Weakly Supervised Tabla Stroke Transcription via TI-SDRM: A Rhythm-Aware Lattice Rescoring Framework

TL;DR

This paper introduces a rhythm-aware lattice rescoring framework for weakly supervised tabla stroke transcription, leveraging a novel rhythmic model to improve accuracy without requiring detailed annotations.

Contribution

It presents a new weakly supervised approach combining a CTC-based model with a rhythmic rescoring framework, and establishes the first benchmark for this task in Hindustani classical music.

Findings

Significant reduction in stroke error rate with rhythmic rescoring

Effective integration of long-term rhythmic structure

First benchmark dataset for weakly supervised TST

Abstract

Tabla Stroke Transcription (TST) is central to the analysis of rhythmic structure in Hindustani classical music, yet remains challenging due to complex rhythmic organization and the scarcity of strongly annotated data. Existing approaches largely rely on fully supervised learning with onset-level annotations, which are costly and impractical at scale. This work addresses TST in a weakly supervised setting, using only symbolic stroke sequences without temporal alignment. We propose a framework that combines a CTC-based acoustic model with sequence-level rhythmic rescoring. The acoustic model produces a decoding lattice, which is refined using a \textbf{$T\bar{a}la$}-Independent Static--Dynamic Rhythmic Model (TI-SDRM) that integrates long-term rhythmic structure with short-term adaptive dynamics through an adaptive interpolation mechanism. We curate a new real-world tabla solo dataset and a complementary synthetic dataset, establishing the first benchmark for weakly supervised TST in Hindustani classical music. Experiments demonstrate consistent and substantial reductions in stroke error rate over acoustic-only decoding, confirming the importance of explicit rhythmic structure for accurate transcription.