A computationally efficient scheme for dominant harmonic source separation

Mathieu Lagrange; Luis Gustavo Martins; George Tzanetakis

doi:10.1109/ICASSP.2008.4517572

A computationally efficient scheme for dominant harmonic source separation

Mathieu Lagrange^*, Luis Gustavo Martins, George Tzanetakis

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

The leading voice is an important feature of musical pieces and can often be considered as the dominant harmonic source. We propose in this paper a new scheme for the purpose of efficient dominant harmonic source separation. This is achieved by considering an har-monicity cue which is first compared with state-of-the-art cues using a generic evaluation methodology. The proposed separation scheme is then compared to a generic Computational Auditory Scene Analysis framework. Computational speed-up and performance comparison is done using source separation and music information retrieval tasks.

Original language	English
Title of host publication	2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Pages	165-168
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2008.4517572
Publication status	Published - 2008
Externally published	Yes
Event	2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP - Las Vegas, NV, United States Duration: 31 Mar 2008 → 4 Apr 2008

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)	1520-6149

Conference

Conference	2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Country/Territory	United States
City	Las Vegas, NV
Period	31/03/08 → 4/04/08

Keywords

Audio source separation
Auditory scene analysis
Harmonicity
Music information retrieval
Sinusoidal modeling

Access to Document

10.1109/ICASSP.2008.4517572

Cite this

Lagrange, M., Martins, L. G., & Tzanetakis, G. (2008). A computationally efficient scheme for dominant harmonic source separation. In 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP (pp. 165-168). Article 4517572 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2008.4517572

@inproceedings{1101a20ef0df4883a23e0aec23772055,

title = "A computationally efficient scheme for dominant harmonic source separation",

abstract = "The leading voice is an important feature of musical pieces and can often be considered as the dominant harmonic source. We propose in this paper a new scheme for the purpose of efficient dominant harmonic source separation. This is achieved by considering an har-monicity cue which is first compared with state-of-the-art cues using a generic evaluation methodology. The proposed separation scheme is then compared to a generic Computational Auditory Scene Analysis framework. Computational speed-up and performance comparison is done using source separation and music information retrieval tasks.",

keywords = "Audio source separation, Auditory scene analysis, Harmonicity, Music information retrieval, Sinusoidal modeling",

author = "Mathieu Lagrange and Martins, {Luis Gustavo} and George Tzanetakis",

note = "Copyright: Copyright 2008 Elsevier B.V., All rights reserved.; 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP ; Conference date: 31-03-2008 Through 04-04-2008",

year = "2008",

doi = "10.1109/ICASSP.2008.4517572",

language = "English",

isbn = "1424414849",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

pages = "165--168",

booktitle = "2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP",

}

Lagrange, M, Martins, LG & Tzanetakis, G 2008, A computationally efficient scheme for dominant harmonic source separation. in 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP., 4517572, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 165-168, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Las Vegas, NV, United States, 31/03/08. https://doi.org/10.1109/ICASSP.2008.4517572

A computationally efficient scheme for dominant harmonic source separation. / Lagrange, Mathieu; Martins, Luis Gustavo; Tzanetakis, George.
2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 2008. p. 165-168 4517572 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A computationally efficient scheme for dominant harmonic source separation

AU - Lagrange, Mathieu

AU - Martins, Luis Gustavo

AU - Tzanetakis, George

PY - 2008

Y1 - 2008

N2 - The leading voice is an important feature of musical pieces and can often be considered as the dominant harmonic source. We propose in this paper a new scheme for the purpose of efficient dominant harmonic source separation. This is achieved by considering an har-monicity cue which is first compared with state-of-the-art cues using a generic evaluation methodology. The proposed separation scheme is then compared to a generic Computational Auditory Scene Analysis framework. Computational speed-up and performance comparison is done using source separation and music information retrieval tasks.

AB - The leading voice is an important feature of musical pieces and can often be considered as the dominant harmonic source. We propose in this paper a new scheme for the purpose of efficient dominant harmonic source separation. This is achieved by considering an har-monicity cue which is first compared with state-of-the-art cues using a generic evaluation methodology. The proposed separation scheme is then compared to a generic Computational Auditory Scene Analysis framework. Computational speed-up and performance comparison is done using source separation and music information retrieval tasks.

KW - Audio source separation

KW - Auditory scene analysis

KW - Harmonicity

KW - Music information retrieval

KW - Sinusoidal modeling

UR - http://www.scopus.com/inward/record.url?scp=51449111220&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2008.4517572

DO - 10.1109/ICASSP.2008.4517572

M3 - Conference contribution

AN - SCOPUS:51449111220

SN - 1424414849

SN - 9781424414840

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 165

EP - 168

BT - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP

T2 - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP

Y2 - 31 March 2008 through 4 April 2008

ER -

A computationally efficient scheme for dominant harmonic source separation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this