Rachel Bittner

Closing this because of inactivity, but feel free to reopen if you're still running into this issue.

Hey @nick-thompson ! We're following the [General MIDI protocol for pitch bend values](https://en.wikipedia.org/wiki/Pitch_wheel#:~:text=MIDI%20represents%20pitch%20bend%20as,range%20of%20%C2%B12%20semitones). The values will be between -8192 and 8191, representing a semitone range of +/- 2 semitones (i.e....

Closing due to inactivity - feel free to reopen if this issue is still persisting.

Hey @kasravi ! We do support human voice - (check out our [about page](https://basicpitch.spotify.com/about)) - but not every recording will work perfectly out of the box. On the website, you...

@cwitkowitz good catch on this bug! I think the bug boils down to a false assumption the function makes - that the time series is uniformly spaced / time stamps...

> The high-level rule is to try to stick to external conventions, i.e. if in all past datasets/papers/competitions the multipitch time series are uniform, then we can assume that. But...

@cwitkowitz If you haven't gotten too far - I have a [old script](https://github.com/marl/medleydb/blob/master/scripts/fill_tony_file.py) that does exactly this (filling in missing time stamps) if you want to use it as a...

@cwitkowitz > I went a little down the path of implementing what I mentioned above, i.e. estimating the hop length by taking the mean of first-order differentials wherever the second-order...

Another difference - multipitch is intended for time varying pitch curves/sequences whereas transcription is events with a single pitch throughout the note. On Wednesday, September 21, 2016, Colin Raffel [email protected]...

Hey @maxpv >In the first paper from 2007 there are two sections in the Transcription Results section: Frame-level transcription (5.1) and Note onset detection (5.2). In the [documentation](https://craffel.github.io/mir_eval/#id11)  The...