Fast and Flexible Audio Bandwidth Extension via Vocos

Yatharth Sharma
3/7/2026
eess.AScs.LGcs.SD

No confident code implementation found for this paper.

Abstract

We propose a Vocos-based bandwidth extension model that enhances audio at 8-48 kHz by generating missing high-frequency content. Inputs are resampled to 48 kHz and processed by a neural vocoder backbone, enabling a single network to support arbitrary upsampling ratios. A lightweight Linkwitz-Riley-inspired refiner merges the original low band with the generated high frequencies via a smooth crossover. On validation, the model achieves competitive log-spectral distance while running at a real-time factor of 0.0001 on an NVIDIA A100 GPU and 0.0053 on an 8-core CPU, demonstrating practical, high-quality BWE at extreme throughput.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

83% match2 repos242023

Speech Bandwidth Expansion Via High Fidelity Generative Adversarial Networks

82% match2024

HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement

81% match1 repo1792022

High Fidelity Neural Audio Compression

78% match1 repo4.1k2022

High-Fidelity Audio Compression with Improved RVQGAN

78% match1 repo1.9k2023

NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates

78% match1 repo3142022

Cite this paper

@article{sharma2026fast,
  title  = {Fast and Flexible Audio Bandwidth Extension via Vocos},
  author = {Yatharth Sharma},
  year   = {2026},
  eprint = {2603.07285},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2603.07285v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2603.07285.svg)](https://codeofpaper.com/paper/2603.07285)

Discussion