Deconstructing Jazz Piano Style Using Machine Learning
This work addresses the challenge of aligning computational insights with practitioner interests in music analysis, offering a tool for music theory and performer identification, though it is incremental in applying existing methods to a specific domain.
The paper tackled the problem of identifying jazz musicians' styles using machine learning, achieving 94% accuracy across 20 classes with a novel multi-input architecture that analyzes melody, harmony, rhythm, and dynamics separately.
Artistic style has been studied for centuries, and recent advances in machine learning create new possibilities for understanding it computationally. However, ensuring that machine-learning models produce insights aligned with the interests of practitioners and critics remains a significant challenge. Here, we focus on musical style, which benefits from a rich theoretical and mathematical analysis tradition. We train a variety of supervised-learning models to identify 20 iconic jazz musicians across a carefully curated dataset of 84 hours of recordings, and interpret their decision-making processes. Our models include a novel multi-input architecture that enables four musical domains (melody, harmony, rhythm, and dynamics) to be analysed separately. These models enable us to address fundamental questions in music theory and also advance the state-of-the-art in music performer identification (94% accuracy across 20 classes). We release open-source implementations of our models and an accompanying web application for exploring musical styles.