AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
3min chapter
Neural Synthesis of Binaural Speech From Mono Audio with Alexander Richard - #514
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Codac Avatars
The paper that we'll be talking about falls under the context of this broader effort called codac avatars. The idea of codec avatas is that you can have an avataof yourself in vetereality that looks like you, sounds like you, moves like you, while you wear the headset with this lossy sensory input. We need enough facial data to be able to make high quality threedy reconstruction in vr. So when we talk about the decoda site, that is what will generate your highly realistic representation in virtual reality.
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any
moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share
& Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Discover
highlights
Listen to the best highlights from the podcasts you love and dive into the full episode