Neural audio timbre transfer with RAVE trained on Amen breaks using nn~in Pure Data
Timbre transfer is one of the main use cases for RAVE, “A variational autoencoder for fast and high-quality neural audio synthesis” created by Antoine Caillon and Philippe Esling of Artificial Creative Intelligence and Data Science (ACIDS) at IRCAM, Paris.
In this video I’m showcasing a RAVE model (V2 architecture, spherical regularization) trained on of Amen break samples. The model loading is done via nn~ object in Pure Data.
1 view
660
167
8 months ago 00:05:41 0
Sofia - Your call in the night (Dieter Bohlen Style)
8 months ago 00:08:37 0
Are Hallucinations Popping the AI Bubble?
8 months ago 00:04:03 3
Три дня дождя, Тося Чайкина - Земля (Metal Version by SergeyVally) #кавер
9 months ago 00:01:40 24
Accentize Chameleon2 - Automatic Reverb Matching
9 months ago 00:04:47 15
Split Second - The Blade | Front Line Assembly
9 months ago 00:02:26 0
Gus Drax - Melancholic B minor ft@plugandplaychannel
9 months ago 01:00:00 0
ТРЕК С НУЛЯ Archetype Gojira’s Octaver вместо 8 струн
9 months ago 00:00:52 10
Guy tries DJENT for the 1st time
9 months ago 00:03:36 1
Alex Jones - Hurt
9 months ago 00:00:22 34
Deep Vintage Enhanced by APNN 2.0 - Trailer | Three-Body Technology