FlowSE: Efficient and High-Quality Speech Enhancement via Flow Matching

TL;DR

FlowSE introduces a flow-matching approach for speech enhancement that reduces inference latency and improves quality, effectively handling noisy speech with or without textual information.

Contribution

This paper presents FlowSE, a novel flow-matching model for speech enhancement that outperforms existing generative methods and simplifies the transformation process.

Findings

FlowSE achieves higher speech quality than state-of-the-art methods.

FlowSE operates efficiently with reduced inference latency.

FlowSE performs well with or without textual transcripts.

Abstract

Generative models have excelled in audio tasks using approaches such as language models, diffusion, and flow matching. However, existing generative approaches for speech enhancement (SE) face notable challenges: language model-based methods suffer from quantization loss, leading to compromised speaker similarity and intelligibility, while diffusion models require complex training and high inference latency. To address these challenges, we propose FlowSE, a flow-matching-based model for SE. Flow matching learns a continuous transformation between noisy and clean speech distributions in a single pass, significantly reducing inference latency while maintaining high-quality reconstruction. Specifically, FlowSE trains on noisy mel spectrograms and optional character sequences, optimizing a conditional flow matching loss with ground-truth mel spectrograms as supervision. It implicitly learns speech's temporal-spectral structure and text-speech alignment. During inference, FlowSE can operate with or without textual information, achieving impressive results in both scenarios, with further improvements when transcripts are available. Extensive experiments demonstrate that FlowSE significantly outperforms state-of-the-art generative methods, establishing a new paradigm for generative-based SE and demonstrating the potential of flow matching to advance the field. Our code, pre-trained checkpoints, and audio samples are available.