EURASIP Journal on Audio, Speech, and Music Processing

Table 9 Recognition rates of BF-DNN with and without pre-training for training data (%)

From: Deep neural network-based bottleneck feature and denoising autoencoder-based dereverberation for distant-talking speaker identification

Method	Pre-training	CENSREC-4 database			Ave.
		0.40	0.60	0.75
BF-DNN	With	88.40	83.90	88.10	86.80
BF-MLP	Without	84.85	78.15	83.50	82.17

Back to article page