Feature Aggregation with Two-Layer Ensemble Framework for Multilingual Speech Emotion Recognition

Table 15

Comparison of crossdataset evaluation results and EF-KEN performance for English and Korean.

Training dataset	Testing dataset (four emotions)
	IEMOCAP (%)	RAVDESS [45] (%)	MSP-IMPROV [46] (%)	KETI (%)
IEMOCAP	77.8	40.8	36.5	–
EF-KEN	39	–	–	43