AudioCAN: Enhanced Few-Shot Audio Classification via Energy-Guided Temporal Cross Attention
- 19 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 2215-2219
Abstract
Despite the growing research interest and practical potential of few-shot audio classification, its efficacy remains limited by the temporal sparsity of target sound events and the presence of non-target acoustic interference within audio samples. In this work, we leverage the cross attention mechanism to address these challenges. While the Cross Attention Network (CAN) has demonstrated superior performance in few-shot image classification by highlighting semantically relevant regions between support and query features, we propose AudioCAN by extending CAN to audio domain through two-fold, audio-specific modifications. In particular, we first reformulate the original 2D spatial cross attention to 1D temporal version to prioritize the time frames containing discriminative acoustic information, thereby mitigating interference from non-target sounds. Secondly, we introduce an energy-guided masking strategy to synthesize a pseudo-query set from the support set via data augmentation, which then serves as a guidance for optimizing the 1D temporal cross attention during training. Experimental results on several few-shot audio classification benchmarks demonstrate that AudioCAN achieves state-of-the-art performance in 5-way-1-shot settings while remaining highly competitive in 5-way-5-shot configurations.Keywords
This publication has 15 references indexed in Scilit:
- Prototypical Contrastive Learning for Improved Few Shot Audio Classification2025
- MetaAudio: A Few-Shot Audio Classification Benchmark2022
- Meta-Baseline: Exploring Simple Meta-Learning for Few-Shot Learning2021
- Few-Shot Continual Learning for Audio Classification2021
- Few-Shot Acoustic Event Detection Via Meta Learning2020
- Few-Shot Sound Event Detection2020
- Multi-label Few-shot Learning for Sound Event Recognition2019
- Learning to Match Transient Sound Events Using Attentional Similarity for Few-shot Sound Recognition2019
- Learning to Compare: Relation Network for Few-Shot Learning2018
- Deep Residual Learning for Image Recognition2016