I was just asked on my forum if the continuous code does any kind of ongoing
recalibration of the expected level for silence after the initial calibration,
and I wasn't sure. If pocketsphinx_continuous is open for a while and the
average background noise level changes, does it pick up on that and alter the
expected power level that marks the transition from silence to speech, or
should we be doing the occasional recalibration?
Thanks,
Halle
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi Nickolay,
I was just asked on my forum if the continuous code does any kind of ongoing
recalibration of the expected level for silence after the initial calibration,
and I wasn't sure. If pocketsphinx_continuous is open for a while and the
average background noise level changes, does it pick up on that and alter the
expected power level that marks the transition from silence to speech, or
should we be doing the occasional recalibration?
Thanks,
Halle
Hello
Silence detector updates speech threshold on the way, there is no need to
recalibrate.
Excellent, thanks.
Is there any way to turn this auto calibration/silence detection off?
Not without source code modification