SampleRNN: An Unconditional End-to-End Neural Audio Generation Model — mentioned by songeater

Mon, 04 Jul 2022 00:35:09 GMT

>> has anyone solved the data problem? So MIDI songs were being generated quite "early" on, even with basic text generators (LSTM models), where the "alphabet" was replaced by MIDI symbols. [1] What Jukebox (and other models) did well was work with raw audio, rather than rely on MIDI or similar transcriptions. They break down audio into "blocks" using Fast Fourier Transforms, then each block is "tokenized" and then fed into transformers, similar to GPT-3 or other newer text generation models. This now allows the "subtle" musicalities to be discovered by models without relying on…

Paper and discussion history. A mention is not an endorsement.

SampleRNN: An Unconditional End-to-End Neural Audio Generation Model · HackerPapers discussions

SampleRNN: An Unconditional End-to-End Neural Audio Generation Model — mentioned by songeater