One paper has been accepted to NeurIPS 2022. NeurIPS is one of the major international conferences on machine learning and related areas.
Title: ComMU: Dataset for Combinatorial Music Generation
Authors: Lee Hyun* ** (Pozalabs, POSTECH), {TaeHyun Kim*, Hyolim Kang, Minjoo Ki} (Yonsei Univ.), {Hyeonchan Hwang, Kwanho Park, Sharang Han} (Pozalabs), Seon Joo Kim (Yonsei Univ.)
* equal contribution
** work done at Pozalabs, now at POSTECH EE
In this paper, we introduce combinatorial music generation, a new task to create varying background music based on given conditions. Combinatorial music generation creates short samples of music with rich musical metadata, and combines them to produce a complete music. In addition, we introduce ComMU, the first symbolic music dataset consisting of short music samples and their corresponding 12 musical metadata for combinatorial music generation. Our results show that we can generate diverse high-quality music only with metadata, and that our unique metadata such as track-role and extended chord quality improves the capacity of the automatic composition.
Listen music generated from the model.
You can listen other various generated music here!
