Work

Deep Learning Based Real-Time Speech Enhancement for Dual-Microphone Mobile Phones

Year: 2021

Type: article

Abstract: In mobile speech communication, speech signals can be severely corrupted by background noise when the far-end talker is in a noisy acoustic environment. To suppress background noise, speech enhancement systems are typically integrated into mobile phones, in which one or more microphones are deployed. In this study, we propose a novel deep learning based approach to real-time speech enhancement for dual-microphone mobile phones. The proposed approach employs a new densely-connected convolutional recurrent network to perform dual-channel complex spectral mapping. We utilize a structured pruning technique to compress the model without significantly degrading the enhancement performance, which yields a low-latency and memory-efficient enhancement system for real-time processing. Experimental results suggest that the proposed approach consistently outperforms an earlier approach to dual-channel speech enhancement for mobile phone communication, as well as a deep learning based beamformer.

Source: IEEE/ACM Transactions on Audio Speech and Language Processing

DOI: 10.1109/taslp.2021.3082318

Authors: Ke Tan, Xueliang Zhang, DeLiang Wang

Institutions: The Ohio State University, Inner Mongolia University

Language: English

Topic: Speech and Audio Processing

Subfield: Signal Processing

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Ohio Supercomputer Center, National Institute on Deafness and Other Communication Disorders

Award: Speech segregation to improve intelligility of reverberant-noisy speech