Medley2K: A Dataset of Medley Transitions
This dataset facilitates research on medley generation, addressing a niche problem in music AI, but it is incremental as it primarily provides a new resource without major methodological breakthroughs.
The authors tackled the understudied problem of automatic medley generation by creating Medley2K, a dataset of 2,000 medleys with 7,712 labeled transitions across various music genres, and validated it by training a state-of-the-art generative model for transition generation.
The automatic generation of medleys, i.e., musical pieces formed by different songs concatenated via smooth transitions, is not well studied in the current literature. To facilitate research on this topic, we make available a dataset called Medley2K that consists of 2,000 medleys and 7,712 labeled transitions. Our dataset features a rich variety of song transitions across different music genres. We provide a detailed description of this dataset and validate it by training a state-of-the-art generative model in the task of generating transitions between songs.