Title: Comparative Study between Adversarial Networks and Classical Techniques for Speech Enhancement
Authors: Tito Caco Curimbaba Spadini, Ricardo Suyama
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.
Key-words: generative adversarial network; speech enhancement; denoising; Wiener filter; log-mmse
DOI code: 10.21528/CBIC2019-99
PDF file: CBIC2019-99.pdf
BibTeX file: CBIC2019-99.bib