pocketsphinx recognizer.py does not work [closed]

asked 2015-07-15 19:30:57 -0600

Zozo gravatar image

updated 2015-07-15 19:42:18 -0600

I have ROS indigo on Ubuntu 14.04 trusty. I am trying to work with pocketsphinx for sound recognition but it doesn’t work.

I run this command:

 roslaunch pocketsphinx robocup.launch

everything seems alright and I see this:

INFO: ngram_model_arpa.c(292): Reading trigrams
INFO: ngram_model_arpa.c(555):      154 = #trigrams created
INFO: ngram_model_arpa.c(556):        6 = #prob3 entries
INFO: ngram_search_fwdtree.c(99): 77 unique initial diphones
INFO: ngram_search_fwdtree.c(147): 0 root, 0 non-root channels, 12 single-phone words
INFO: ngram_search_fwdtree.c(186): Creating search tree
INFO: ngram_search_fwdtree.c(191): before: 0 root, 0 non-root channels, 12 single-phone words
INFO: ngram_search_fwdtree.c(326): after: max nonroot chan increased to 328
INFO: ngram_search_fwdtree.c(338): after: 77 root, 200 non-root channels, 11 single-phone words

But it doesn’t realize any word after this. I checked my microphone in sound/input and it is working well.

I use this function in my code too, recognize_from_microphone , https://github.com/cmusphinx/pocketsp...

It was working for a few days, and it stopped working. I got this mesage after running it.

ERROR: "cmd_ln.c", line 946: Unknown argument: -adcdev
READY....
Listening...
INFO: cmn_prior.c(131): cmn_prior_update: from < 40.00  3.00 -1.00  0.00  0.00  0.00  0.00  0.00  0.00  0.00  0.00  0.00  0.00 >
INFO: cmn_prior.c(149): cmn_prior_update: to   < 56.05  7.90 -4.66 -3.07  4.76  2.65 -0.72  5.26 -0.75  0.76  2.11  0.39  1.30 >
READY....
Listening...

Does anyone know what the problem could be? Thanks

edit retag flag offensive reopen merge delete

Closed for the following reason question is not relevant or outdated by tfoote
close date 2018-01-11 20:17:29.307371

Comments

did you resolve this problem?

guilherme gravatar image guilherme  ( 2017-02-10 12:53:11 -0600 )edit