Memory augmented neural network for source separation

Kai Wei Tsou, Jen-Tzung Chien

研究成果: Conference contribution同行評審

8 引文 斯高帕斯(Scopus)

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.

原文English
主出版物標題2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Proceedings
編輯Naonori Ueda, Jen-Tzung Chien, Tomoko Matsui, Jan Larsen, Shinji Watanabe
發行者IEEE Computer Society
頁面1-6
頁數6
ISBN(電子)9781509063413
DOIs
出版狀態Published - 5 十二月 2017
事件2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017 - Tokyo, Japan
持續時間: 25 九月 201728 九月 2017

出版系列

名字IEEE International Workshop on Machine Learning for Signal Processing, MLSP
2017-September
ISSN(列印)2161-0363
ISSN(電子)2161-0371

Conference

Conference2017 IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2017
國家Japan
城市Tokyo
期間25/09/1728/09/17

指紋 深入研究「Memory augmented neural network for source separation」主題。共同形成了獨特的指紋。

引用此