Monophonic sound source separation by non-negative sparse autoencoders

Monophonic sound source separation is an essential subject on the fields where sound, such as voice, music and noise, is dealt with. In particular, unsupervised approaches to this problem have high versatility in comparison with supervised approaches. Non-negative matrix factorization is the most fr...

Full description

Bibliographic Details

Published in:	Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics pp. 3623 - 3626
Main Authors:	Zen, Keiki, Suzuki, Masahiro, Sato, Haruhiko, Oyama, Satoshi, Kurihara, Masahito
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01.01.2014
Subjects:	Artificial neural networks Image reconstruction IP networks monophonic sound source separation Neurons NMF non-negative sparse autoencoder online learning Source separation Sparse matrices unsupervised learning Vectors
ISSN:	1062-922X
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!