@inproceedings{mirsamadi2016a,
author = {Mirsamadi, Seyedmahdad and Tashev, Ivan},
title = {A Causal Speech Enhancement Approach Combining Data-driven Learning and Suppression Rule Estimation},
booktitle = {Proc. InterSpeech 2016},
year = {2016},
month = {May},
abstract = {The problem of single-channel speech enhancement has been traditionally addressed by using statistical signal processing algorithms that are designed to suppress time-frequency regions affected by noise. We study an alternative data-driven approach which uses deep neural networks (DNNs) to learn the transformation from noisy and reverberant speech to clean speech, with a focus on real-time applications which require low-latency causal processing. We examine several structures in which deep learning can be used within an enhancement system. These include end-to-end DNN regression from noisy to clean spectra, as well as less intervening approaches which estimate a suppression gain for each time-frequency bin instead of directly recovering the clean spectral features. We also propose a novel architecture in which the general structure of a conventional noise suppressor is preserved, but the sub-tasks are independently learned and carried out by separate networks. It is shown that DNN-based suppression gain estimation outperforms the regression approach in the causal processing mode and for noise types that are not seen during DNN training.},
url = {http://approjects.co.za/?big=en-us/research/publication/causal-speech-enhancement-approach-combining-data-driven-learning-suppression-rule-estimation/},
}