Melody Classification based on Performance Event Vector and BRNN
This work addresses melody classification for music technology applications, but it appears incremental as it applies existing methods to a specific data challenge.
The authors tackled the problem of melody classification by proposing a model that uses Performance Event Vector as input to a Bidirectional RNN, achieving satisfying performance on development and Wikifonia datasets.
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.