Semi-Supervised Singing Voice Separation with Noisy Self-Training
Abstract
Recent progress in singing voice separation has primarily focused on supervised deep learning methods. However, the scarcity of ground-truth data with clean musical sources has been a problem for long. Given a limited set of labeled data, we present a method to leverage a large volume of unlabeled data to improve the model's performance. Following the noisy self-training framework, we first train a teacher network on the small labeled dataset and infer pseudo-labels from the large corpus of unlabeled mixtures. Then, a larger student network is trained on combined ground-truth and self-labeled datasets. Empirical results show that the proposed self-training scheme, along with data augmentation methods, effectively leverage the large unlabeled corpus and obtain superior performance compared to supervised methods.
Cite
@article{arxiv.2102.07961,
title = {Semi-Supervised Singing Voice Separation with Noisy Self-Training},
author = {Zhepei Wang and Ritwik Giri and Umut Isik and Jean-Marc Valin and Arvindh Krishnaswamy},
journal= {arXiv preprint arXiv:2102.07961},
year = {2021}
}
Comments
Accepted at 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2021)