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

TL;DR

This paper presents MUSE, a lightweight speech enhancement model using a novel MET Transformer with flexible receptive fields and multi-path fusion, achieving high performance with minimal parameters.

Contribution

Introduces a Multi-path Enhanced Taylor Transformer with Deformable Embedding and attention fusion for efficient speech enhancement within a U-net architecture.

Findings

Achieves competitive speech enhancement performance

Reduces model size to 0.51M parameters

Demonstrates lower training and deployment costs

Abstract

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.