Hi all,
Just wanted to share this paper from @ralphpeterson that is now published in eLife:
The journal has a nice explainer post here:
As part of the analysis, they extract acoustic features using VocalPy.
Check out Figure 3, supplement 2:
Acoustic features for GMM clusters.
Acoustic features computed on the top 100 most probable vocalizations from each GMM cluster. Mean values ± standard deviation shown. Details on acoustic feature calculation are described in the Methods section.
These features are computed with voc.feature.sat
https://vocalpy.readthedocs.io/en/latest/api/generated/vocalpy.feature.sat.html#vocalpy.feature.sat
We are mainly helping with a control experiment here, but I’ll take it! 
Huge thanks to @ralphpeterson for your contributions and feedback on vocalpy.feature.sat, and for giving us a shout out and citation in the methods 
