LatentFlowSR: High-Fidelity Audio Super-Resolution via Noise-Robust Latent Flow Matching

TL;DR

LatentFlowSR introduces a novel latent space approach for high-fidelity audio super-resolution, leveraging conditional flow matching and a noise-robust autoencoder to enhance reconstruction quality across diverse audio types.

Contribution

The paper proposes a new latent-space super-resolution method using conditional flow matching and a noise-robust autoencoder, improving performance on complex audio beyond speech.

Findings

Outperforms baseline methods on various audio types and settings.

Demonstrates strong high-frequency reconstruction and generalization.

Utilizes a one-step ODE solver for efficient latent space generation.

Abstract

Audio super-resolution aims to recover missing high-frequency details from bandwidth-limited low-resolution audio, thereby improving the naturalness and perceptual quality of the reconstructed signal. However, most existing methods directly operate in the waveform or time-frequency domain, which not only involves high-dimensional generation spaces but is also largely limited to speech tasks, leaving substantial room for improvement on more complex audio types such as sound effects and music. To mitigate these limitations, we introduce LatentFlowSR, a new audio super-resolution approach that leverages conditional flow matching (CFM) within a latent representation space. Specifically, we first train a noise-robust autoencoder, which encodes low-resolution audio into a continuous latent space. Conditioned on the low-resolution latent representation, a CFM mechanism progressively generates the corresponding high-resolution latent representation from a Gaussian prior with a one-step ordinary differential equation (ODE) solver. The resulting high-resolution latent representation is then decoded by the pretrained autoencoder to reconstruct the high-resolution audio. Experimental results demonstrate that LatentFlowSR consistently outperforms baseline methods across various audio types and super-resolution settings. These results indicate that the proposed method possesses strong high-frequency reconstruction capability and robust generalization performance, providing compelling evidence for the effectiveness of latent-space modeling in audio super-resolution. All relevant code will be made publicly available upon completion of the paper review process.