DADABOTS

Generating Black Metal and Math Rock

A Paper By CJ Carr & Zack Zukowski

"We use a modified SampleRNN architecture to generate music in modern genres such as black metal and math rock. Unlike MIDI and symbolic models, SampleRNN generates raw audio in the time domain. This requirement becomes increasingly important in modern music styles where timbre and space are used compositionally. Long developmental compositions with rapid transitions between sections are possible by increasing the depth of the network beyond the number used for speech datasets. We are delighted by the unique characteristic artifacts of neural synthesis."

Listen

New Albums

NOFX - Punk in Drublic

Original Music

Generated Music

Battles - Mirrored

Original Music

Generated Music

Meshuggah - Nothing

Original Music

Generated Music

Deep The Beatles

The Evolution of A Neural Model

Dillinger Escape Plan - Calculating Infinity

Original Music

Generated Music

Krallice - Diotima

Original Music

Generated Music