标题: MEMORY AUGMENTED NEURAL NETWORK FOR SOURCE SEPARATION
作者: Tsou, Kai-Wei
Chien, Jen-Tzung
电机工程学系
Department of Electrical and Computer Engineering
关键字: Long short-term memory;memory augmented neural network;monaural source separation
公开日期: 1-一月-2017
摘要: Recurrent neural network (RNN) based on long short-term memory (LSTM) has been successfully developed for single-channel source separation. Temporal information is learned by using dynamic states which are evolved through time and stored as an internal memory. The performance of source separation is constrained due to the limitation of internal memory which could not sufficiently preserve long-term characteristics from different sources. This study deals with this limitation by incorporating an external memory in RNN and accordingly presents a memory augmented neural network for source separation. In particular, we carry out a neural Turing machine to learn a separation model for sequential signals of speech and noise in presence of different speakers and noise types. Experiments show that speech enhancement based on memory augmented neural network consistently outperforms that using deep neural network and LSTM in terms of short-term objective intelligibility measure.
URI: http://hdl.handle.net/11536/146954
ISSN: 2161-0363
期刊: 2017 IEEE 27TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING
显示于类别:Conferences Paper