English

Inplace Gated Convolutional Recurrent Neural Network For Dual-channel Speech Enhancement

Audio and Speech Processing 2021-07-27 v1

Abstract

For dual-channel speech enhancement, it is a promising idea to design an end-to-end model based on the traditional array signal processing guideline and the manifold space of multi-channel signals. We found that the idea above can be effectively implemented by the classical convolutional recurrent neural networks (CRN) architecture. We propose a very compact in place gated convolutional recurrent neural network (inplace GCRN) for end-to-end multi-channel speech enhancement, which utilizes inplace-convolution for frequency pattern extraction and reconstruction. The inplace characteristics efficiently preserve spatial cues in each frequency bin for channel-wise long short-term memory neural networks (LSTM) tracing the spatial source. In addition, we come up with a new spectrum recovery method by predict amplitude mask, mapping, and phase, which effectively improves the speech quality.

Keywords

Cite

@article{arxiv.2107.11968,
  title  = {Inplace Gated Convolutional Recurrent Neural Network For Dual-channel Speech Enhancement},
  author = {Jinjiang Liu and Xueliang Zhang},
  journal= {arXiv preprint arXiv:2107.11968},
  year   = {2021}
}

Comments

Accepted by INTERSPEECH2021