arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.07285eess.AScs.LGcs.SD
收藏

通过Vocos实现快速且灵活的音频带宽扩展

Fast and Flexible Audio Bandwidth Extension via Vocos

Independent Researcher(独立研究者)

Yatharth Sharma

AI总结:

本文提出了一种基于Vocos的音频带宽扩展模型,通过生成高频内容实现8-48kHz范围内的高质量音频增强,具备高吞吐量和实时处理能力。

摘要:

我们提出了一种基于Vocos的带宽扩展模型,通过生成缺失的高频内容来增强音频,频率范围为8-48 kHz。输入被重新采样到48 kHz,并通过神经语音编码器主干进行处理,使单个网络能够支持任意的上采样比例。一个轻量级的受Linkwitz-Riley启发的精炼器通过平滑的过渡将原始低频带与生成的高频内容合并。在验证过程中,该模型在NVIDIA A100 GPU上以0.0001的实时因子和8核CPU上以0.0053的实时因子运行,实现了在极高水平下的实用且高质量的带宽扩展。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑