Skip to main content

Table 4 WER when using acoustic models trained with (‘ ’) and without (‘-’) processing the training data with the SE front-end used during testing. The results are averaged over the acoustic conditions of SimData and RealData, for the development set

From: Strategies for distant speech recognitionin reverberant environments

Processing Train w/ SimData RealData
  SE front-end   
Distant - 8.3 % 24.1 %
WPE(1ch) - 7.5 % 22.8 %
  7.0 % 24.4 %
WPE(8ch) + MVDR - 6.2 % 16.1 %
  5.0 % 20.5 %