DCASE-2022

The DCASE2022 dataset/benchmark is used to evaluate sound event detection (SED) methods, providing a platform for assessing the performance of models in identifying and classifying overlapping audio events in real-world recordings.

Papers using DCASE-2022 (3)

AST-SED: An Effective Sound Event Detection Method Based On Audio Spectrogram Transformer2023 · 26 citesLanguage-based Audio Retrieval With Converging Tied Layers And Contrastive Loss2022 · 3 citesLanguage-Based Audio Retrieval with Converging Tied Layers and Contrastive Loss2022