EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

MRBERT: Pre-Training of Melody and Rhythm for Automatic Music Generation

Shuyu Li, Yunsick Sung

Mathematics · 2023-02-04 · 11 (4) · 798

DOI: 10.3390/math11040798 ↗

At a glance

Journal article in Mathematics, published online on 2023-02-04. Written by Shuyu Li and 1 co-authors. Cited 25 times so far (Crossref); 32 references. The full text is freely available (open access, CC BY 4.0). Funded by: Ministry of Education of the Republic of Korea, National Research Foundation of Korea.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Deep learning technology has been extensively studied for its potential in music, notably for creative music generation research. Traditional music generation approaches based on recurrent neural networks cannot provide satisfactory long-distance dependencies. These approaches are typically designed for specific tasks, such as melody and chord generation, and cannot generate diverse music simultaneously. Pre-training is used in natural language processing to accomplish various tasks and overcome the limitation of long-distance dependencies. However, pre-training is not yet widely used in automatic music generation. Because of the differences in the attributes of language and music, traditional pre-trained models utilized in language modeling cannot be directly applied to music fields. This paper proposes a pre-trained model, MRBERT, for multitask-based music generation to learn melody and rhythm representation. The pre-trained model can be applied to music generation applications such as web-based music composers that includes the functions of melody and rhythm generation, modification, completion, and chord matching after being fine-tuned. The results of ablation experiments performed on the proposed model revealed that under the evaluation metrics of HITS@k, the pre-trained MRBERT considerably improved the performance of the generation tasks by 0.09–13.10% and 0.02–7.37%, compared to the usage of RNNs and the original BERT, respectively.

Funding

  • Ministry of Education of the Republic of Korea
  • National Research Foundation of Korea

Cite

APA

Li, S., & Sung, Y. (2023). MRBERT: Pre-Training of Melody and Rhythm for Automatic Music Generation. Mathematics, 11(4), 798. https://doi.org/10.3390/math11040798

Vancouver

Li S, Sung Y. MRBERT: Pre-Training of Melody and Rhythm for Automatic Music Generation. Mathematics. 2023;11(4):798. doi:10.3390/math11040798

BibTeX
@article{Li2023,
  author = {Li, Shuyu and Sung, Yunsick},
  title = {MRBERT: Pre-Training of Melody and Rhythm for Automatic Music Generation},
  journal = {Mathematics},
  year = {2023},
  volume = {11},
  number = {4},
  pages = {798},
  doi = {10.3390/math11040798}
}
Start for free →