Conference paper Open Access

Multi-Task Learning of Tempo and Beat: Learning One to Improve the Other

Sebastian Böck; Matthew Davies; Peter Knees

In this paper, we propose a multi-task learning approach for simultaneous tempo estimation and beat tracking of musical audio. The system shows state-of-the-art performance for both tasks on a wide range of data, but has another fundamental advantage: due to its multi-task nature, it is not only able to exploit the mutual information of both tasks by learning a common, shared representation, but can also improve one by learning only from the other. The multi-task learning is achieved by globally aggregating the skip connections of a beat tracking system built around temporal convolutional networks, and feeding them into a tempo classification layer. The benefit of this approach is investigated by the inclusion of training data for which tempo-only annotations are available, and which is shown to provide improvements in beat tracking accuracy.

Files (360.1 kB)
Name Size
360.1 kB Download
All versions This version
Views 1313
Downloads 1212
Data volume 4.3 MB4.3 MB
Unique views 1111
Unique downloads 1212


Cite as