Unsupervised contrastive learning of sound event representations
Unsupervised contrastive learning of sound event representations
Citació
- Fonseca E, Ortego D, McGuinness K, O’Connor NE, Serra X. Unsupervised contrastive learning of sound event representations. In: 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2021): proceedings; 2021 Jun 6-11; Toronto, Canada. [Piscataway]: IEEE, 2021. p. 371-5. DOI: 10.1109/ICASSP39728.2021.9415009
Enllaç permanent
Descripció
Resum
Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data—a common scenario in sound event research. In this work, we explore unsupervised contrastive learning as a way to learn sound event representations. To this end, we propose to use the pretext task of contrasting differently augmented views of sound events. The views are computed primarily via mixing of training examples with unrelated backgrounds, followed by other data augmentations. We analyze the main components of our method via ablation experiments. We evaluate the learned representations using linear evaluation, and in two in-domain downstream sound event classification tasks, namely, using limited manually labeled data, and using noisy labeled data. Our results suggest that unsupervised contrastive pre-training can mitigate the impact of data scarcity and increase robustness against noisy labels.Descripció
Comunicació presentada a 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2021), celebrat del 6 a l'11 de juny de 2021 de manera virtual.