I'm trying to make use of pocketsphinx's phoneme recognition capabilities in the Unity engine in real time. Currently, the only way to get a sufficiently fast recognition rate is to use context independent recognition (allphone_ci). However, the accuracy is understandably poor.
Given the overwhelmingly large amount of parameters to tune pocketsphinx with, I was wondering if anyone could provide me with some useful configuration options for my specific usage.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I'm trying to make use of pocketsphinx's phoneme recognition capabilities in the Unity engine in real time. Currently, the only way to get a sufficiently fast recognition rate is to use context independent recognition (allphone_ci). However, the accuracy is understandably poor.
Given the overwhelmingly large amount of parameters to tune pocketsphinx with, I was wondering if anyone could provide me with some useful configuration options for my specific usage.
I am intrestiog too with the same issu