Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Fast and Flexible Audio Bandwidth Extension via Vocos

Yatharth Sharma

TL;DR

A Vocos-based bandwidth extension model that enhances audio at 8-48 kHz by generating missing high-frequency content by using a lightweight Linkwitz-Riley-inspired refiner and a neural vocoder backbone, demonstrating practical, high-quality BWE at extreme throughput.

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.

Fast and Flexible Audio Bandwidth Extension via Vocos

TL;DR

A Vocos-based bandwidth extension model that enhances audio at 8-48 kHz by generating missing high-frequency content by using a lightweight Linkwitz-Riley-inspired refiner and a neural vocoder backbone, demonstrating practical, high-quality BWE at extreme throughput.

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.
Paper Structure (19 sections, 4 equations, 2 figures, 5 tables)

This paper contains 19 sections, 4 equations, 2 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Proposed Method
  3. Problem formulation
  4. Model architecture
  5. Linkwitz-riley inspired frequency refiner
  6. Training objectives
  7. Experimental Setup
  8. Dataset
  9. Degradation process
  10. Baselines
  11. Evaluation metrics
  12. Results and Analysis
  13. Quality benchmarks
  14. Performance Analysis
  15. Robustness to Out-of-Domain Sample Rates
  16. ...and 4 more sections

Figures (2)

  • Figure 1: Overview of the proposed BWE architecture following the Vocos framework. The input audio is upsampled to 48 kHz via Sinc interpolation and transformed into an 80-bin Mel-spectrogram. The backbone consists of 8 ConvNeXt blocks using $7 \times 1$ depthwise and $1 \times 1$ pointwise convolutions. The head employs a linear layer and ISTFT for waveform reconstruction, followed by a Linkwitz-Riley inspired refiner for significant quality enhancement.
  • Figure 2: Model performance (LSD) across in-domain and out-of-domain (OOD) sample rates. The curve demonstrates a linear improvement in fidelity as input bandwidth increases, regardless of whether the rate was seen during training.