We have 2 research papers accepted to present at #ICASSP in Hyderabad! You can read the preprints:
"LHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and Tagging" led by Shubhr Singh https://arxiv.org/abs/2501.03464
"Acoustic identification of individual animals with hierarchical contrastive learning" led by Ines Nolasco https://arxiv.org/abs/2409.08673 #machinelearning #machinelistening #bioacoustics
arXiv.orgLHGNN: Local-Higher Order Graph Neural Networks For Audio Classification and TaggingTransformers have set new benchmarks in audio processing tasks, leveraging self-attention mechanisms to capture complex patterns and dependencies within audio data. However, their focus on pairwise interactions limits their ability to process the higher-order relations essential for identifying distinct audio objects. To address this limitation, this work introduces the Local- Higher Order Graph Neural Network (LHGNN), a graph based model that enhances feature understanding by integrating local neighbourhood information with higher-order data from Fuzzy C-Means clusters, thereby capturing a broader spectrum of audio relationships. Evaluation of the model on three publicly available audio datasets shows that it outperforms Transformer-based models across all benchmarks while operating with substantially fewer parameters. Moreover, LHGNN demonstrates a distinct advantage in scenarios lacking ImageNet pretraining, establishing its effectiveness and efficiency in environments where extensive pretraining data is unavailable.
