Explainable Deep Learning Analysis for Raga Identification in Indian Art Music

TL;DR

This paper develops an explainable deep learning approach for Indian Raga identification, creating a new dataset, training a CNN-LSTM model, and applying explainability techniques to ensure the model's reasoning aligns with human expert understanding.

Contribution

It introduces a curated dataset of Hindustani Classical Music, trains a CNN-LSTM model for Raga identification, and employs explainability methods to interpret model decisions in line with human expertise.

Findings

Achieved 0.89 F1-score on Raga classification

Model explanations align well with human expert annotations

Demonstrated the effectiveness of explainability techniques in music classification

Abstract

Raga identification is an important problem within the domain of Indian Art music, as Ragas are fundamental to its composition and performance, playing a crucial role in music retrieval, preservation, and education. Few studies that have explored this task employ approaches such as signal processing, Machine Learning (ML), and more recently, Deep Learning (DL) based methods. However, a key question remains unanswered in all these works: do these ML/DL methods learn and interpret Ragas in a manner similar to human experts? Besides, a significant roadblock in this research is the unavailability of an ample supply of rich, labeled datasets, which drives these ML/DL-based methods. In this paper, firstly we curate a dataset comprising 191 hours of Hindustani Classical Music (HCM) recordings, annotate it for Raga and tonic labels, and train a CNN-LSTM model for the task of Automatic Raga Identification (ARI). We achieve a chunk-wise f1-measure of 0.89 for a subset of 12 Raga classes. Following this, we make one of the first attempts to employ model explainability techniques: SoundLIME and GradCAM++ for Raga identification, to evaluate whether the classifier's predictions align with human understanding of Ragas. We compare the generated explanations with human expert annotations and further analyze individual test examples to understand the role of regions highlighted by explanations in making correct or incorrect predictions made by the model. Our results demonstrate a significant alignment of the model's understanding with human understanding, and the thorough analysis validates the effectiveness of our approach.