Skip to main content

Table 4 Reverberation methods

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

Reverberation methods
Conventional methods
1 CMN MFCC with CMN
2 MCLMS-SS Multichannel least mean squares
   with spectral subtraction
3 MSLP-SS Multistep linear prediction
   with spectral subtraction
4 BF-MLP Bottleneck feature extracted
   from multilayer perceptron
DNN-based feature transformation methods
5 BF-DNN Bottleneck feature extracted
   from deep neural network
6 DAE Denoising autoencoder-based
   cepstral-domain dereverberation
7 DAE + BF-DNN Combination of DAE
   and BF-DNN