For my bachelor thesis, I would like to analyse the voice stream of a few meetings of 5 to 10 persons.
The goal is to validate some hypothesis linking speech time repartition to the workshop creativity. I am looking for a tool that can be implemented easily and without any extensive knowledge of signal processing.
Ideally, I would like to feed the tool with an an audio input and get the time segments of the speaker either graphically or in matrix/array form.
- diarization does not need to be realtime
- source can be single or multi stream (we could install microphones on each participant)
- the process and can be (semi-)supervised if need be, we know the number of participants beforehand.
- Tool can be an matlab, .exe, java, or similar file. I am open for suggestions.
Again I am looking for the simplest, easy-to-install solution.
Thank you in advance
Basile Verhulst
Record your data with separate channels for each participant (min. 10 channel mixer). I would use Headset- microphones (e.g. Samson QV) plus appropriate preamps. Then either use what "http://www.praatvocaltoolkit.com/2012/11/extract-voiced-and-unvoiced.html" gives you (Free Software Praat) or try http://www.helsinki.fi/~lennes/praat-scripts/#pauses --> the mark_pauses.praat Script. For each participant you have to set individual pause thresholds of course. Then extract all not empty intervals add subtract pause time from recording time to get participants active part. Of course you can also implement a Matlab routine that runs through the signal with a certain time window detecting above threshold parts to calculate your data. Praat scripts might give you an idea on how to program it in Matlab.
Best
http://www-lium.univ-lemans.fr/diarization/doku.php/overview
https://www.idiap.ch/scientific-research/resources/speaker-diarization-toolkit
http://shout-toolkit.sourceforge.net/user_manual.html
- Badges
- Science topic