Binaural speech enhancement using complex convolutional recurrent networks
Author(s)
Type
Conference Paper
Abstract
From hearing aids to augmented and virtual reality devices, binau-ral speech enhancement algorithms have been established as state-of-the-art techniques to improve speech intelligibility and listening comfort. In this paper, we present an end-to-end binaural speech enhancement method using a complex recurrent convolutional net-work with an encoder-decoder architecture and a complex LSTM recurrent block placed between the encoder and decoder. A loss function that focuses on the preservation of spatial information in addition to speech intelligibility improvement and noise reduction is introduced. The network estimates individual complex ratio masks for the left and right-ear channels of a binaural hearing device in the time-frequency domain. We show that, compared to other baseline algorithms, the proposed method significantly improves the estimated speech intelligibility and reduces the noise while preserving the spatial information of the binaural signals in acoustic situations with a single target speaker and isotropic noise of various types.
Date Issued
2024-04-01
Date Acceptance
2023-10-01
Citation
2023 57th Asilomar Conference on Signals, Systems, and Computers, 2024, pp.1130-1134
Publisher
IEEE
Start Page
1130
End Page
1134
Journal / Book Title
2023 57th Asilomar Conference on Signals, Systems, and Computers
Copyright Statement
Copyright © 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Identifier
http://dx.doi.org/10.1109/ieeeconf59524.2023.10476738
Source
2023 57th Asilomar Conference on Signals, Systems, and Computers
Publication Status
Published
Start Date
2023-10-29
Finish Date
2023-11-01
Coverage Spatial
Pacific Grove, CA, USA