A Modulation-Domain Loss for Neural-Network-Based Real-Time Speech Enhancement

Tyler Vuong; Yangyang Xia; Richard M. Stern

ICASSP 2021accepted0 citations

A Modulation-Domain Loss for Neural-Network-Based Real-Time Speech Enhancement

Tyler Vuong, Yangyang Xia, Richard M. Stern

Abstract

We describe a modulation-domain loss function for deep-learning-based speech enhancement systems. Learnable spectro-temporal receptive fields (STRFs) were adapted to optimize for a speaker identification task. The learned STRFs were then used to calculate a weighted mean-squared error (MSE) in the modulation domain for training a speech enhancement system. Experiments showed that adding the modulation-domain MSE to the MSE in the spectro-temporal domain substantially improved the objective prediction of speech quality and intelligibility for real-time speech enhancement systems without incurring additional computation during inference.

BibTeX

@inproceedings{icassp2021_amodulationdomai,
  title = {A Modulation-Domain Loss for Neural-Network-Based Real-Time Speech Enhancement},
  author = {Tyler Vuong and Yangyang Xia and Richard M. Stern},
  booktitle = {ICASSP 2021},
  year = {2021}
}