Ask HN: What's a good way to estimate notes from music files

[alkylketone]

I'm trying to estimate what note is being played in an instrumental track. I'd tried to approach this problem with by splitting the track into its different instruments with open_unmix [0], and then using librosa pitch tracking [1], and then cleaned the results, but unfortunately, the midi came out totally unrecognizable. I thought about approaching this problem again when I saw the recent post on audio source separation [2], but that still only solves the problem of separating the vocals from the instrumental track and into separate instruments.

Is there a better/more state of the art method to pitch estimation than librosa's piptrack, or am I just using piptrack improperly?

[0] https://github.com/sigsep/open-unmix-pytorch

[1] http://man.hubwiz.com/docset/LibROSA.docset/Contents/Resources/Documents/generated/librosa.core.piptrack.html

[2] https://news.ycombinator.com/item?id=24748793

[bjourne]

Are more than one instrument or pitch sounding simultaneously? If so, it is almost impossible. You could try deep learning, but there's no guarantee that your results would be transferable.

[alkylketone]

There's a couple source separation algorithms that do a pretty good job splitting the audio into single instrument tracks (I tried open_unmix) -- I'm struggling to transform the single instrument audio into frequencies or notes from that one instrument track.