Title: | DISCRIMINATIVE DEEP RECURRENT NEURAL NETWORKS FOR MONAURAL SPEECH SEPARATION |
Authors: | Wang, Guan-Xiang Hsu, Chung-Chien Chien, Jen-Tzung 電機工程學系 Department of Electrical and Computer Engineering |
Keywords: | deep learning;discriminative learning;neural network;monaural speech separation |
Issue Date: | 2016 |
Abstract: | Deep neural network is now a new trend towards solving different problems in speech processing. In this paper, we propose a discriminative deep recurrent neural network (DRNN) model for monaural speech separation. Our idea is to construct DRNN as a regression model to discover the deep structure and regularity for signal reconstruction from a mixture of two source spectra. To reinforce the discrimination capability between two separated spectra, we estimate DRNN separation parameters by minimizing an integrated objective function which consists of two measurements. One is the within source reconstruction errors due to the individual source spectra while the other conveys the discrimination information which preserves the mutual difference between two source spectra during the supervised training procedure. This discrimination information acts as a kind of regularization so as to maintain between-source separation in monaural source separation. In the experiments, we demonstrate the effectiveness of the proposed method for speech separation compared with the other methods. |
URI: | http://hdl.handle.net/11536/136363 |
ISBN: | 978-1-4799-9988-0 |
ISSN: | 1520-6149 |
Journal: | 2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS |
Begin Page: | 2544 |
End Page: | 2548 |
Appears in Collections: | Conferences Paper |