A Modulation-Domain Loss for Neural-Network-based Real-time Speech Enhancement
Audio and Speech Processing
2021-02-16 v1
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.
Cite
@article{arxiv.2102.07330,
title = {A Modulation-Domain Loss for Neural-Network-based Real-time Speech Enhancement},
author = {Tyler Vuong and Yangyang Xia and Richard M. Stern},
journal= {arXiv preprint arXiv:2102.07330},
year = {2021}
}
Comments
Accepted IEEE ICASSP 2021