IEICE TRANSACTIONS on Fundamentals
Music Signal Separation Based on Supervised Nonnegative Matrix Factorization with Orthogonality and Maximum-Divergence Penalties
Summary :
In this letter, we address monaural source separation based on supervised nonnegative matrix factorization (SNMF) and propose a new penalized SNMF. Conventional SNMF often degrades the separation performance owing to the basis-sharing problem. Our penalized SNMF forces nontarget bases to become different from the target bases, which increases the separated sound quality.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E97-A No.5 pp.1113-1118
- Publication Date
- 2014/05/01
- Publicized
- Online ISSN
- 1745-1337
- DOI
- 10.1587/transfun.E97.A.1113
- Type of Manuscript
- LETTER
- Category
- Engineering Acoustics
Authors
Daichi KITAMURA
Nara Institute of Science and Technology
Hiroshi SARUWATARI
Nara Institute of Science and Technology
Kosuke YAGI
Nara Institute of Science and Technology
Kiyohiro SHIKANO
Nara Institute of Science and Technology
Yu TAKAHASHI
Yamaha Corporation
Kazunobu KONDO
Yamaha Corporation
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Daichi KITAMURA, Hiroshi SARUWATARI, Kosuke YAGI, Kiyohiro SHIKANO, Yu TAKAHASHI, Kazunobu KONDO, "Music Signal Separation Based on Supervised Nonnegative Matrix Factorization with Orthogonality and Maximum-Divergence Penalties" in IEICE TRANSACTIONS on Fundamentals,
vol. E97-A, no. 5, pp. 1113-1118, May 2014, doi: 10.1587/transfun.E97.A.1113.
Abstract: In this letter, we address monaural source separation based on supervised nonnegative matrix factorization (SNMF) and propose a new penalized SNMF. Conventional SNMF often degrades the separation performance owing to the basis-sharing problem. Our penalized SNMF forces nontarget bases to become different from the target bases, which increases the separated sound quality.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.E97.A.1113/_p
Copy
@ARTICLE{e97-a_5_1113,
author={Daichi KITAMURA, Hiroshi SARUWATARI, Kosuke YAGI, Kiyohiro SHIKANO, Yu TAKAHASHI, Kazunobu KONDO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Music Signal Separation Based on Supervised Nonnegative Matrix Factorization with Orthogonality and Maximum-Divergence Penalties},
year={2014},
volume={E97-A},
number={5},
pages={1113-1118},
abstract={In this letter, we address monaural source separation based on supervised nonnegative matrix factorization (SNMF) and propose a new penalized SNMF. Conventional SNMF often degrades the separation performance owing to the basis-sharing problem. Our penalized SNMF forces nontarget bases to become different from the target bases, which increases the separated sound quality.},
keywords={},
doi={10.1587/transfun.E97.A.1113},
ISSN={1745-1337},
month={May},}
Copy
TY - JOUR
TI - Music Signal Separation Based on Supervised Nonnegative Matrix Factorization with Orthogonality and Maximum-Divergence Penalties
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1113
EP - 1118
AU - Daichi KITAMURA
AU - Hiroshi SARUWATARI
AU - Kosuke YAGI
AU - Kiyohiro SHIKANO
AU - Yu TAKAHASHI
AU - Kazunobu KONDO
PY - 2014
DO - 10.1587/transfun.E97.A.1113
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E97-A
IS - 5
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - May 2014
AB - In this letter, we address monaural source separation based on supervised nonnegative matrix factorization (SNMF) and propose a new penalized SNMF. Conventional SNMF often degrades the separation performance owing to the basis-sharing problem. Our penalized SNMF forces nontarget bases to become different from the target bases, which increases the separated sound quality.
ER -
English
