Skip to main content

Table 2 Details of data set of SimData and RealData

From: Environment-dependent denoising autoencoder for distant-talking speech recognition

Speech Corpus Reverberant time Signal-to-noise ratio Distance between the microphones  
   Room 1 Room 2 Room 3   Near Far  
SimData WSJCAM0 0.25 s 0.5 s 0.7 s 20 dB 50 cm 200 cm  
RealData MC-WSJ-AV 0.7 s - - - 100 cm 250 cm