Revisiting Meter Tracking in Carnatic Music using Deep Learning Approaches

Beat and downbeat tracking, jointly referred to as Meter Tracking, is a fundamental task in Music Information Retrieval (MIR). Deep learning models have far surpassedtraditional signal processing and classical machine learning approaches in this domain, particularly for Western (Eurogenetic) genres, where large annotated datasetsare widely available. These systems, however, perform less reliably on underrepresented musical traditions. Carnatic music, a rich tradition from the Indian subcontinent, is renowned for its rhythmic intricacy and unique metrical structures (t¯al.as). The most notable priorwork on meter tracking in this context employed probabilistic Dynamic Bayesian Networks (DBNs). The performance of state-of-the-art (SOTA) deep learning modelson Carnatic music, however, remains largely unexplored. In this study, we evaluate two models for meter tracking in Carnatic music: the Temporal Convolutional Network (TCN), a lightweight architecture that has beensuccessfully adapted for Latin rhythms, and Beat This!, a transformer-based model designed for broad stylistic coverage without the need for post-processing. Replicatingthe experimental setup of the DBN baseline on the Carnatic Music Rhythm (CMRf ) dataset, we systematically assess the performance of these models in a directlycomparable setting. We further investigate adaptation strategies, including fine-tuning the models on Carnatic data and the use of musically informed parameters. Results show that while off-the-shelf models do not always outperform the DBN, their performance improves substantially with transfer learning, matching or surpassingthe baseline. These findings indicate that SOTA deep learning models can be effectively adapted to underrepresented traditions, paving the way for more inclusiveand broadly applicable meter tracking systems.