Release Time:2019-03-12  Hits:

Indexed by: Conference Paper

Date of Publication: 2017-01-01

Included Journals: CPCI-S、EI、Scopus

Volume: 10261

Page Number: 285-292

Key Words: Single channel speech separation; Deep neural network; Discriminative object function

Abstract: Single channel speech separation (SCSS) is an important and challenging research problem and has received considerable interests in recent years. A supervised single channel speech separation method based on deep neural network (DNN) is proposed in this paper. We explore a new training strategy based on curriculum learning to enhance the robustness of DNN. In the training processing, the training samples firstly are sorted by the separation difficulties and then gradually introduced into DNN for training from easy to complex cases, which is similar to the learning principle of human brain. In addition, a strong discriminative objective function for reducing the source interference is designed by adding in the correlation coefficients and negentropy. The efficiency of the proposed method is substantiated by a monaural speech separation task using TIMIT corpus.