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