English

RNNoise-Ex: Hybrid Speech Enhancement System based on RNN and Spectral Features

Sound 2021-05-26 v1 Machine Learning Audio and Speech Processing

Abstract

Recent interest in exploiting Deep Learning techniques for Noise Suppression, has led to the creation of Hybrid Denoising Systems that combine classic Signal Processing with Deep Learning. In this paper, we concentrated our efforts on extending the RNNoise denoising system (arXiv:1709.08243) with the inclusion of complementary features during the training phase. We present a comprehensive explanation of the set-up process of a modified system and present the comparative results derived from a performance evaluation analysis, using a reference version of RNNoise as control.

Keywords

Cite

@article{arxiv.2105.11813,
  title  = {RNNoise-Ex: Hybrid Speech Enhancement System based on RNN and Spectral Features},
  author = {Constantine C. Doumanidis and Christina Anagnostou and Evangelia-Sofia Arvaniti and Anthi Papadopoulou},
  journal= {arXiv preprint arXiv:2105.11813},
  year   = {2021}
}

Comments

6 pages, 5 figures, presented at ECESCON 12, for code see https://github.com/CedArctic/rnnoise-ex