A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition

06/30/2020 ∙ by Anurag Kumar, et al. ∙ 0

An important problem in machine auditory perception is to recognize and detect sound events. In this paper, we propose a sequential self-teaching approach to learning sounds. Our main proposition is that it is harder to learn sounds in adverse situations such as from weakly labeled and/or noisy labeled data, and in these situations a single stage of learning is not sufficient. Our proposal is a sequential stage-wise learning process that improves generalization capabilities of a given modeling system. We justify this method via technical results and on Audioset, the largest sound events dataset, our sequential learning approach can lead to up to 9 comprehensive evaluation also shows that the method leads to improved transferability of knowledge from previously trained models, thereby leading to improved generalization capabilities on transfer learning tasks.



There are no comments yet.


page 14

This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.