DF-ERC

Reported on 4 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio4 results

Emotion RecognitiononMELD
Accuracy· 2023-08-08
68.28
best: 68.7 (ELR-GNN)
SOTA
Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition arXiv:2308.04502
Emotion RecognitiononIEMOCAP
Accuracy· 2023-08-08
71.84
best: 73.95 (SDT)
SOTA
Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition arXiv:2308.04502
Emotion RecognitiononMELD
Weighted-F1· 2023-08-08
67.03
best: 69.9 (ELR-GNN)
Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition arXiv:2308.04502
Emotion RecognitiononIEMOCAP
Weighted-F1· 2023-08-08
71.75
best: 74.08 (SDT)
Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition arXiv:2308.04502