Revision history [back]

You will need to prepare a dictionary and a keyword-list for those specific words.
Sample files for the same can be found:
https://github.com/Pankaj-Baranwal/pocketsphinx/tree/kinetic-devel/demo

The .dic files contain the words along with there phonetic transforms.
The .kwlist files contain the words along with their thresholds which can lie between -50 to +50. If it is too low, then the detection might contain way too many false alarms and thus give undesirable results. If it is too high, the engine might miss the detection for many utterances of the corresponding key-phrases.
You can use the script mentioned here to automate these setting up of these threshold values:
https://medium.com/@PankajB96/automatic-tuning-of-keyword-spotting-thresholds-a27256869d31