Advantages of nonstationary Gabor transforms in beat tracking
2011 (English)In: MIRUM ’11 Proceedings of the 1st international ACM workshop on Music information retrieval with user-centered and multimodal strategies, ACM Press, 2011, 45-50 p.Conference paper (Refereed)
In this paper the potential of using nonstationary Gabor transform for beat tracking in music is examined. Nonstationary Gabor transforms are a generalization of the short-time Fourier transform, which allow flexibility in choosing the number of bins per octave, while retaining a perfect inverse transform. In this paper, it is evaluated if these properties can lead to an improved beat tracking in music signals, thus presenting an approach that introduces recent findings in mathematics to music information retrieval. For this, both nonstationaryGabor transforms and short-time Fourier transform are integrated into a simple beat tracking framework. Statistically significant improvements are observed on a large dataset, which motivates to integrate the nonstationary Gabor transform into state of the art approaches for beat tracking and tempo estimation.
Place, publisher, year, edition, pages
ACM Press, 2011. 45-50 p.
Beat tracking; Music information retrieval; Nonstationary Gabor transform
Research subject Computer Science; Information and Communication Technology; Speech and Music Communication
IdentifiersURN: urn:nbn:se:kth:diva-193768DOI: 10.1145/2072529.2072542ScopusID: 2-s2.0-84555188107OAI: oai:DiVA.org:kth-193768DiVA: diva2:1040348
1st international ACM workshop on Music information retrieval with user-centered and multimodal strategies
QC 201610312016-10-272016-10-102016-11-11Bibliographically approved