Audiovisual (AV) speech refers to the perception of speech that combines both auditory (hearing) & visual (seeing) cues from a speaker's head face and mouth movements - the ref you cited is about one area ('machine' AV speech processing) - for human studies, see www.ncbi.nlm.nih.gov/pmc/articles...

Audiovisual speech perception: Moving beyond McGurk

Although it is clear that sighted listeners use both auditory and visual cues during speech perception, the manner in which multisensory information is combined is a matter of debate. One approach to ...

👍Thank you!