Skip to main content

Table 17 Speaker identification rates in actual environment (%)

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

Method Recognition rate
CMN 72.5
MCLMS-SS 87.8
MSLP-SS 83.8
BF-DNN 88.0
DAE 91.0
DAE + BF-DNN 92.5