Unsupervised Discriminative Learning of Sounds for Audio Event Classification

TitleUnsupervised Discriminative Learning of Sounds for Audio Event Classification
Publication TypeConference Paper
Year of Publication2021
AuthorsHornauer, S., Li K., Yu S. X., Ghaffarzadegan S., & Ren L.
Published inProceedings of IEEE International Conference on Acoustics, Speech and Signal Processing
Date Published06/2021
Other NumbersarXiv:2105.09279
Keywordsaudio event classification, unsupervised representation learning

Recent progress in network-based audio event classification has shown the benefit of pre-training models on visual data such as ImageNet. While this process allows knowledge transfer across different domains, training a model on large-scale visual datasets is time consuming. On several audio event classification benchmarks, we show a fast and effective alternative that pre-trains the model unsupervised, only on audio data and yet delivers on-par performance with ImageNet pre-training. Furthermore, we show that our discriminative audio learning can be used to transfer knowledge across audio datasets and optionally include ImageNet pre-training.