An approach to ontological learning from weak labels
Published in ICASSP 2023 - IEEE International Conference on Acoustics, Speech and Signal Processing, 2023
We present an approach to ontological learning from weak labels that leverages hierarchical relationships between audio event classes. Using the AudioSet ontology as our testbed, we demonstrate that incorporating structural knowledge about how concepts relate to each other can improve learning from weakly labeled data. Our method uses graph neural networks to model the ontological relationships and shows improved performance on both parent and child concepts in the audio event hierarchy.
Recommended citation: @inproceedings{shah2023approach, title={An Approach to Ontological Learning from Weak Labels}, author={Shah, Ankit and Tang, Larry and Chou, Po Hao and Zheng, Yi Yu and Ge, Ziqian and Raj, Bhiksha}, booktitle={ICASSP 2023 - IEEE International Conference on Acoustics, Speech and Signal Processing}, pages={1--5}, year={2023}, organization={IEEE} }
Download Paper