View Single Post
Posts: 752 | Thanked: 2,808 times | Joined on Jan 2011 @ Czech Republic
#74
Originally Posted by taixzo View Post
That's more or less how I imagined writing a text. However, three things in that that I am still trying to figure out:
  1. Pocketsphinx uses a pre-trained grammatical model. This model apparently assigns a very low probability to multiple numbers being used in sequence, so it never seems to recognize a phone number. Even saying ten of the most distinctively pronounced number (seven), it only recognized four sevens. This is something I need to work on with the voice model, but have been putting off until I have enough time to recompile the model (maybe Sunday).
  2. Also, Pocketsphinx is not very good with names. This could possibly be alleviated by running a phoneme search on all contacts once it's determined to be not a number.
  3. If the user is dictating a text, there needs to be some way to edit what they said. Ideally, this would also train the voice model. This is definately possible, but I need to learn more about pocketsphinx first.


I'm working on it.
I see. I plan to look into creating custom language models after my upcoming exams. I have found some tutorials on Voxforge and if it is not beyond my capabilities, I could then make a 'translation' of your app to my language (AFAIK there ain't any publicly available language models for Czech yet). Do you think it would be useful to include some kind of GUI to choose your own model as part of settings to your app?
 

The Following 2 Users Say Thank You to nodevel For This Useful Post: