I would like to use pocketshinx to recognize and spot keyword from audio recording, and I need the time information of recognized keyword(i.e. at which time point the key word appears). So I want to know if there is any existing methods in API that can be used to achieve this. If no, could you please give me some suggestions on how to deal with such problem.
Many thanks.
Yuru Wang
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello.
I would like to use pocketshinx to recognize and spot keyword from audio recording, and I need the time information of recognized keyword(i.e. at which time point the key word appears). So I want to know if there is any existing methods in API that can be used to achieve this. If no, could you please give me some suggestions on how to deal with such problem.
Many thanks.
Yuru Wang
You can find the example in Python here:
https://github.com/cmusphinx/pocketsphinx/blob/master/swig/python/test/kws_test.py