Cross-domain Semi-Supervised Audio Event Classification Using Contrastive Regularization
This addresses a domain-specific challenge in audio classification, offering incremental improvements for handling mismatched data distributions.
The paper tackled the problem of semi-supervised audio event classification with unlabeled data from different class distributions, proposing a contrastive regularization method and audio mixing augmentation, which improved performance and enhanced stable training and generalization.
In this study, we proposed a novel semi-supervised training method that uses unlabeled data with a class distribution that is completely different from the target data or data without a target label. To this end, we introduce a contrastive regularization that is designed to be target task-oriented and trained simultaneously. In addition, we propose an audio mixing based simple augmentation strategy that performed in batch samples. Experimental results validate that the proposed method successfully contributed to the performance improvement, and particularly showed that it has advantages in stable training and generalization.