Page
%P
-
Chapter and Conference Paper
Simultaneous Progressive Filtering-Based Monaural Speech Enhancement
Speech enhancement (SE) benefits from multi-stage stacking. However, this will introduce a lot of new parameters to the neural network. In this paper, we propose a simultaneous progressive filtering-based mona...
-
Chapter and Conference Paper
Speech Dereverberation Based on Scale-Aware Mean Square Error Loss
Recently, deep learning-based speech dereverberation appro-aches have achieved remarkable performance by directly map** the input spectrogram to a target spectrogram or time-frequency mask. However, these ap...