EmoBERTa

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

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

Audio4 results

Emotion RecognitiononIEMOCAP
Weighted-F1· 2021-08-26
68.57
best: 74.08 (SDT)
SOTA
EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa arXiv:2108.12009
Emotion RecognitiononCPED
Accuracy of Sentiment· 2021-08-26
48.09
best: 51.5 (BERT+AVG+MLP)
EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa arXiv:2108.12009
Emotion RecognitiononCPED
Macro-F1 of Sentiment· 2021-08-26
44.6
best: 48.02 (BERT+AVG+MLP)
EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa arXiv:2108.12009
Emotion RecognitiononMELD
Weighted-F1· 2021-08-26
65.61
best: 69.9 (ELR-GNN)
EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa arXiv:2108.12009