Saved in:
Bibliographic Details
Main Authors: Zhou, Nan, Jiang, Youhai, Tan, Jialin, Qi, Chongmin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.03899
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916277645213696
author Zhou, Nan
Jiang, Youhai
Tan, Jialin
Qi, Chongmin
author_facet Zhou, Nan
Jiang, Youhai
Tan, Jialin
Qi, Chongmin
contents Low-complexity speech enhancement on mobile phones is crucial in the era of 5G. Thus, focusing on handheld mobile phone communication scenario, based on power level difference (PLD) algorithm and lightweight U-Net, we propose PLD-guided lightweight deep network (PLDNet), an extremely lightweight dual-microphone speech enhancement method that integrates the guidance of signal processing algorithm and lightweight attention-augmented U-Net. For the guidance information, we employ PLD algorithm to pre-process dual-microphone spectrum, and feed the output into subsequent deep neural network, which utilizes a lightweight U-Net with our proposed gated convolution augmented frequency attention (GCAFA) module to extract desired clean speech. Experimental results demonstrate that our proposed method achieves competitive performance with recent top-performing models while reducing computational cost by over 90%, highlighting the potential for low-complexity speech enhancement on mobile phones.
format Preprint
id arxiv_https___arxiv_org_abs_2406_03899
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PLDNet: PLD-Guided Lightweight Deep Network Boosted by Efficient Attention for Handheld Dual-Microphone Speech Enhancement
Zhou, Nan
Jiang, Youhai
Tan, Jialin
Qi, Chongmin
Audio and Speech Processing
Signal Processing
Low-complexity speech enhancement on mobile phones is crucial in the era of 5G. Thus, focusing on handheld mobile phone communication scenario, based on power level difference (PLD) algorithm and lightweight U-Net, we propose PLD-guided lightweight deep network (PLDNet), an extremely lightweight dual-microphone speech enhancement method that integrates the guidance of signal processing algorithm and lightweight attention-augmented U-Net. For the guidance information, we employ PLD algorithm to pre-process dual-microphone spectrum, and feed the output into subsequent deep neural network, which utilizes a lightweight U-Net with our proposed gated convolution augmented frequency attention (GCAFA) module to extract desired clean speech. Experimental results demonstrate that our proposed method achieves competitive performance with recent top-performing models while reducing computational cost by over 90%, highlighting the potential for low-complexity speech enhancement on mobile phones.
title PLDNet: PLD-Guided Lightweight Deep Network Boosted by Efficient Attention for Handheld Dual-Microphone Speech Enhancement
topic Audio and Speech Processing
Signal Processing
url https://arxiv.org/abs/2406.03899