0

I want to create a model to recognize Arabic Letters. I know how to create the language model and the dictionary files, but I am stuck at the acoustic model. I record wav files for each letter, but during the training, it says that the training hours are too small although the training continues. When I try to use it, the model doesn't recognize anything(giving null).

I want to know how should I record the wav files, should I keep repeating, for example, the letter Alif like 100 times in one wav file or should I just record multiple wav files of the same letter.

Your help is highly appreciated.

coding4fun
  • 3,485
  • 1
  • 16
  • 28

1 Answers1

1

I want to know how should I record the wav files, should I keep repeating, for example, the letter Alif like 100 times in one wav file or should I just record multiple wav files of the same letter.

It's better to have multiple files with continuos words, not with letters. Letters are hard to recognize.

When I try to use it, the model doesn't recognize anything(giving null).

There might be different issues here (wrong audio format, etc). You can share your database on CMUSphinx forums with dropbox to get help on this issue.

Nikolay Shmyrev
  • 24,897
  • 5
  • 43
  • 87
  • But my application is to recognize letters and if I use your suggestion then there's no way i can recognize letters since I'll be using words instead of letters in the language model. So how should my model look like? – coding4fun Oct 06 '14 at 09:59
  • Redesign your application to recognize words instead of letters. Letters are pretty hard to recognize with current state of technology. For example for English RADIO alphabet is used instead of letters "ALPHA, BRAVO, CHARLIE, DELTA ...." – Nikolay Shmyrev Oct 06 '14 at 10:02