EUVIMEDEUVIMED entdecken
Crossref

AudioCAN: Enhanced Few-Shot Audio Classification via Energy-Guided Temporal Cross Attention

Xuanyu Zhuang, Geoffroy Peeters, Gaël Richard

IEEE Signal Processing Letters · 2026 · 33 · 2215-2219

DOI: 10.1109/lsp.2026.3694791 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Signal Processing Letters, 2026. Verfasst von Xuanyu Zhuang und 2 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Zhuang, X., Peeters, G., & Richard, G. (2026). AudioCAN: Enhanced Few-Shot Audio Classification via Energy-Guided Temporal Cross Attention. IEEE Signal Processing Letters, 33, 2215-2219. https://doi.org/10.1109/lsp.2026.3694791

Vancouver

Zhuang X, Peeters G, Richard G. AudioCAN: Enhanced Few-Shot Audio Classification via Energy-Guided Temporal Cross Attention. IEEE Signal Processing Letters. 2026;33:2215-2219. doi:10.1109/lsp.2026.3694791

BibTeX
@article{Zhuang2026,
  author = {Zhuang, Xuanyu and Peeters, Geoffroy and Richard, Gaël},
  title = {AudioCAN: Enhanced Few-Shot Audio Classification via Energy-Guided Temporal Cross Attention},
  journal = {IEEE Signal Processing Letters},
  year = {2026},
  volume = {33},
  pages = {2215--2219},
  doi = {10.1109/lsp.2026.3694791}
}
Kostenlos starten →