Score informed audio source separation using a parametric model of non-negative spectrogram

Author

Hennequin, Romain ; David, Bertrand ; Badeau, Roland

Author_Institution

Telecom ParisTech, Inst. Telecom, Paris, France

fYear

2011

fDate

22-27 May 2011

Firstpage

45

Lastpage

48

Abstract

In this paper we present a new technique for monaural source separation in musical mixtures, which uses the knowledge of the musical score. This information is used to initialize an algorithm which computes a parametric decomposition of the spectrogram based on non-negative matrix factorization (NMF). This algorithm provides time-frequency masks which are used to separate the sources with Wiener filtering.

Keywords

Wiener filters; audio signal processing; matrix decomposition; music; source separation; time-frequency analysis; Wiener filtering; monaural source separation; musical mixture; musical score; nonnegative matrix factorization; nonnegative spectrogram; parametric decomposition; parametric model; score informed audio source separation; time-frequency mask; Atomic clocks; Databases; Harmonic analysis; Source separation; Spectrogram; Time frequency analysis; Training; audio source separation; machine learning; music information retrieval; non-negative matrix factorization;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing (ICASSP), 2011 IEEE International Conference on

Conference_Location

Prague

ISSN

1520-6149

Print_ISBN

978-1-4577-0538-0

Electronic_ISBN

1520-6149

Type

conf

DOI

10.1109/ICASSP.2011.5946324

Filename

5946324