I am interested in building a speech transcription system. Transcription does not need to occur in real time since input would be from a recording.
I have installed Sphinx2 and I am able to use the test scripts.
I can't figure out, though, how to enable Sphinx to recognize more words. I know that I need a dictionary and there are several available, but I can't seem to figure out which one would be appropriate.
Are there other things that I need, too?
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
You should monitor or join the Open Source Speech Recognition Initiative listserve (OSSRI). In a group we are planning to do that, but perhaps using Sphinx perhaps another of the engines.
Susan Cragin http://harvee.org/mailman/listinfo/ossri
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I am interested in building a speech transcription system. Transcription does not need to occur in real time since input would be from a recording.
I have installed Sphinx2 and I am able to use the test scripts.
I can't figure out, though, how to enable Sphinx to recognize more words. I know that I need a dictionary and there are several available, but I can't seem to figure out which one would be appropriate.
Are there other things that I need, too?
You need a dictionary and a language model.
There is information here about building a language model:
http://www.speech.cs.cmu.edu/sphinx/
There are some LMs and dictionaries at
http://xvoice.sourceforge.net/xvoice-sphinx/
You should monitor or join the Open Source Speech Recognition Initiative listserve (OSSRI). In a group we are planning to do that, but perhaps using Sphinx perhaps another of the engines.
Susan Cragin
http://harvee.org/mailman/listinfo/ossri