Semi-supervised Learning Using Teacher-student Models for Vocal Melody Extraction

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 173
  • Download : 0
The lack of labeled data is a major obstacle in many music information retrieval tasks such as melody extraction, where labeling is extremely laborious or costly. Semi-supervised learning (SSL) provides a solution to alleviate the issue by leveraging a large amount of unlabeled data. In this paper, we propose an SSL method using teacher-student models for vocal melody extraction. The teacher model is pre-trained with labeled data and guides the student model to make identical predictions given unlabeled input in a self-training setting. We examine three setups of teacher-student models with different data augmentation schemes and loss functions. Also, considering the scarcity of labeled data in the test phase, we artificially generate large-scale testing data with pitch labels from unlabeled data using an analysis-synthesis method. The results show that the SSL method significantly increases the performance against supervised learning only and the improvement depends on the teacher-student models, the size of unlabeled data, the number of self-training iterations, and other training details. We also find that it is essential to ensure that the unlabeled audio has vocal parts. Finally, we show that the proposed SSL method allows a simple convolutional recurrent neural network model to achieve performance comparable to state-of-the-arts.
Publisher
International Society for Music Information Retrieval
Issue Date
2020-10-13
Language
English
Citation

The 21th International Society for Music Information Retrieval Conference (ISMIR)

URI
http://hdl.handle.net/10203/279069
Appears in Collection
GCT-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0