@misc{10481/70588,
year = {2020},
month = {10},
url = {http://hdl.handle.net/10481/70588},
abstract = {Visual voice activity detection (V-VAD) uses visual
features to predict whether a person is speaking or not. VVAD
is useful whenever audio VAD (A-VAD) is inefficient either
because the acoustic signal is difficult to analyze or because it is
simply missing. We propose two deep architectures for V-VAD,
one based on facial landmarks and one based on optical flow.
Moreover, available datasets, used for learning and for testing VVAD,
lack content variability. We introduce a novel methodology
to automatically create and annotate very large datasets inthe-
wild – WildVVAD – based on combining A-VAD with face
detection and tracking. A thorough empirical evaluation shows
the advantage of training the proposed deep V-VAD models with
this dataset.},
organization = {European Commission	871245 SPRING},
organization = {Multidisciplinary Institute in Artificial Intelligence (MIAI)	ANR-19-P3IA-0003},
publisher = {IEEE},
title = {Learning Visual Voice Activity Detection with an Automatically Annotated Dataset},
author = {Guy, Sylvain and Lathuilière, Stéphane and Mesejo Santiago, Pablo and Horaud, Radu},
}