# Fast and Flexible Audio Bandwidth Extension via Vocos Source: [Fast and Flexible Audio Bandwidth Extension via Vocos]() Collection index: [llms.txt]() Data updated: 2026-03-11T05:00:04.181Z Authors: Yatharth Sharma Published: 2026-03-07T17:12:08.000Z ## 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Audio Bandwidth Extension (12→48 kHz) on VCTK (test)](): Audio Bandwidth Extension (12→48 kHz); VCTK (test); LSD: 0.8. - [Audio Bandwidth Extension (8→48 kHz) on VCTK (test)](): Audio Bandwidth Extension (8→48 kHz); VCTK (test); LSD: 0.85. - [Audio Bandwidth Extension (16→48 kHz) on VCTK (test)](): Audio Bandwidth Extension (16→48 kHz); VCTK (test); LSD: 0.74. ## Original sources and implementation [Original paper]() [PDF]()