[gradys]

They're discrete with such high cardinality that successful approaches will likely model them assuming they're basically continuous. Neural network layer activations are also discrete after all, but they're often 256+ dimensional vectors of float32s or float16s.

[rjeli]

Well, WaveNet[0] outputs audio in the time (not freq.) domain using PixelCNN, so it's not unthinkable.

https://deepmind.com/blog/wavenet-generative-model-raw-audio...