HIFI++: A Unified Framework for Bandwidth Extension and Speech Enhancement

Pavel Andreev, Aibek Alanov, Oleg V. Ivanov, Dmitry Vetrov

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 frame-work 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.
BibTeX
@inproceedings{andreev2023hifi,
  author = {Pavel Andreev and Aibek Alanov and Oleg V. Ivanov and Dmitry Vetrov},
  title = {{HIFI++: A Unified Framework for Bandwidth Extension and Speech Enhancement}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2023},
  url = {https://openreview.net/forum?id=kizL9PHivX},
}
Figure