Speech-to-Speech Model Research at Google DeepMind — Valeria Wu Fon & Tom Ouyang, Google DeepMind
About this video
Advanced · Hand-picked by a BrighterTube curator · found via round-3 back catalogue of a channel Lumen picks video by video · 82% confidenceDescribes speech-to-speech model research and architecture at Google DeepMind. Teaches direct speech synthesis techniques that bypass text intermediate representations.
A 17-minute video from AI Engineer: “Speech-to-Speech Model Research at Google DeepMind — Valeria Wu Fon & Tom Ouyang, Google DeepMind”.
Video by AI Engineer, played through YouTube's embedded player.