3min chapter

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) cover image

Neural Synthesis of Binaural Speech From Mono Audio with Alexander Richard - #514

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

CHAPTER

How to Make a Realistic Virtual Reality Environment?

The system learns a kind of global representation of the room acoustics you are in, but it does not learn that you are standing in the corner of the room and it sounds significantly different. This is som we need to solve if we want to bring this technology into virtual reality and want to have a realistic impression. We can generalize really well on the transmitter side, meaning it doesn't really matter which kind of person is speaking. In the reconstruction of this arbitrary transmitter voice,. When it comes to the receiver, of course, the generalization is, well, we have one fixed ear pair. The relationship between the metric that you're training on and like, perceptual metrics from everything we

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

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

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