Please excuse me for my ignorance. I am an avid user of voice command and have been for over a year using In3. When I stumbled on to this board, my jaw dropped, and I was elated! I am a Linux newbie and unfortunately will most likely be shackled to Windows for longer than I care to be.
My questions is, where do I start? Am I even in the right place? I have installed Mandrake and just downloaded Debian. Am I on the right track? Is there a prefered OS distribution for voice command? Is there a Windows application? I would love to do what I can for the cause, and bring others to the Open Source Community. I have much to learn, and I am not asking to be spoon fed, I just need to be pointed in the right direction.
I am sorry if I am "out of place".
TIA,
Sam
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Somewhat off-topic.
hello and welcome, newbie.
CMU Sphinx is a good starting point but is problematic. A group of developers has gotten together to create a full-service speech recognition engine with command and control functionality, much like you are probably used to with Windows, ViaVoice or Dragon NaturallySpeaking.
you may wish to monitor our list, at least in digest form. The name is Open-Source Speech Recognition Initiative, or OSSRI for short. Just enter it in Google and you will be directed to our listserv and probably to our newsletter, VoxPopulin, which contains only the transcripts of our first two Board of Directors meetings.
In a couple of weeks we will also have a web site -- probably www.OSSRI.org.
We may be working off the CMU sphinx engine. Other possibilities are the engine developed by the Julius Project in Japan, University of Kyoto, or the engines developed by the University of Colorado or Mississippi State University.
It is an exciting time for us. Even though the list won't answer any or many technical questions now, (because we don't have our own product yet) at some point in the future it will be a valuable resource for everyone who wants a good continuous speech recognition engine running on Linux.
Susan Cragin
susancragin@earthlink.net
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
Hello,
Please excuse me for my ignorance. I am an avid user of voice command and have been for over a year using In3. When I stumbled on to this board, my jaw dropped, and I was elated! I am a Linux newbie and unfortunately will most likely be shackled to Windows for longer than I care to be.
My questions is, where do I start? Am I even in the right place? I have installed Mandrake and just downloaded Debian. Am I on the right track? Is there a prefered OS distribution for voice command? Is there a Windows application? I would love to do what I can for the cause, and bring others to the Open Source Community. I have much to learn, and I am not asking to be spoon fed, I just need to be pointed in the right direction.
I am sorry if I am "out of place".
TIA,
Sam
Somewhat off-topic.
hello and welcome, newbie.
CMU Sphinx is a good starting point but is problematic. A group of developers has gotten together to create a full-service speech recognition engine with command and control functionality, much like you are probably used to with Windows, ViaVoice or Dragon NaturallySpeaking.
you may wish to monitor our list, at least in digest form. The name is Open-Source Speech Recognition Initiative, or OSSRI for short. Just enter it in Google and you will be directed to our listserv and probably to our newsletter, VoxPopulin, which contains only the transcripts of our first two Board of Directors meetings.
In a couple of weeks we will also have a web site -- probably www.OSSRI.org.
We may be working off the CMU sphinx engine. Other possibilities are the engine developed by the Julius Project in Japan, University of Kyoto, or the engines developed by the University of Colorado or Mississippi State University.
It is an exciting time for us. Even though the list won't answer any or many technical questions now, (because we don't have our own product yet) at some point in the future it will be a valuable resource for everyone who wants a good continuous speech recognition engine running on Linux.
Susan Cragin
susancragin@earthlink.net