Hidden discrete tempo model: A tempo-aware timing model for audio-to-score alignment

Cyril Joder; Slim Essid; Gaël Richard

doi:10.1109/ICASSP.2011.5946424

Hidden discrete tempo model: A tempo-aware timing model for audio-to-score alignment

Cyril Joder, Slim Essid, Gaël Richard

CNRS LTCI

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

Abstract

In this paper, we present the Hidden Discrete Tempo Model, an effective Dynamic Bayesian Network for audio to score matching. Its main feature is an explicit modeling of tempo, which directly influences the timing model of the musical performance. Thanks to a discretization of the tempo set, it allows for an efficient decoding by the Viterbi algorithm, and facilitates the introduction of features which directly depend on the local tempo. We take advantage of this property by using the cyclic tempogram descriptor in addition to chroma vectors and onset detection features. Experiment run on both classical piano and pop music show the very high accuracy of this model for audio to score alignment, as well as the usefulness of the tempo feature used.

Original language	English
Title of host publication	2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings
Pages	397-400
Number of pages	4
DOIs	https://doi.org/10.1109/ICASSP.2011.5946424
Publication status	Published - 18 Aug 2011
Externally published	Yes
Event	36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Prague, Czech Republic Duration: 22 May 2011 → 27 May 2011

Publication series

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

Conference

Conference	36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011
Country/Territory	Czech Republic
City	Prague
Period	22/05/11 → 27/05/11

Keywords

acoustic features
automatic alignment
dynamic Bayesian networks
music information retrieval

Access to Document

10.1109/ICASSP.2011.5946424

Cite this

Joder, C., Essid, S., & Richard, G. (2011). Hidden discrete tempo model: A tempo-aware timing model for audio-to-score alignment. In 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings (pp. 397-400). Article 5946424 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2011.5946424

@inproceedings{cbdf995738fe4da0bc37511ae6d1e400,

title = "Hidden discrete tempo model: A tempo-aware timing model for audio-to-score alignment",

abstract = "In this paper, we present the Hidden Discrete Tempo Model, an effective Dynamic Bayesian Network for audio to score matching. Its main feature is an explicit modeling of tempo, which directly influences the timing model of the musical performance. Thanks to a discretization of the tempo set, it allows for an efficient decoding by the Viterbi algorithm, and facilitates the introduction of features which directly depend on the local tempo. We take advantage of this property by using the cyclic tempogram descriptor in addition to chroma vectors and onset detection features. Experiment run on both classical piano and pop music show the very high accuracy of this model for audio to score alignment, as well as the usefulness of the tempo feature used.",

keywords = "acoustic features, automatic alignment, dynamic Bayesian networks, music information retrieval",

author = "Cyril Joder and Slim Essid and Ga{\"e}l Richard",

year = "2011",

month = aug,

day = "18",

doi = "10.1109/ICASSP.2011.5946424",

language = "English",

isbn = "9781457705397",

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

pages = "397--400",

booktitle = "2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings",

note = "36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 ; Conference date: 22-05-2011 Through 27-05-2011",

}

Joder, C, Essid, S & Richard, G 2011, Hidden discrete tempo model: A tempo-aware timing model for audio-to-score alignment. in 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings., 5946424, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 397-400, 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011, Prague, Czech Republic, 22/05/11. https://doi.org/10.1109/ICASSP.2011.5946424

Hidden discrete tempo model: A tempo-aware timing model for audio-to-score alignment. / Joder, Cyril; Essid, Slim; Richard, Gaël.
2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings. 2011. p. 397-400 5946424 (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 - Hidden discrete tempo model

T2 - 36th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011

AU - Joder, Cyril

AU - Essid, Slim

AU - Richard, Gaël

PY - 2011/8/18

Y1 - 2011/8/18

N2 - In this paper, we present the Hidden Discrete Tempo Model, an effective Dynamic Bayesian Network for audio to score matching. Its main feature is an explicit modeling of tempo, which directly influences the timing model of the musical performance. Thanks to a discretization of the tempo set, it allows for an efficient decoding by the Viterbi algorithm, and facilitates the introduction of features which directly depend on the local tempo. We take advantage of this property by using the cyclic tempogram descriptor in addition to chroma vectors and onset detection features. Experiment run on both classical piano and pop music show the very high accuracy of this model for audio to score alignment, as well as the usefulness of the tempo feature used.

AB - In this paper, we present the Hidden Discrete Tempo Model, an effective Dynamic Bayesian Network for audio to score matching. Its main feature is an explicit modeling of tempo, which directly influences the timing model of the musical performance. Thanks to a discretization of the tempo set, it allows for an efficient decoding by the Viterbi algorithm, and facilitates the introduction of features which directly depend on the local tempo. We take advantage of this property by using the cyclic tempogram descriptor in addition to chroma vectors and onset detection features. Experiment run on both classical piano and pop music show the very high accuracy of this model for audio to score alignment, as well as the usefulness of the tempo feature used.

KW - acoustic features

KW - automatic alignment

KW - dynamic Bayesian networks

KW - music information retrieval

U2 - 10.1109/ICASSP.2011.5946424

DO - 10.1109/ICASSP.2011.5946424

M3 - Conference contribution

AN - SCOPUS:80051645414

SN - 9781457705397

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

SP - 397

EP - 400

BT - 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings

Y2 - 22 May 2011 through 27 May 2011

ER -

Joder C, Essid S, Richard G. Hidden discrete tempo model: A tempo-aware timing model for audio-to-score alignment. In 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011 - Proceedings. 2011. p. 397-400. 5946424. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2011.5946424

Hidden discrete tempo model: A tempo-aware timing model for audio-to-score alignment

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this