I've generated my own voice with AI! This is a relatively new technology and people have started generating not just celebrity voices, but entire musical pieces as well. The technology to generate sounds, both voices & music, has been rapidly improving the past few years thanks to deep learning. In this episode, I'll first demo some AI generated music. Then, i'll explain the physics of a waveform and how DeepMind used waveform-based data to generate some pretty realistic sounds in 2016. At the end, I'll describe the cutting edge of generative sound modeling, a paper released just 2 months ago called "MelNet". Enjoy! It would mean so much to me if you subscribe to my Youtube channel!
Coding challenge! Replicate MelNet by Sept 1 2019, submit your github links in the comment section and i'll announce the winner shortly afterwards in a video. Check out this guy's partial code for a headstart:
INSTAGRAM:
FACEBOOK:
TWITTER:
WEBSITE:
Generate your own voice using this web app:
DeepMind's WaveNet Blogpost + paper:
MelNet blogpost + paper:
My video on Convolutional Neural Networks:
Look at this absolute boss using sound for debugging:
Learn Machine Learning in 3 Months:
Shoutout to 3blue1brown's amazing "Manim" library! I used it for the first time in this video, for the latex highlighting and for the brief neural network. Watch me get better at it in the next few weeks:
Join us in the Wizards Slack channel:
Hit the Join button above to sign up to become a member of my channel for access to exclusive live streams!
Join us at the School of AI:
Signup for my newsletter for exciting updates in the field of AI:
And please support me on Patreon:
0 Comments