News Uncategorized Experimental AI framework Vx2Text generates video captions using inferences from audio and text [VentureBeat] February 2, 2021 Thomas Giboney computers, home theater, Nintendo, playstation, projectors, receivers, Smart Home, speakers, surround sound, technology, televisions, video games, xbox Researchers at Facebook have developed a framework, Vx2Text, that can generate captions by inferring from videos, audio, and text. View Article on VentureBeat AI,Big Data,Dev,Media,VB Home Page,ai,artificial intelligence,audio,machine learning,multimodal,text,Video,Vx2Text audio Spread the word!Click to share on Twitter (Opens in new window)Click to share on Facebook (Opens in new window)Click to share on LinkedIn (Opens in new window)