Learning Visual Voice Activity Detection with an Automatically Annotated Dataset Guy, Sylvain Lathuilière, Stéphane Mesejo Santiago, Pablo Horaud, Radu This work has been funded by the EU H2020 project #871245 SPRING and by the Multidisciplinary Institute in Artificial Intelligence (MIAI) #ANR-19-P3IA-0003. 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. 2021-10-04T07:11:17Z 2021-10-04T07:11:17Z 2020-10-16 info:eu-repo/semantics/conferenceObject Published version: S. Guy... [et al.]. "Learning Visual Voice Activity Detection with an Automatically Annotated Dataset," 2020 25th International Conference on Pattern Recognition (ICPR), 2021, pp. 4851-4856, doi: [10.1109/ICPR48806.2021.9412884] http://hdl.handle.net/10481/70588 eng info:eu-repo/grantAgreement/EC/H2020/871245 http://creativecommons.org/licenses/by-nc-nd/3.0/es/ info:eu-repo/semantics/openAccess Atribución-NoComercial-SinDerivadas 3.0 España IEEE