Exploring the Possibilities of Automated Annotation of Classical Music with Abrupt Tempo Changes

Exploring the Possibilities of Automated Annotation of Classical Music with Abrupt Tempo Changes

Paper in proceedings (conference paper)

In this paper, we introduce options for automatic measure detection based on synchronization, beat detection, and downbeat detection strategy. We evaluate proposed methods on two motifs from the dataset of Leoš Janáček's string quartet music. We use specific user-driven metrics to capture annotation efficiency simulating a scenario where a musicologist has to use the output of an automated system to create ground-truth annotations on given recordings. In the case of the first motif, synchronization outperformed other methods by detecting most of the measure positions correctly. This procedure was also the most suitable for the second motif—it achieved a low number of correct detections, but the vast majority of transferred time positions belonged within the outer tolerance window. Therefore, in most cases, only shifting operations were needed resulting in higher annotation efficiency. Results suggest that the state-of-the-art downbeat tracking is not yet efficient for expressive music.

In this paper, we introduce options for automatic measure detection based on synchronization, beat detection, and downbeat detection strategy. We evaluate proposed methods on two motifs from the dataset of Leoš Janáček's string quartet music. We use specific user-driven metrics to capture annotation efficiency simulating a scenario where a musicologist has to use the output of an automated system to create ground-truth annotations on given recordings. In the case of the first motif, synchronization outperformed other methods by detecting most of the measure positions correctly. This procedure was also the most suitable for the second motif—it achieved a low number of correct detections, but the vast majority of transferred time positions belonged within the outer tolerance window. Therefore, in most cases, only shifting operations were needed resulting in higher annotation efficiency. Results suggest that the state-of-the-art downbeat tracking is not yet efficient for expressive music.

beat tracking; classical music; downbeat detection; DTW; music information retrieval; music performance analysis; synchronization

beat tracking; classical music; downbeat detection; DTW; music information retrieval; music performance analysis; synchronization

IŠTVÁNEK, M.; MIKLÁNEK, Š.

2022

26.04.2022

Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií

Brno

978-80-214-6030-0

Proceedings II of the 28th Conference STUDENT EEICT 2022 Selected Papers

1

286

290

5

https://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2022_sbornik_2_v3.pdf