I am an absolute beginner for CMU Sphinx or any speech recognition system so apologies for mistakes I am about to make.
I saw the android demo but that is not the way I want to use pocketspinx, I want to use it for continuous conversation and I want to add a new language model (swahili) to it. but I dont even know I can do that, thanks for your help!!
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I am an absolute beginner for CMU Sphinx or any speech recognition system so apologies for mistakes I am about to make.
I saw the android demo but that is not the way I want to use pocketspinx, I want to use it for continuous conversation and I want to add a new language model (swahili) to it. but I dont even know I can do that, thanks for your help!!
It is not really possible, android phone is too slow for that. You can recognize a fixed set of words or you can spot a keyphrase.
Acoustic model training is described in tutorial
http://cmusphinx.sourceforge.net/wiki/tutorialam
Swahili data for training is available here:
https://github.com/besacier/ALFFA_PUBLIC/tree/master/ASR/SWAHILI
Also you probalby asked the same question here:
https://www.quora.com/How-can-I-develop-speech-recognition-android-app-for-Swahili-language