Melodic and Metrical Elements of Expressiveness in Hindustani Vocal Music

2025-08-06

AI Summary

How can distinct performances of the same Khayal composition—specifically two ragas—be computationally distinguished based on expressive pitch and rhythmic variation? Method: We propose a computational representation model integrating expressive temporal deviations and fine-grained pitch contour adjustments. The approach combines high-precision pitch tracking, beat-synchronous alignment, expert annotation, and cross-performance comparative analysis, applied to a multi-version audio dataset comprising ten artists’ renditions. Contribution/Results: Our model reliably discriminates between individual performances across both ragas, capturing subtle expressive differences that conventional features miss. This work constitutes the first systematic identification of computationally tractable dimensions of structured expressivity in Khayal improvisation. It establishes a novel paradigm for computational musicological modeling of Hindustani vocal music, advancing quantitative analysis of raga-based performance practice.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning
• Machine Learning: Representation Learning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

This paper presents an attempt to study the aesthetics of North Indian Khayal music with reference to the flexibility exercised by artists in performing popular compositions. We study expressive timing and pitch variations of the given lyrical content within and across performances and propose computational representations that can discriminate between different performances of the same song in terms of expression. We present the necessary audio processing and annotation procedures, and discuss our observations and insights from the analysis of a dataset of two songs in two ragas each rendered by ten prominent artists.

Problem

• Analyzing expressive timing and pitch variations in Hindustani vocal music
• Developing computational models to differentiate artistic performances
• Studying audio processing techniques for Khayal music aesthetics

Innovation

• Analyzing expressive timing and pitch variations
• Proposing computational performance discrimination models
• Developing audio processing and annotation techniques