Revision history [back]

You asked the same question on stack overflow and Nikolay had posted an answer there.
So, I am just adding a link to that post so that others may find his apt answer.
Correct answer here
Also, there is an updated version of pocketsphinx available for ROS. You can find it here:
https://github.com/Pankaj-Baranwal/pocketsphinx/
You should use that instead.

You asked the same question on stack overflow and Nikolay had posted an answer there.
So, I am just adding a link to that post so that others may find his apt answer.
Correct answer here
---x---
The answer says the following:
"You can retrieve individual segments of hypothesis with iterator:
print 'Best hypothesis segments: ', [(seg.word, seg.prob) for seg in decoder.seg()]

seg.prob contains the confidence score. To have a meaningful confidence score you need to make sure your language model is large enough."
---x---
Also, there is an updated version of pocketsphinx available for ROS. You can find it here:
https://github.com/Pankaj-Baranwal/pocketsphinx/
You should use that instead.