A friend of mine needs some help on Audio Analysis.
She has around 40 files of speeches which need to be analyzed in a way to find out:
The pitch, volume, How long there is a pause, If the rhythm is getting faster or lower, if the speaker speaks slower or faster, how long does it take for the speaker to reply and then some more acoustic features likje MFCCs, spectral flux, centroid, larynx F.
She needs to get these info from each one of it separately and the compare them all together (machine learning) to get some results.
If anyone is interested to you can email me at: email@example.com for more info