FlowAVSE: Efficient Audio-Visual Speech Enhancement with Conditional Flow Matching

TL;DR

FlowAVSE introduces a fast, efficient audio-visual speech enhancement method using conditional flow matching, significantly improving inference speed and reducing model size without sacrificing quality.

Contribution

It presents a novel conditional flow matching approach that enables high-quality speech generation in a single step, optimizing the U-net architecture for efficiency.

Findings

22 times faster inference speed

Model size reduced by half

Maintains high output quality

Abstract

This work proposes an efficient method to enhance the quality of corrupted speech signals by leveraging both acoustic and visual cues. While existing diffusion-based approaches have demonstrated remarkable quality, their applicability is limited by slow inference speeds and computational complexity. To address this issue, we present FlowAVSE which enhances the inference speed and reduces the number of learnable parameters without degrading the output quality. In particular, we employ a conditional flow matching algorithm that enables the generation of high-quality speech in a single sampling step. Moreover, we increase efficiency by optimizing the underlying U-net architecture of diffusion-based systems. Our experiments demonstrate that FlowAVSE achieves 22 times faster inference speed and reduces the model size by half while maintaining the output quality. The demo page is available at: https://cyongong.github.io/FlowAVSE.github.io/