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)
Deep Learning for Audio - What Is It and How Do We Do It?
Waf net has revolutionized text to speech and vocoting, meaning transferring mal spectrograms of frequency information into actual way forms of speech. So this is the logical starting point whenever you do something where you have generative audio and want to generate a raw way fom it. And we just used a conditioning on this information between transmitter and receiver. We designed differential version of dynamic time wopping as a neura network layer. This enables us to maintain all the physical properties of sound, but at the same time still a lining exactly between the transmitter and the receiver.
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