JAZZVAR: A Dataset of Variations found within Solo Piano Performances of Jazz Standards for Music Overpainting
This provides a resource for music information retrieval researchers focusing on jazz variations, though it is incremental as it builds on existing jazz datasets by shifting focus from improvisation to variations.
The authors tackled the lack of datasets for jazz piano variations by creating JAZZVAR, a dataset of 502 pairs of Variation and Original MIDI segments from solo performances, and introduced a new generative task called Music Overpainting with a baseline Transformer model.
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.