Inferring metrical structure in music using particle filters
2015 (English)In: IEEE Transactions on Audio, Speech and Language Processing, Vol. 23, no 5, 817-827 p.Article in journal (Refereed) Published
In this paper, we propose a new state-of-the-art particle filter (PF) system to infer the metrical structure of musical audio signals. The new inference method is designed to overcome the problem of PFs in multi-modal probability distributions, which arise due to tempo and phase ambiguities in musical rhythm representations. We compare the new method with a hidden Markov model (HMM) system and several other PF schemes in terms of performance, speed and scalability on several audio datasets. We demonstrate that using the proposed system the computational complexity can be reduced drastically in comparison to the HMM while maintaining the same order of beat tracking accuracy. Therefore, for the first time, the proposed system allows fast meter inference in a high-dimensional state space, spanned by the three components of tempo, type of rhythm, and position in a metric cycle.
Place, publisher, year, edition, pages
IEEE Press, 2015. Vol. 23, no 5, 817-827 p.
approximate inference; Bayesian modeling; beat tracking; downbeat tracking; particle filters (PFs)
Research subject Computer Science; Information and Communication Technology; Speech and Music Communication
IdentifiersURN: urn:nbn:se:kth:diva-193770DOI: 10.1109/TASLP.2015.2409737ISI: 000352281500001ScopusID: 2-s2.0-84954458463OAI: oai:DiVA.org:kth-193770DiVA: diva2:1040350
QC 201610272016-10-272016-10-102016-11-22Bibliographically approved