Constrained and regularized variants of non-negative matrix factorization incorporating music-specific constraints

Author

Kameoka, Hirokazu ; Nakano, Masahiro ; Ochiai, Kazuki ; Imoto, Yutaka ; Kashino, Kunio ; Sagayama, Shigeki

Author_Institution

Grad. Sch. of Inf. Sci. & Technol., Univ. of Tokyo, Tokyo, Japan

fYear

2012

fDate

25-30 March 2012

Firstpage

5365

Lastpage

5368

Abstract

Music spectrograms typically have many structural regularities that can be exploited to help solve the problem of decomposing a given spectrogram into distinct musically meaningful components. In this paper, we introduce new variants of the non-negative matrix factorization concept that incorporate music-specific constraints.

Keywords

audio signal processing; matrix decomposition; music; source separation; constrained variants; music spectrograms; music-specific constraints; nonnegative matrix factorization; regularized variants; source separation; spectrogram decomposition problem; structural regularities; Hidden Markov models; Instruments; Matrix decomposition; Multiple signal classification; Source separation; Spectrogram; Vectors; Music transcription; Non-negative Matrix Factorization; Source separation;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on

Conference_Location

Kyoto

ISSN

1520-6149

Print_ISBN

978-1-4673-0045-2

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2012.6289133

Filename

6289133

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3168605