Fast and Flexible Audio Bandwidth Extension via Vocos
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 5 of its 8 references that are in the map. First posted on arXiv 7 Mar 2026.
Builds on
5 of 8 references.
References · 5
- 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
- 2023Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesiscited by 150
- 2023AudioSR: Versatile Audio Super-resolution at Scalecited by 39
- 2022Neural Vocoder is All You Need for Speech Super-resolutioncited by 37
- 2024Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Predictioncited by 14
Built on by
Not cited yet.