Browsing by Subject "Audio visual speech recognition"
Now showing items 1-2 of 2
-
Audio-visual speech recognition using depth information from the Kinect in noisy video conditions
(2012)In this paper we build on our recent work, where we successfully incorporated facial depth data of a speaker captured by the Microsoft Kinect device, as a third data stream in an audio-visual automatic speech recognizer. ... -
Deep View2View Mapping for View-Invariant Lipreading
(2019)Recently, visual-only and audio-visual speech recognition have made significant progress thanks to deep-learning based, trainable visual front-ends (VFEs), with most research focusing on frontal or near-frontal face videos. ...