I am new to Sphinx, I have taken up a course project Speech to text recognition and I am using Sphinx4.
Problem defination is as follows: The program should be able to convert continuous human speech without any other spoken language training samples for each individual.
I have installed Sphinx and ran demo files and I am going through documentation.
Can you please let me know where to start for the project?
Thanks in advance
Gurucharan
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi,
1> I downloaded JAR file of evalDictator. When i ran it, a window opens it has "Clear Text" and "Donate Voice" buttons and shows "Loading Recognizer" on text pane which never clears. If I speak nothing shows up on the text pane. Is this right way to run evalDictator?
2> I extracted JAR file and imported it to Eclipse. But, I didnt find info regarding how to run it.
Please let me know what to do in both cases.
Thanks for the help.
Gurucharan
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Also, if you read the instructions on the site , it says you need to hold the mouse on the text pane while you talk and release when your done talking.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hi All,
I am new to Sphinx, I have taken up a course project Speech to text recognition and I am using Sphinx4.
Problem defination is as follows: The program should be able to convert continuous human speech without any other spoken language training samples for each individual.
I have installed Sphinx and ran demo files and I am going through documentation.
Can you please let me know where to start for the project?
Thanks in advance
Gurucharan
Thanks for your reply. I will look into EvalDictator.
Thanks,
Gurucharan
Hi,
1> I downloaded JAR file of evalDictator. When i ran it, a window opens it has "Clear Text" and "Donate Voice" buttons and shows "Loading Recognizer" on text pane which never clears. If I speak nothing shows up on the text pane. Is this right way to run evalDictator?
2> I extracted JAR file and imported it to Eclipse. But, I didnt find info regarding how to run it.
Please let me know what to do in both cases.
Thanks for the help.
Gurucharan
Get the latest source via the svn.
Also, if you read the instructions on the site , it says you need to hold the mouse on the text pane while you talk and release when your done talking.
WEll, not going to do your homework assignment for you =)
You want to look into evaldictator. It is the closest thing sphinx has to dictation.
http://www.speech.cs.cmu.edu/sphinx/dictator/
It works out of the box, follow the steps there to install it. The results arent great but it works.
There are things you could do to increase the accuracy like switching to voxforge.org acoustic model but the above should work at least sort of =).