AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
4min 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)
How Do You Predict the Face?
The research was inspired by computer vision, or computer graphics. Threedinura rendering is big in that field for years and has led to massive improvements. And for some reason, audio was kind of lacking behind that,. Right? So we wondere why this is the case, and why we do not follow the same route as computer graphics where you have some threedy renderes that you can train and to and from data. If we want to represent reality, we do not want to have a linear function that is as close as possible, but we want to have data that we can measure and that we can optimize against. We could show in this paper that we can really improve
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