Graph-based temporal anomaly detection with self-supervised contrastive learning and dynamic adaptive thresholding for acoustic howling suppression

Acoustic howling due to feedback loops in audio systems is a major challenge in such fields as hearing aids or public address systems. Traditional approaches such as notch filters and adaptive feedback cancellation often have limitations such as lack of adaptability in dynamic environments, and a ne...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Xiaoqian Fan, Francisco Hernando-Gallego, Diego Martín, Mohammad Khishe
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	Elsevier 2026-03-01
Schriftenreihe:	Egyptian Informatics Journal
Schlagworte:	Self supervised learning Anomaly detection Howling detection Adaptive thresholding
Online-Zugang:	http://www.sciencedirect.com/science/article/pii/S1110866526000095
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!