Speech Enhancement with Mixture of Deep Experts with Clean Clustering Pre-Training

Shlomo E. Chazan; Jacob Goldberger; Sharon Gannot

ICASSP 2021accepted0 citations

Speech Enhancement with Mixture of Deep Experts with Clean Clustering Pre-Training

Shlomo E. Chazan, Jacob Goldberger, Sharon Gannot

Abstract

In this study we present a mixture of deep experts (MoDE) neural-network architecture for single microphone speech enhancement. Our architecture comprises a set of deep neural networks (DNNs), each of which is an ‘expert’ in a different speech spectral pattern such as phoneme. A gating DNN is responsible for the latent variables which are the weights assigned to each expert’s output given a speech segment. The experts estimate a mask from the noisy input and the final mask is then obtained as a weighted average of the experts’ estimates, with the weights determined by the gating DNN. A soft spectral attenuation, based on the estimated mask, is then applied to enhance the noisy speech signal. As a byproduct, we gain reduction at the complexity in test time. We show that the experts specialization allows better robustness to unfamiliar noise types. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

BibTeX

@inproceedings{icassp2021_speechenhancemen,
  title = {Speech Enhancement with Mixture of Deep Experts with Clean Clustering Pre-Training},
  author = {Shlomo E. Chazan and Jacob Goldberger and Sharon Gannot},
  booktitle = {ICASSP 2021},
  year = {2021}
}