The current version of pocketsphinx_continous gives the recognized output only after the long pause is detected, I would like to know if we can get the output immediately after speaking instead of waiting till the recording is stopped.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
You can call ps_get_hyp any time during decoding, it will return you current hypothesis, there is no need to wait for the end of the utterance. In particular this is very important in keyword spotting mode.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
The current version of pocketsphinx_continous gives the recognized output only after the long pause is detected, I would like to know if we can get the output immediately after speaking instead of waiting till the recording is stopped.
Pause is not that long, it's just 0.1 second.
You can call ps_get_hyp any time during decoding, it will return you current hypothesis, there is no need to wait for the end of the utterance. In particular this is very important in keyword spotting mode.