337 citations · 2.2k across the 46 of their papers we have counts for
Showing cs.SDShow all
2 papers · 1 filter
cs.SD2022
Melody transcription via generative pre-training
Chris Donahue, John Thickstun, Percy Liang
Despite the central role that melody plays in music perception, it remains an open challenge in music information retrieval to reliably detect the notes of the melody present in an…
cs.SD2021★ 22 cited
Codified audio language modeling learns useful representations for music information retrieval
Rodrigo Castellon, Chris Donahue, Percy Liang
We demonstrate that language models pre-trained on codified (discretely-encoded) music audio learn representations that are useful for downstream MIR tasks. Specifically, we explor…