Change search
ReferencesLink to record
Permanent link

Direct link
Bayesian meter tracking on learned signal representations
Austrian Research Institute for Artificial Intelligence (OFAI).ORCID iD: 0000-0003-1679-6018
2016 (English)In: Proceedings of ISMIR - International Conference on Music Information Retrieval, ISMIR , 2016, 262-268 p.Conference paper (Refereed)
Abstract [en]

Most music exhibits a pulsating temporal structure, known as meter. Consequently, the task of meter tracking is of great importance for the domain of Music Information Retrieval. In our contribution, we specifically focus on Indian art musics, where meter is conceptualized at several hierarchical levels, and a diverse variety of metrical hierarchies exist, which poses a challenge for state of the art analysis methods. To this end, for the first time, we combine Convolutional Neural Networks (CNN), allowing to transcend manually tailored signal representations, with subsequent Dynamic Bayesian Tracking (BT), modeling the recurrent metrical structure in music. Our approach estimates meter structures simultaneously at two metrical levels. The results constitute a clear advance in meter tracking performance for Indian art music, and we also demonstrate that these results generalize to a set of Ballroom dances. Furthermore, the incorporation of neural network output allows a computationally efficient inference. We expect the combination of learned signal representations through CNNs and higher-level temporal modeling to be applicable to all styles of metered music, provided the availability of sufficient training data.

Place, publisher, year, edition, pages
ISMIR , 2016. 262-268 p.
Keyword [en]
Bayesian signal processing, Deep learning, Beat Tracking, Meter, Rhythm
National Category
Media Engineering
Research subject
Computer Science; Media Technology; Speech and Music Communication
Identifiers
URN: urn:nbn:se:kth:diva-193756OAI: oai:DiVA.org:kth-193756DiVA: diva2:1040415
Conference
ISMIR - International Conference on Music Information Retrieval
Note

QC 20161031

Available from: 2016-10-27 Created: 2016-10-10 Last updated: 2016-11-11Bibliographically approved

Open Access in DiVA

fulltext(683 kB)8 downloads
File information
File name FULLTEXT01.pdfFile size 683 kBChecksum SHA-512
1131ad11e2aee4be03ae2b299ad0c3d604cc4d9f039392212479fa76299586c3065025e1194b4ecc4248103a7967179cd2e28529b845953f49b9b7f4dbe1b5ec
Type fulltextMimetype application/pdf

Other links

Published version

Search in DiVA

By author/editor
Holzapfel, André
Media Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 8 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 5 hits
ReferencesLink to record
Permanent link

Direct link