As part of my PhD research into the use of generative music models with music composition, I worked alongside my friend and fellow researcher Jingjing Tang at C4DM, QMUL to develop a dataset where we could explore generating variations with a transformer model.
The dataset is available to download here: dataset link.
Since the publication of the dataset, I have been working towards benchmarking this data for the Music Overpainting task. A paper presenting a baseline for the task was recently accepted to the AES International Symposium on AI and the Musician.
Stay tuned for the official implementation, and newer generations of variations!
References
2023
-
JAZZVAR: A Dataset of Variations found within Solo Piano Performances of Jazz Standards for Music Overpainting
Eleanor Row, Jingjing Tang, and George Fazekas
In Proceedings of the 16th International Symposium on Computer Music Multidisciplinary Research, Jul 2023
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.