NMF-based multiple pitch estimation using sparseness and inter-frame continuity constraints

Takanori Fujisawa, Ikuo Degawa, Masaaki Ikehara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper proposes NMF-based (non-negative matrix factorization) multiple pitch estimation algorithm. The approach of NMF-based multiple pitch estimation is to decompose input magnitude spectrogram into sum of basis spectra representing individual pitches. In decomposing music signals, the amplitude of basis spectra should have sparseness, and the shape of amplitude should be continuous between neighbor temporal frames. We introduce the constraint using matrix norm to enforce these characteristic at once and propose new NMF algorithm for spectral decomposition with this constraint. The evaluation of solo piano music shows this algorithm can implement more robust pitch estimation in the place which input spectrum has certain different shape from basis spectra or the shape of input spectrum has temporal change.

Original languageEnglish
Title of host publication2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)9781479958962
DOIs
Publication statusPublished - 2014 Nov 14
Event2014 16th IEEE International Workshop on Multimedia Signal Processing, MMSP 2014 - Jakarta, Indonesia
Duration: 2014 Sep 222014 Sep 24

Other

Other2014 16th IEEE International Workshop on Multimedia Signal Processing, MMSP 2014
CountryIndonesia
CityJakarta
Period14/9/2214/9/24

Fingerprint

Factorization
Decomposition

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Signal Processing

Cite this

Fujisawa, T., Degawa, I., & Ikehara, M. (2014). NMF-based multiple pitch estimation using sparseness and inter-frame continuity constraints. In 2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014 [6958808] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MMSP.2014.6958808

NMF-based multiple pitch estimation using sparseness and inter-frame continuity constraints. / Fujisawa, Takanori; Degawa, Ikuo; Ikehara, Masaaki.

2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014. Institute of Electrical and Electronics Engineers Inc., 2014. 6958808.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fujisawa, T, Degawa, I & Ikehara, M 2014, NMF-based multiple pitch estimation using sparseness and inter-frame continuity constraints. in 2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014., 6958808, Institute of Electrical and Electronics Engineers Inc., 2014 16th IEEE International Workshop on Multimedia Signal Processing, MMSP 2014, Jakarta, Indonesia, 14/9/22. https://doi.org/10.1109/MMSP.2014.6958808
Fujisawa T, Degawa I, Ikehara M. NMF-based multiple pitch estimation using sparseness and inter-frame continuity constraints. In 2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014. Institute of Electrical and Electronics Engineers Inc. 2014. 6958808 https://doi.org/10.1109/MMSP.2014.6958808
Fujisawa, Takanori ; Degawa, Ikuo ; Ikehara, Masaaki. / NMF-based multiple pitch estimation using sparseness and inter-frame continuity constraints. 2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014. Institute of Electrical and Electronics Engineers Inc., 2014.
@inproceedings{4b8d2170a016453a98f657a59ce6db1e,
title = "NMF-based multiple pitch estimation using sparseness and inter-frame continuity constraints",
abstract = "This paper proposes NMF-based (non-negative matrix factorization) multiple pitch estimation algorithm. The approach of NMF-based multiple pitch estimation is to decompose input magnitude spectrogram into sum of basis spectra representing individual pitches. In decomposing music signals, the amplitude of basis spectra should have sparseness, and the shape of amplitude should be continuous between neighbor temporal frames. We introduce the constraint using matrix norm to enforce these characteristic at once and propose new NMF algorithm for spectral decomposition with this constraint. The evaluation of solo piano music shows this algorithm can implement more robust pitch estimation in the place which input spectrum has certain different shape from basis spectra or the shape of input spectrum has temporal change.",
author = "Takanori Fujisawa and Ikuo Degawa and Masaaki Ikehara",
year = "2014",
month = "11",
day = "14",
doi = "10.1109/MMSP.2014.6958808",
language = "English",
isbn = "9781479958962",
booktitle = "2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - NMF-based multiple pitch estimation using sparseness and inter-frame continuity constraints

AU - Fujisawa, Takanori

AU - Degawa, Ikuo

AU - Ikehara, Masaaki

PY - 2014/11/14

Y1 - 2014/11/14

N2 - This paper proposes NMF-based (non-negative matrix factorization) multiple pitch estimation algorithm. The approach of NMF-based multiple pitch estimation is to decompose input magnitude spectrogram into sum of basis spectra representing individual pitches. In decomposing music signals, the amplitude of basis spectra should have sparseness, and the shape of amplitude should be continuous between neighbor temporal frames. We introduce the constraint using matrix norm to enforce these characteristic at once and propose new NMF algorithm for spectral decomposition with this constraint. The evaluation of solo piano music shows this algorithm can implement more robust pitch estimation in the place which input spectrum has certain different shape from basis spectra or the shape of input spectrum has temporal change.

AB - This paper proposes NMF-based (non-negative matrix factorization) multiple pitch estimation algorithm. The approach of NMF-based multiple pitch estimation is to decompose input magnitude spectrogram into sum of basis spectra representing individual pitches. In decomposing music signals, the amplitude of basis spectra should have sparseness, and the shape of amplitude should be continuous between neighbor temporal frames. We introduce the constraint using matrix norm to enforce these characteristic at once and propose new NMF algorithm for spectral decomposition with this constraint. The evaluation of solo piano music shows this algorithm can implement more robust pitch estimation in the place which input spectrum has certain different shape from basis spectra or the shape of input spectrum has temporal change.

UR - http://www.scopus.com/inward/record.url?scp=84914141814&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84914141814&partnerID=8YFLogxK

U2 - 10.1109/MMSP.2014.6958808

DO - 10.1109/MMSP.2014.6958808

M3 - Conference contribution

AN - SCOPUS:84914141814

SN - 9781479958962

BT - 2014 IEEE International Workshop on Multimedia Signal Processing, MMSP 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -