Sound Event Detection with Soft Labels Using Self-Attention for Global Scene Feature Extraction

Published in DCASE 2023, 2023

Authors: Do Tri Nhan et al. (2023). Sound Event Detection with Soft Labels Using Self-Attention for Global Scene Feature Extraction. DCASE Workshop 2023.

Sound Event Detection system using soft-label training combined with self-attention mechanisms to capture global acoustic scene features, submitted to the DCASE 2023 Challenge.