EURASIP Journal on Audio, Speech, and Music Processing

Table 2 RECOLA database 5-fold cross-validation partitions

From: End-to-end speech emotion recognition using a novel context-stacking dilated convolution neural network

	Fold 1	Fold 2	Fold 3	Fold 4	Fold 5
Valid	train_1, dev_1	train_3, dev_3	train_5, dev_5	train_7, dev_7	train_9
Test	train_2 dev_2	train_4, dev_4	train_6, dev_6	train_8, dev_8	dev_9

Back to article page