Im working on cmusphinx speech to text, I need to train/add words to my dictionary, so i used lmtool and uploaded a corpus file and used the .dict and .lm file and used these as parameters for pocketsphinx and it worked. Im wondering how to add these files to default files. i.e i want to add the new words .dict and .lm files to /edu/cmu/sphinx/models/en-us/cmudict-en-us.dict
and /edu/cmu/sphinx/models/en-us/en-us.lm.bin
Im not sure, if this is feasible and im wondering how to combine dictionaries into single one. I found this link but not sure how to achieve the same.
When i use the TranscriberDemo.java my wav file has different words and the output prints different. how to improve the accuracy ?