论文标题
HIFI ++：带宽扩展和语音增强的统一框架
HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement
论文作者
论文摘要
生成的对抗网络最近在神经声音中表现出卓越的表现，表现优于最佳自回归和基于流动的模型。在本文中，我们表明，这种成功可以扩展到有条件音频的其他任务。特别是，在HIFI Vocoders的基础上，我们提出了一个新型的HIFI ++带宽扩展和语音增强的通用框架。我们表明，通过改进的生成器体系结构，HIFI ++在这些任务中的最先进的过程中的性能更好或相当，而计算资源的支出则大大减少了。通过一系列广泛的实验，我们的方法的有效性得到了验证。
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.
