Sequencing the musical sections with deep learning

Xuange Cui, Mingxue Liao, Pin Lv, Changwen Zheng

Abstract

Deep learning has become increasingly popular for sequence modeling in various domains. In this work, we address the musical order verification as a sequential pattern learning task. We present a more advanced self-supervised learning model, dubbed as the triple-wise similarity with recurrent neural networks (TSN-R) which is on the basis of state-of-the-art Similarity Embedding Network. We take triple-wise musical sections as the input instance, and leverage the temporal coherence as a supervisory signal. As a first step, we use the triplet Siamese network as the input layer, and assess the similarity of the triplet feature maps. After that, we choose the bidirectional LSTM to extract features along the time dimension. Finally, the subsequent fully-connected layers are used for order verification. The experiments show that our approach outperforms other competing models in terms of prediction accuracy. Additionally, this paper reveals the reasons for the good performance of our model through the 2d-visualization of features. All the source code, pre-trained models and the experiment results are available in our project page. https://github.com/ISCASTEAM/Sequencing-the-musical-sections.
BibTeX
@inproceedings{cui2019sequencing,
  author = {Xuange Cui and Mingxue Liao and Pin Lv and Changwen Zheng},
  title = {{Sequencing the musical sections with deep learning}},
  booktitle = {IJCNN},
  year = {2019},
  doi = {10.1109/ijcnn.2019.8851935},
}

Loading related content...

Figure