Text record of the talk 22 jan
Discrimination & big data
http://www.constantvzw.org/site/Discrimination-Big-Data.html
through speech recognition with Sphinx
with processus
../share/texts/22-01-2015_talk-discrimination-big-data_speech-recognition.txt (8Mo)
text cut in chapters
../share/texts/22-01-2015_talk-discrimination_speech-recognition_chapters.zip
final text only
../share/texts/22-01-2015_talk-dbd_speech-recognition_finalRonly.txt
___
about sphinx
http://cmusphinx.sourceforge.net/
howto install:
sudo apt-get install python-pocketsphinx
or
http://cmusphinx.sourceforge.net/wiki/download/
http://cmusphinx.sourceforge.net/wiki/tutorialpocketsphinx
then launch pocketsphinx_continuous to test
___
python script used for the talk's text-capture:
../share/scripts/rybn_python_OK.py
to use it, also install Gstreamer, with:
sudo apt-get install gstreamer0.10-pocketsphinx
__
then launch
python /home/.../sphinx/rybn_python_OK.py
and in a second terminal
netcat -u -k -l 5005 > /tmp/output.txt
or
netcat -u -k -l 5005 | tee /tmp/output.txt