ShrutiSense: Microtonal Modeling and Correction in Indian Classical Music

2025-08-02

AI Summary

Indian classical music relies on the 22-shruti microtonal system and raga-specific grammatical rules—structures poorly captured by existing symbolic music processing tools. To address this, we propose the first dual-model framework integrating shruti-aware modeling and raga-constrained generation: a finite-state transducer (FST) grounded in the 22-shruti scale for pitch restoration, coupled with a grammar-guided Shruti Hidden Markov Model (GC-SHMM) for context-aware melodic completion. Evaluated across five canonical ragas, the FST achieves 91.3% pitch correction accuracy and maintains robustness (86.7–90.0%) under 0.2–0.4 contamination rates and ±50-cent noise. This work constitutes the first unified computational model jointly encoding both the microtonal (shruti) and grammatical (raga) foundations of Indian classical music, establishing a novel paradigm for culturally aware music AI.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Indian classical music relies on a sophisticated microtonal system of 22 shrutis (pitch intervals), which provides expressive nuance beyond the 12-tone equal temperament system. Existing symbolic music processing tools fail to account for these microtonal distinctions and culturally specific raga grammars that govern melodic movement. We present ShrutiSense, a comprehensive symbolic pitch processing system designed for Indian classical music, addressing two critical tasks: (1) correcting westernized or corrupted pitch sequences, and (2) completing melodic sequences with missing values. Our approach employs complementary models for different tasks: a Shruti-aware finite-state transducer (FST) that performs contextual corrections within the 22-shruti framework and a grammar-constrained Shruti hidden Markov model (GC-SHMM) that incorporates raga-specific transition rules for contextual completions. Comprehensive evaluation on simulated data across five ragas demonstrates that ShrutiSense (FST model) achieves 91.3% shruti classification accuracy for correction tasks, with example sequences showing 86.7-90.0% accuracy at corruption levels of 0.2 to 0.4. The system exhibits robust performance under pitch noise up to +/-50 cents, maintaining consistent accuracy across ragas (90.7-91.8%), thus preserving the cultural authenticity of Indian classical music expression.

Problem

• Correcting westernized pitch sequences in Indian music
• Completing melodic sequences with missing values
• Modeling microtonal distinctions and raga grammars

Innovation

• Shruti-aware finite-state transducer for corrections
• Grammar-constrained Shruti hidden Markov model
• 22-shruti framework preserving cultural authenticity