Discriminative Enhancement for Single Channel Audio Source Separation Using Deep Neural Networks

详细信息    查看全文

• 关键词：Single channel audio source separation ; Deep neural networks ; Audio enhancement ; Discriminative training
• 刊名：Lecture Notes in Computer Science
• 出版年：2017
• 出版时间：2017
• 年：2017
• 卷：10169
• 期：1
• 页码：236-246
• 丛书名：Latent Variable Analysis and Signal Separation
• ISBN：978-3-319-53547-0
• 卷排序：10169

文摘

The sources separated by most single channel audio source separation techniques are usually distorted and each separated source contains residual signals from the other sources. To tackle this problem, we propose to enhance the separated sources to decrease the distortion and interference between the separated sources using deep neural networks (DNNs). Two different DNNs are used in this work. The first DNN is used to separate the sources from the mixed signal. The second DNN is used to enhance the separated signals. To consider the interactions between the separated sources, we propose to use a single DNN to enhance all the separated sources together. To reduce the residual signals of one source from the other separated sources (interference), we train the DNN for enhancement discriminatively to maximize the dissimilarity between the predicted sources. The experimental results show that using discriminative enhancement decreases the distortion and interference between the separated sources.