dc.contributor.author | Singh, S | en_US |
dc.contributor.author | Steinmetz, C | en_US |
dc.contributor.author | Benetos, E | en_US |
dc.contributor.author | Phan, QH | en_US |
dc.contributor.author | Stowell, D | en_US |
dc.date.accessioned | 2024-01-10T15:45:33Z | |
dc.date.available | 2023-12-27 | en_US |
dc.date.issued | 2024-01-17 | en_US |
dc.identifier.issn | 1558-2361 | en_US |
dc.identifier.uri | https://qmro.qmul.ac.uk/xmlui/handle/123456789/93742 | |
dc.description.abstract | Deep learning models such as CNNs and Transformers have achieved impressive performance for end-to-end audio tagging. Recent works have shown that despite stacking multiple layers, the receptive field of CNNs remains severely limited. Transformers on the other hand are able to map global context through self-attention, but treat the spectrogram as a sequence of patches which is not flexible enough to capture irregular audio objects. In this work, we treat the spectrogram in a more flexible way by considering it as graph structure and process it with a novel graph neural architecture called ATGNN. ATGNN not only combines the capability of CNNs with the global information sharing ability of Graph Neural Networks, but also maps semantic relationships between learnable class embeddings and corresponding spectrogram regions. We evaluate ATGNN on two audio tagging tasks, where it achieves 0.585 mAP on the FSD50K dataset and 0.335 mAP on the AudioSet-balanced dataset, achieving comparable results to Transformer based models with significantly lower number of learnable parameters. | en_US |
dc.format.extent | ? - ? (5) | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.relation.ispartof | IEEE Signal Processing Letters | en_US |
dc.title | ATGNN: audio tagging graph neural network | en_US |
dc.type | Article | |
dc.rights.holder | © 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | |
dc.identifier.doi | 10.1109/LSP.2024.3352514 | en_US |
pubs.notes | Not known | en_US |
pubs.publication-status | Published | en_US |
dcterms.dateAccepted | 2023-12-27 | en_US |
qmul.funder | GraphNEx: Graph Neural Networks for Explainable Artificial Intelligence::Engineering and Physical Sciences Research Council | en_US |
qmul.funder | GraphNEx: Graph Neural Networks for Explainable Artificial Intelligence::Engineering and Physical Sciences Research Council | en_US |
qmul.funder | GraphNEx: Graph Neural Networks for Explainable Artificial Intelligence::Engineering and Physical Sciences Research Council | en_US |