Semi-supervised Audio Classification with Consistency-Based Regularization

Semi-supervised Audio Classification with Consistency-Based Regularization
Title:
Semi-supervised Audio Classification with Consistency-Based Regularization
Other Titles:
INTERSPEECH 2019
Publication Date:
15 September 2019
Citation:
Lu, K., Foo, C., Teh, K.K., Tran, H.D., Chandrasekhar, V.R. (2019) Semi-Supervised Audio Classification with Consistency-Based Regularization. Proc. Interspeech 2019, 3654-3658, DOI: 10.21437/Interspeech.2019-1231.
Abstract:
Consistency-based semi-supervised learning methods such as the Mean Teacher method are state-of-the-art on image datasets, but have yet to be applied to audio data. Such methods encourage model predictions to be consistent on perturbed input data. In this paper, we incorporate audio-specific perturbations into the Mean Teacher algorithm and demonstrate the effectiveness of the resulting method on audio classification tasks. Specifically, we perturb audio inputs by mixing in other environmental audio clips, and leverage other training examples as sources of noise. Experiments on the Google Speech Command Dataset and UrbanSound8K Dataset show that the method can achieve comparable performance to a purely supervised approach while using only a fraction of the labels.
License type:
PublisherCopyrights
Funding Info:
Description:
Full paper can be downloaded from: https://doi.org/10.21437/Interspeech.2019-1231
ISBN:

Files uploaded:
File Size Format Action
There are no attached files.