I would like to add my own words to the vocabulary, but am constrained by the lack of phonetic representation of these words. I am working with American English, and will be using the standard 39/40 phoneme-set of CMU Dictoinary (0.7a).
Any pointers/suggestions on getting started would be most useful.
cheers,
Sunny
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Thanks for the quick reply Nickolay and the CMU Dict test-set you put together.
I am in the process of installing swig, but running into installation issues in cygwin.
Once this is done, I'll be able to start using g2p.
Shall keep you posted...
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I would like to add my own words to the vocabulary, but am constrained by the lack of phonetic representation of these words. I am working with American English, and will be using the standard 39/40 phoneme-set of CMU Dictoinary (0.7a).
Any pointers/suggestions on getting started would be most useful.
cheers,
Sunny
Thanks for the quick reply Nickolay and the CMU Dict test-set you put together.
I am in the process of installing swig, but running into installation issues in cygwin.
Once this is done, I'll be able to start using g2p.
Shall keep you posted...
You can use sequitur-g2p to generate missing pronuncations. The model for cmudict is available.
http://www-i6.informatik.rwth-aachen.de/web/Software/g2p.html
http://www.mediafire.com/download.php?ijmnprkz9nm