated synthetic impulse responses for improved far-field speech recognition

We propose a method for generating low-frequency compensated synthetic i...
research
02/24/2021

Thoughts on the potential to compensate a hearing loss in noise

The effect of hearing impairment on speech perception was described by P...
research
06/14/2019

Cumulative Adaptation for BLSTM Acoustic Models

This paper addresses the robust speech recognition problem as an adaptat...
research
04/02/2022

Leveraging Phone Mask Training for Phonetic-Reduction-Robust E2E Uyghur Speech Recognition

In Uyghur speech, consonant and vowel reduction are often encountered, e...
research
07/14/2015

Feature Normalisation for Robust Speech Recognition

Speech recognition system performance degrades in noisy environments. If...

Please sign up or login with your details

Forgot password? Click here to reset