Skip to main content

Table 8 Performance (in overall SAD detection error [77]) of deep learning-based approaches vs. the proposed algorithm for room-localized SAD on the DIRHA-sim-evalita corpus

From: Room-localized speech activity detection in multi-microphone smart homes

Method SAD error(%)
Deep learning DNN [30] 5.8
  3D-CNN [31] 7.0
  3D-CNN [32] 5.2
  3D-CNN (SAD+SLOC) [32] 3.5
Proposed Seg 5.7
  Win 4.7