Geometry Constrained Progressive Learning for Lstm-Based Speech Enhancement
Xin Tang, Jun Du, Li Chai, Yannan Wang, Qing Wang, Chin-Hui Lee
Abstract
In our previous work, a progressive learning framework for long short-term memory (LSTM)-based speech enhancement was proposed to improve the performance in low SNR environment, where each LSTM layer is guided to learn an intermediate target with a specific SNR gain via the MMSE criterion. However, the constraint relationship among these targets is not considered in the objective function. In this paper, we incorporate two kinds of geometric constraints among these targets into the objective function to help LSTM achieve better training. One constraint is edge constraint and the other is the centroid constraint. In addition, we propose a method for constructing the intermediate targets online. It saves device storage space and alleviates the trouble of manually constructing intermediate targets. Experiment results demonstrate these geometric constraints can bring remarkable improvements in low SNR environments.
BibTeX
@inproceedings{icassp2020_geometryconstrai,
title = {Geometry Constrained Progressive Learning for Lstm-Based Speech Enhancement},
author = {Xin Tang and Jun Du and Li Chai and Yannan Wang and Qing Wang and Chin-Hui Lee},
booktitle = {ICASSP 2020},
year = {2020}
}