Music was generated autoregressively with SampleRNN, a recurrent neural network, trained on raw audio from the album Ideas of Reference. The machine listened to the album 29 times over several days. The machine generated 435 minutes of audio. A human listened to the machine audio, chose sections from varied evolution points, and taped them together into a 10 minute album. Titles were generated by a Markov chain, except for track 2. Epoch 29, iteration 79751 refers to how much the net had trained when the t
Hide player controls
Hide resume playing