MusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2106.05630/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTMusicBERT: Symbolic Music Understanding with Large-Scale Pre-Training — mentioned by radqhttps://news.ycombinator.com/item?id=36054406urn:hackerpapers:mention:2106.05630:36054406Wed, 24 May 2023 05:26:52 GMT<p>This reminds me of the Octuple MIDI tokenization scheme introduced in the MusicBERT paper (https://arxiv.org/pdf/2106.05630.pdf). Would be interesting to see how much of a performance difference results from using a smaller decoder model (in Megabyte) instead of just doing a softmax (a la Octuple).</p><p><a href="https://hackerpaper.kaipfister.de/p/2106.05630/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.SD