The Application of Tempo Calculation for Musicological Purposes

The Application of Tempo Calculation for Musicological Purposes

Paper in proceedings (conference paper)

Beat tracking systems capture time positions of beats within digital recordings. They are used, for example, in streaming portals, but applications in the musicological analysis are often neglected. In this article, two different methods of beat tracking systems are tested—conventional and the state-of-the-art—on the specific motif of a string quartet music, which is one of the most complex tasks for beat detectors in general. The aim here is to determine which system is better for musicology purposes. This often involves determining not only the position of individual beats and estimating the tempo but also the accuracy of determining their number. Evaluation analysis may be suitable for comparing the accuracy of detectors, but may not necessarily reflect the requirements of musicological analysis. The results of selected detectors show that a system based on a recurrent neural network seems to be the most suitable.

Beat tracking systems capture time positions of beats within digital recordings. They are used, for example, in streaming portals, but applications in the musicological analysis are often neglected. In this article, two different methods of beat tracking systems are tested—conventional and the state-of-the-art—on the specific motif of a string quartet music, which is one of the most complex tasks for beat detectors in general. The aim here is to determine which system is better for musicology purposes. This often involves determining not only the position of individual beats and estimating the tempo but also the accuracy of determining their number. Evaluation analysis may be suitable for comparing the accuracy of detectors, but may not necessarily reflect the requirements of musicological analysis. The results of selected detectors show that a system based on a recurrent neural network seems to be the most suitable.

beat tracking; musicology; music analysis; music information retrieval; tempo estimation

beat tracking; musicology; music analysis; music information retrieval; tempo estimation

IŠTVÁNEK, M.

2021

27.04.2021

Brno University of Technology, Faculty of Electrical Engineering and Communication

Brno

978-80-214-5943-4

Proceedings II of the 27th Conference STUDENT EEICT 2021 selected papers

1

265

269

5

https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2021_sbornik_2_v3_DOI.pdf