English

Invertible DNN-based nonlinear time-frequency transform for speech enhancement

Audio and Speech Processing 2020-02-17 v2 Sound

Abstract

We propose an end-to-end speech enhancement method with trainable time-frequency~(T-F) transform based on invertible deep neural network~(DNN). The resent development of speech enhancement is brought by using DNN. The ordinary DNN-based speech enhancement employs T-F transform, typically the short-time Fourier transform~(STFT), and estimates a T-F mask using DNN. On the other hand, some methods have considered end-to-end networks which directly estimate the enhanced signals without T-F transform. While end-to-end methods have shown promising results, they are black boxes and hard to understand. Therefore, some end-to-end methods used a DNN to learn the linear T-F transform which is much easier to understand. However, the learned transform may not have a property important for ordinary signal processing. In this paper, as the important property of the T-F transform, perfect reconstruction is considered. An invertible nonlinear T-F transform is constructed by DNNs and learned from data so that the obtained transform is perfectly reconstructing filterbank.

Keywords

Cite

@article{arxiv.1911.10764,
  title  = {Invertible DNN-based nonlinear time-frequency transform for speech enhancement},
  author = {Daiki Takeuchi and Kohei Yatabe and Yuma Koizumi and Yasuhiro Oikawa and Noboru Harada},
  journal= {arXiv preprint arXiv:1911.10764},
  year   = {2020}
}

Comments

To appear in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2020)

R2 v1 2026-06-23T12:26:00.873Z