English

Melody Classification based on Performance Event Vector and BRNN

Sound 2020-10-19 v2 Information Retrieval Audio and Speech Processing

Abstract

We proposed a model for the Conference of Music and Technology (CSMT2020) data challenge of melody classification. Our model used the Performance Event Vector as the input sequence to build a Bidirectional RNN network for classfication. The model achieved a satisfying performance on the development dataset and Wikifonia dataset. We also discussed the effect of several hyper-parameters, and created multiple prediction outputs for the evaluation dataset.

Keywords

Cite

@article{arxiv.2010.07562,
  title  = {Melody Classification based on Performance Event Vector and BRNN},
  author = {Jinyue Guo and Aozhi Liu and Jing Xiao},
  journal= {arXiv preprint arXiv:2010.07562},
  year   = {2020}
}
R2 v1 2026-06-23T19:22:02.134Z