Skip to main content

Table 12 Recognition rates of DAE with varying numbers of layers for training data (%)

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

Method Number of layers CENSREC-4 database Ave.
   0.40 0.60 0.75  
DAE 1 95.35 90.65 95.20 93.73
DAE 3 95.40 91.50 94.70 93.87
DAE 5 94.30 90.85 93.80 92.98
DAE 7 89.65 84.40 87.60 87.22
DAE 9 87.85 82.75 87.50 86.03