MUSE: Flexible Voiceprint Receptive Fields and Multi-Path Fusion Enhanced Taylor Transformer for U-Net-based Speech Enhancement

Autor:	Lin, Zizhen, Chen, Xiaoting, Wang, Junyu
Rok vydání:	2024
Předmět:	Computer Science - Sound Computer Science - Information Retrieval Computer Science - Information Theory Computer Science - Machine Learning Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	Achieving a balance between lightweight design and high performance remains a challenging task for speech enhancement. In this paper, we introduce Multi-path Enhanced Taylor (MET) Transformer based U-net for Speech Enhancement (MUSE), a lightweight speech enhancement network built upon the Unet architecture. Our approach incorporates a novel Multi-path Enhanced Taylor (MET) Transformer block, which integrates Deformable Embedding (DE) to enable flexible receptive fields for voiceprints. The MET Transformer is uniquely designed to fuse Channel and Spatial Attention (CSA) branches, facilitating channel information exchange and addressing spatial attention deficits within the Taylor-Transformer framework. Through extensive experiments conducted on the VoiceBank+DEMAND dataset, we demonstrate that MUSE achieves competitive performance while significantly reducing both training and deployment costs, boasting a mere 0.51M parameters. Comment: This paper was accepted by Interspeech 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2406.04589 Zobrazit plný text záznamu View this record from Arxiv