I am having a problem with the demos only recognizing once or twice. For example when I run the Hello world demo and say "Hello Paul" it works fine. I get a second prompt telling me what to say. I than say something like "Hello Rita" and nothing happens. I keep trying using various combinations of Hello and the persons' name but nothing. I than tried using the live test mode and the same thing happens. It recognizes the first sentence/phrase I say and nothing else. I am using a Windows 2000 machine running Sphinx 4 with a wireless microphone. I suspect that it is the microphone or sound card. The reason I suspect the microphone is due to the fact that on my home PC running Windows XP with a regular headset microphone I do not get this same problem. I have also noticed others posting a similar problem on Linux machines. I need a way to determine the cause of this so that I can tell my project manager .
I appologize if this has already been answered and could somebody point me to the link.
Thanks for any help
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I had the same (or similar) problem. I never was able to resolve it, and finally gave up. Did you get any help with this issue yet? BTW, I was running under XP Pro, using cygwin.
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I realized the problem was the receiver. After hours of trying everything I could think of I decided to turn the volume switch on the receiver up to max. That was the problem. On other speech recognition engines such as via voice we had to keep the volume nob on the receiver low but sphinx it needed to be cranked all the way up. Wasted 2 hours of my live on this when there was such a simple solution.
Hope this helps
If you would like to refer to this comment somewhere else in this project, copy and paste the following link:
I am having a problem with the demos only recognizing once or twice. For example when I run the Hello world demo and say "Hello Paul" it works fine. I get a second prompt telling me what to say. I than say something like "Hello Rita" and nothing happens. I keep trying using various combinations of Hello and the persons' name but nothing. I than tried using the live test mode and the same thing happens. It recognizes the first sentence/phrase I say and nothing else. I am using a Windows 2000 machine running Sphinx 4 with a wireless microphone. I suspect that it is the microphone or sound card. The reason I suspect the microphone is due to the fact that on my home PC running Windows XP with a regular headset microphone I do not get this same problem. I have also noticed others posting a similar problem on Linux machines. I need a way to determine the cause of this so that I can tell my project manager .
I appologize if this has already been answered and could somebody point me to the link.
Thanks for any help
I had the same (or similar) problem. I never was able to resolve it, and finally gave up. Did you get any help with this issue yet? BTW, I was running under XP Pro, using cygwin.
I realized the problem was the receiver. After hours of trying everything I could think of I decided to turn the volume switch on the receiver up to max. That was the problem. On other speech recognition engines such as via voice we had to keep the volume nob on the receiver low but sphinx it needed to be cranked all the way up. Wasted 2 hours of my live on this when there was such a simple solution.
Hope this helps