A Neural Beamspace-Domain Filter for Real-Time Multi-Channel Speech Enhancement

Most deep-learning-based multi-channel speech enhancement methods focus on designing a set of beamforming coefficients, to directly filter the low signal-to-noise ratio signals received by microphones, which hinders the performance of these approaches. To handle these problems, this paper designs a...

Full description

Saved in:
Bibliographic Details
Published in:Symmetry (Basel) 2022-06, Vol.14 (6), p.1081
Main Authors: Liu, Wenzhe, Li, Andong, Wang, Xiao, Yuan, Minmin, Chen, Yi, Zheng, Chengshi, Li, Xiaodong
Format: Article
Language:English
Subjects:
Beamforming
Datasets
Deep learning
Design
Domain names
Interference
Microphones
multi-channel speech enhancement
neural beam filter
Neural networks
Signal processing
Signal to noise ratio
Spatial data
Speech
Speech processing
Speech recognition
Voice recognition
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most deep-learning-based multi-channel speech enhancement methods focus on designing a set of beamforming coefficients, to directly filter the low signal-to-noise ratio signals received by microphones, which hinders the performance of these approaches. To handle these problems, this paper designs a causal neural filter that fully exploits the spectro-temporal-spatial information in the beamspace domain. Specifically, multiple beams are designed to steer towards all directions, using a parameterized super-directive beamformer in the first stage. After that, a deep-learning-based filter is learned by, simultaneously, modeling the spectro-temporal-spatial discriminability of the speech and the interference, so as to extract the desired speech, coarsely, in the second stage. Finally, to further suppress the interference components, especially at low frequencies, a residual estimation module is adopted, to refine the output of the second stage. Experimental results demonstrate that the proposed approach outperforms many state-of-the-art (SOTA) multi-channel methods, on the generated multi-channel speech dataset based on the DNS-Challenge dataset.
ISSN:2073-8994
2073-8994
DOI:10.3390/sym14061081