Using Sphinx ASR

From Robert-Depot
Revision as of 10:44, 3 October 2013 by Rtwomey (talk | contribs) (analyzing in ubuntu)

Jump to: navigation, search

Course

http://www.ece.ucsb.edu/Faculty/Rabiner/ece259/speech%20recognition%20course.html

http://www.ece.ucsb.edu/Faculty/Rabiner/ece259/speech%20course.html

analyzing in ubuntu

  • generating output from VoiceID program (prompting for unknown speakers)
vid -u -k -i robertrauschenberg1.mov
  • analyzing output of voiceID program with pocketsphinx
pocketsphinx_continuous -infile rauschenberg1.wav -hmm /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/ -lm /usr/local/share/pocketsphinx/model/lm/en_US/hub4.5000.DMP -dict /usr/local/share/pocketsphinx/model/lm/en_US/hub4.5000.dic
  • generte word timings
pocketsphinx_continuous -infile rauschenberg1.wav -hmm /usr/local/share/pocketsphinx/model/hmm/en_US/hub4wsj_sc_8k/ -lm /usr/local/share/pocketsphinx/model/lm/en_US/hub4.5000.DMP -dict /usr/local/share/pocketsphinx/model/lm/en_US/hub4.5000.dic -time yes