# Chord positions?

**URL:** <https://community.metabrainz.org/t/chord-positions/374903>\
**Category:** AcousticBrainz\
**Created:** [April 16, 2018, 10:10pm UTC](https://community.metabrainz.org/t/chord-positions/374903 "2018-04-16T22:10:22Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![BrooksT](https://community.metabrainz.org/letter_avatar_proxy/v4/letter/b/45deac/32.png) [@BrooksT](https://community.metabrainz.org/u/BrooksT)\
**Post date:** [April 16, 2018, 10:10pm UTC](https://community.metabrainz.org/t/chord-positions/374903/1 "2018-04-16T22:10:22Z")

</div>

I’m getting great value from the beat\_positions element of the low-level data, but it would be even more useful if there was similar data showing the times that chords happen. The aggregation seems to be there in chords\_histogram… is there any way to get back to the discrete time/measurements that created the histogram?

---

<div class="post-metadata">

**Author:** ![loujin](https://community.metabrainz.org/user_avatar/community.metabrainz.org/loujin/32/126_2.png) [@loujin](https://community.metabrainz.org/u/loujin)\
**Post date:** [April 17, 2018, 12:22am UTC](https://community.metabrainz.org/t/chord-positions/374903/2 "2018-04-17T00:22:59Z")

</div>

(ping @alastairp)

You might find some information about it on the Essentia project pages. As far as I remember from discussing with Alastair at the last summit, the chord\_histogram algorithm was not very reliable (I don’t remember why, but I remember being confused by its output)

I think the only algo used by AcousticBrainz is [Chord Detection](http://essentia.upf.edu/documentation/reference/std_ChordsDetection.html) and you would like [Chord Detection Beats](http://essentia.upf.edu/documentation/reference/std_ChordsDetectionBeats.html), so you might want to open a ticket to have it used in the next version.

But again, I don’t know much about this so you should ask Alastair directly 🙂

---

<div class="post-metadata">

**Author:** ![BrooksT](https://community.metabrainz.org/letter_avatar_proxy/v4/letter/b/45deac/32.png) [@BrooksT](https://community.metabrainz.org/u/BrooksT)\
**Post date:** [April 18, 2018, 3:12am UTC](https://community.metabrainz.org/t/chord-positions/374903/3 "2018-04-18T03:12:24Z")

</div>

Thanks – will do. I know there’s some sensitivity to describing musical content in enough detail to be considered a derivative work, so I’d be happy enough just knowing _when_ chords change without knowing what each chord is.

---

<div class="post-metadata">

**Author:** ![alastairp](https://community.metabrainz.org/letter_avatar_proxy/v4/letter/a/b5a626/32.png) [@alastairp](https://community.metabrainz.org/u/alastairp)\
**Post date:** [June 25, 2018, 1:16pm UTC](https://community.metabrainz.org/t/chord-positions/374903/4 "2018-06-25T13:16:17Z")

</div>

Hi,  
We currently don’t compute any melodic/harmonic information in AcousticBrainz that changes over time (The only time-varying data that we compute is beats).  
The underlying algorithms from Essentia that we use in AcousticBrainz do compute this information, but for space and efficiency reasons we don’t share it to AcousticBrainz. If you’re interested in computing this on audio that you have access to I can explain how it’s done (though I expect that you’re more interested in seeing this on data in AB).  
Having an indication of when chords change is an interesting idea - we are thinking about the best way to report beats, bars, and section information about recordings and we can definitely think about adding this. I’ll add it to our ideas list, thanks!