My lips are concealed: Audio-visual speech enhancement through obstructions
This addresses the problem of robust speech separation in noisy environments with visual obstructions for applications like hearing aids or video conferencing, representing an incremental advance by enhancing existing audio-visual methods.
The paper tackles audio-visual speech enhancement for separating a speaker's voice from mixtures, even when visual cues are occluded, by introducing a deep network that conditions on lip movements and/or voice representations, achieving speaker-independent performance on unseen speakers and improving over previous models in occlusion cases.
Our objective is an audio-visual model for separating a single speaker from a mixture of sounds such as other speakers and background noise. Moreover, we wish to hear the speaker even when the visual cues are temporarily absent due to occlusion. To this end we introduce a deep audio-visual speech enhancement network that is able to separate a speaker's voice by conditioning on both the speaker's lip movements and/or a representation of their voice. The voice representation can be obtained by either (i) enrollment, or (ii) by self-enrollment -- learning the representation on-the-fly given sufficient unobstructed visual input. The model is trained by blending audios, and by introducing artificial occlusions around the mouth region that prevent the visual modality from dominating. The method is speaker-independent, and we demonstrate it on real examples of speakers unheard (and unseen) during training. The method also improves over previous models in particular for cases of occlusion in the visual modality.