arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2203.13086cs.SDcs.LGeess.AS

HiFi++:用于带宽扩展和语音增强的统一框架

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

Samsung Research(三星研究院);Higher School of Economics(高等经济大学);Skolkovo Institute of Science and Technology(斯科尔科沃科学技术研究院);Artificial Intelligence Research Institute(人工智能研究院)

Pavel Andreev, Aibek Alanov, Oleg Ivanov, Dmitry Vetrov

AI总结:

本文提出基于 HiFi 声码器并改进生成器架构的统一框架 HiFi++,在带宽扩展和语音增强任务上以更少算力达到优于或可比肩 SOTA 的性能。

摘要:

生成对抗网络最近在神经声码编码方面表现出卓越性能,优于最佳的自回归模型和基于流的模型。本文表明,这一成功可以扩展到条件音频生成的其他任务。具体而言,在 HiFi 声码器的基础上,我们提出了用于带宽扩展和语音增强的新型 HiFi++ 通用框架。结果表明,借助改进的生成器架构,HiFi++ 在这些任务上的表现优于或可比肩当前最先进水平,同时消耗的计算资源显著更少。我们通过一系列广泛实验验证了该方法的有效性。

英文摘要:

Generative adversarial networks have recently demonstrated outstanding performance in neural vocoding outperforming best autoregressive and flow-based models. In this paper, we show that this success can be extended to other tasks of conditional audio generation. In particular, building upon HiFi vocoders, we propose a novel HiFi++ general framework for bandwidth extension and speech enhancement. We show that with the improved generator architecture, HiFi++ performs better or comparably with the state-of-the-art in these tasks while spending significantly less computational resources. The effectiveness of our approach is validated through a series of extensive experiments.

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。

↑