JAZZVAR: A Dataset of Variations found within Solo Piano Performances of Jazz Standards for Music Overpainting

TL;DR

JAZZVAR is a new dataset of paired jazz piano variations and originals, enabling research in music overpainting, expressive performance, and performer identification with a baseline Transformer model.

Contribution

The paper introduces JAZZVAR, a novel dataset of jazz piano variations and originals, and a new generative task called Music Overpainting.

Findings

Created a dataset of 502 variation-original pairs

Developed a baseline Transformer model for Music Overpainting

Demonstrated potential applications in expressive performance analysis

Abstract

Jazz pianists often uniquely interpret jazz standards. Passages from these interpretations can be viewed as sections of variation. We manually extracted such variations from solo jazz piano performances. The JAZZVAR dataset is a collection of 502 pairs of Variation and Original MIDI segments. Each Variation in the dataset is accompanied by a corresponding Original segment containing the melody and chords from the original jazz standard. Our approach differs from many existing jazz datasets in the music information retrieval (MIR) community, which often focus on improvisation sections within jazz performances. In this paper, we outline the curation process for obtaining and sorting the repertoire, the pipeline for creating the Original and Variation pairs, and our analysis of the dataset. We also introduce a new generative music task, Music Overpainting, and present a baseline Transformer model trained on the JAZZVAR dataset for this task. Other potential applications of our dataset include expressive performance analysis and performer identification.