Speech Emotion Recognition on IEMOCAP (Modal Unweighted Accuracy) benchmark leaderboard · SOTA2 Research

Speech Emotion Recognition on IEMOCAP (Modal Unweighted Accuracy)

72.83Unweighted Accuracy (Audio)Mutual Information Regularized Generative Model

Evaluation Results

Method
Mutual Information Regularized Generative Model2025.10	72.83	65.51	76.54
CIF-MMIN2025.10	58.44	69.26	75.65
MMIN2025.10	58.23	67.52	74.72
bc_LSTM2025.10	57.43	67.69	73.89
AE2025.10	56.79	25.44	26.25
CRA2025.10	56.79	27.96	30.13
sc_LSTM2025.10	55.96	63.51	68.45