Drum-Aware Ensemble Architecture for Improved Joint Musical Beat and Downbeat Tracking
This addresses improved music analysis for applications like music information retrieval, though it appears incremental as it builds on existing tracking methods with a novel integration.
The paper tackles the problem of joint beat and downbeat tracking in musical audio by integrating blind source separation to segregate percussive and non-percussive components, with results showing consistent outperformance over a baseline without source separation across four testing sets.
This paper presents a novel system architecture that integrates blind source separation with joint beat and downbeat tracking in musical audio signals. The source separation module segregates the percussive and non-percussive components of the input signal, over which beat and downbeat tracking are performed separately and then the results are aggregated with a learnable fusion mechanism. This way, the system can adaptively determine how much the tracking result for an input signal should depend on the input's percussive or non-percussive components. Evaluation on four testing sets that feature different levels of presence of drum sounds shows that the new architecture consistently outperforms the widely-adopted baseline architecture that does not employ source separation.