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...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics s. 3623 - 3626
Hlavní autoři: Zen, Keiki, Suzuki, Masahiro, Sato, Haruhiko, Oyama, Satoshi, Kurihara, Masahito
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.01.2014
Témata:
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
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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 frequently used algorithm for the monophonic sound source separation without prior knowledge. This is also applied to various applications, including data clustering, face recognition, gene expression classification. However, non-negative matrix factorization cannot be efficiently used in online learning. In order to solve this difficulty, the non-negative sparse autoencoder was proposed in the literature. Although several successful applications have been reported, this is not yet applied to the monophonic sound source separation. This paper shows that the non-negative sparse autoencoder can perform the monophonic sound source separation without prior knowledge in online learning.
ISSN:1062-922X
DOI:10.1109/SMC.2014.6974492