Comparative Study between Adversarial Networks and Classical Techniques for Speech Enhancement
Audio and Speech Processing
2019-10-22 v1 Machine Learning
Abstract
Speech enhancement is a crucial task for several applications. Among the most explored techniques are the Wiener filter and the LogMMSE, but approaches exploring deep learning adapted to this task, such as SEGAN, have presented relevant results. This study compared the performance of the mentioned techniques in 85 noise conditions regarding quality, intelligibility, and distortion; and concluded that classical techniques continue to exhibit superior results for most scenarios, but, in severe noise scenarios, SEGAN performed better and with lower variance.
Cite
@article{arxiv.1910.09522,
title = {Comparative Study between Adversarial Networks and Classical Techniques for Speech Enhancement},
author = {Tito Spadini and Ricardo Suyama},
journal= {arXiv preprint arXiv:1910.09522},
year = {2019}
}