CLAR: Contrastive Learning of Auditory Representations
This work addresses the challenge of learning superior auditory representations for audio processing tasks, presenting an incremental advancement over prior methods like SimCLR.
The paper tackles the problem of learning auditory representations by adapting contrastive self-supervised learning from vision to audio, achieving significant improvement in prediction performance with less labeled data and faster convergence compared to supervised and self-supervised approaches.
Learning rich visual representations using contrastive self-supervised learning has been extremely successful. However, it is still a major question whether we could use a similar approach to learn superior auditory representations. In this paper, we expand on prior work (SimCLR) to learn better auditory representations. We (1) introduce various data augmentations suitable for auditory data and evaluate their impact on predictive performance, (2) show that training with time-frequency audio features substantially improves the quality of the learned representations compared to raw signals, and (3) demonstrate that training with both supervised and contrastive losses simultaneously improves the learned representations compared to self-supervised pre-training followed by supervised fine-tuning. We illustrate that by combining all these methods and with substantially less labeled data, our framework (CLAR) achieves significant improvement on prediction performance compared to supervised approach. Moreover, compared to self-supervised approach, our framework converges faster with significantly better representations.