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

Code

• github.com/andreevp/wvmos
  OfficialIn paperpytorch★ 176
• github.com/rishikksh20/HiFiplusplus-pytorch
  pytorch★ 159
• github.com/MS-P3/code4/tree/main/HiFI
  mindspore★ 0

Abstract

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.

Tasks

Reproductions