Reading List
How Synthesia is combining AI voice and video models to improve avatar realism with natural gestures and accent, intonation, and expressiveness preservation (Rhiannon Williams/MIT Technology Review) from Techmeme RSS feed.
How Synthesia is combining AI voice and video models to improve avatar realism with natural gestures and accent, intonation, and expressiveness preservation (Rhiannon Williams/MIT Technology Review)
Rhiannon Williams / MIT Technology Review:
How Synthesia is combining AI voice and video models to improve avatar realism with natural gestures and accent, intonation, and expressiveness preservation — Earlier this summer, I walked through the glassy lobby of a fancy office in London, into an elevator, and then along a corridor into a clean, carpeted room.