These two modes are different. In JSGF you have more constraints on the accepted phrases, while in KWS you are free to spot what is in your list in any order
Developer can configure several “search” objects with different grammars and language models and switch them in runtime to provide interactive experience for the user.
There are different possible search modes:
keyword-efficientlylooksforkeyphraseandignoresotherspeech.allowstoconfiguredetectionthreshold.</li>grammar-recognizesspeechaccordingtoJSGFgrammar.Unlikekeyphrasegrammarsearchdoesn't ignore words which are not in grammar but tries to recognize them.
maybe he got some misspelled/reconised right cause of grammar mode..
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello!
KWS code
JSGF code
Using JSGF gives better accuracy for command control with microphone than using KWS and the thing is that I don't know why. Could anyone tell me why?
Thanks in advance for reply.
These two modes are different. In JSGF you have more constraints on the accepted phrases, while in KWS you are free to spot what is in your list in any order
Check again the tutorial for more details
http://cmusphinx.sourceforge.net/wiki/tutoriallm
For example, your KWS list might be improved by writing phrases and tuning thresholds.
Hi I am a noob but i found something here
http://cmusphinx.sourceforge.net/wiki/tutorialpocketsphinx#searches
Developer can configure several “search” objects with different grammars and language models and switch them in runtime to provide interactive experience for the user.
There are different possible search modes:
maybe he got some misspelled/reconised right cause of grammar mode..