Stacking WaveNet autoencoders on top of each other leads to raw audio models that can capture long-range structure in music….

2018-06-28 IFTTT, Twitter, sedielem

Stacking WaveNet autoencoders on top of each other leads to raw audio models that can capture long-range structure in music. Check out our new paper: https://t.co/JGHfu2OkAL

Listen to some minute-long piano music samples: https://t.co/CzF7PnxVC3 pic.twitter.com/snWRKHbnwr
— Sander Dieleman (@sedielem) June 28, 2018

(via http://twitter.com/sedielem/status/1012126279871627265)