Anonymous - 2003-01-02

Hi,

I am a beginner, so pardon me if this has been discussed here umpteen times. I will be glad to be directed to appropriate threads or sites.

I want to implement a forced phoneme alignment system using Sphinx. I have audio (English text)and the corresponding text. All I want is the timing for the phonemes.

I don't understand how to begin. Will I need to train models, or I can use the ones that exist.

Thanks a lot

UP