Downbeat Tracking Using Beat-synchronous Features and Recurrent Neural Networks

Florian Krebs; Sebastian Böck; Matthias Dorfer; Gerhard Widmer

Downbeat Tracking Using Beat-synchronous Features and Recurrent Neural Networks

Florian Krebs, Sebastian Böck, Matthias Dorfer, Gerhard Widmer

Institute of Computational Perception

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

Abstract

In this paper, we propose a system that extracts the downbeat times from a beat-synchronous audio feature stream of a music piece. Two recurrent neural networks are used as a front-end: the first one models rhythmic content on multiple frequency bands, while the second one models the harmonic content of the signal. The output activations are then combined and fed into a dynamic Bayesian network which acts as a rhythmical language model. We show on seven commonly used datasets of Western music that the system is able to achieve state-of-the-art results.

Original language	English
Title of host publication	Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR).
Number of pages	7
Publication status	Published - Aug 2016

Fields of science

202002 Audiovisual media
102 Computer Sciences
102001 Artificial intelligence
102003 Image processing
102015 Information systems

JKU Focus areas

Computation in Informatics and Mathematics
Engineering and Natural Sciences (in general)

Cite this

@inproceedings{0a8b497b8baa4e439f56d58a29ecffba,

title = "Downbeat Tracking Using Beat-synchronous Features and Recurrent Neural Networks",

abstract = "In this paper, we propose a system that extracts the downbeat times from a beat-synchronous audio feature stream of a music piece. Two recurrent neural networks are used as a front-end: the first one models rhythmic content on multiple frequency bands, while the second one models the harmonic content of the signal. The output activations are then combined and fed into a dynamic Bayesian network which acts as a rhythmical language model. We show on seven commonly used datasets of Western music that the system is able to achieve state-of-the-art results.",

author = "Florian Krebs and Sebastian B{\"o}ck and Matthias Dorfer and Gerhard Widmer",

year = "2016",

month = aug,

language = "English",

booktitle = "Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR).",

}

TY - GEN

T1 - Downbeat Tracking Using Beat-synchronous Features and Recurrent Neural Networks

AU - Krebs, Florian

AU - Böck, Sebastian

AU - Dorfer, Matthias

AU - Widmer, Gerhard

PY - 2016/8

Y1 - 2016/8

N2 - In this paper, we propose a system that extracts the downbeat times from a beat-synchronous audio feature stream of a music piece. Two recurrent neural networks are used as a front-end: the first one models rhythmic content on multiple frequency bands, while the second one models the harmonic content of the signal. The output activations are then combined and fed into a dynamic Bayesian network which acts as a rhythmical language model. We show on seven commonly used datasets of Western music that the system is able to achieve state-of-the-art results.

AB - In this paper, we propose a system that extracts the downbeat times from a beat-synchronous audio feature stream of a music piece. Two recurrent neural networks are used as a front-end: the first one models rhythmic content on multiple frequency bands, while the second one models the harmonic content of the signal. The output activations are then combined and fed into a dynamic Bayesian network which acts as a rhythmical language model. We show on seven commonly used datasets of Western music that the system is able to achieve state-of-the-art results.

M3 - Conference proceedings

BT - Proceedings of the 17th International Society for Music Information Retrieval Conference (ISMIR).

ER -