FLowHigh: Towards Efficient and High-Quality Audio Super-Resolution with Single Step Flow Matching

Audio super-resolution is challenging owing to its ill-posed nature. Recently, the application of diffusion models in audio super-resolution has shown promising results in alleviating this challenge. However, diffusion-based models have limitations, primarily the necessity for numerous sampling steps, which causes significantly increased latency when synthesizing high-quality audio samples. In this paper, we propose FLowHigh, a novel approach that integrates flow matching, a highly efficient generative model, into audio super-resolution. We also explore probability paths specially tailored for audio super-resolution, which effectively capture high-resolution audio distributions, thereby enhancing reconstruction quality. The proposed method generates high-fidelity, high-resolution audio through a single-step sampling process across various input sampling rates. The experimental results on the VCTK benchmark dataset demonstrate that FLowHigh achieves state-of-the-art performance in audio super-resolution, as evaluated by log-spectral distance and ViSQOL while maintaining computationally efficiency with only a single-step sampling process.

Official implementation of FLowHigh: https://github.com/jjunak-yun/FLowHigh_code

FLowHigh was trained and evaluated on the VCTK dataset.

We compared FLowHigh with several audio super-resolution models as:

1. NU-Wave2 [Code][Demo page]

2. UDM+ [Code][Demo page]

3. mdctGAN [Code]

4. Fre-Painter [Code][Demo page]