Found 2 document(s)
Page 1 of 1
-
Video-mediated conversational systems rely on synchronized speech and facial video, making audio--visual input integrity important for reliable perception. We study audio-frontend design in a fixed MRDF (Modality-Regular...
-
Audio-visual deepfake detectors are often trained under a single dataset or manipulation regime, but multi-source training collections may contain heterogeneous attacks and uneven source distributions. Training separate ...