| Author |
Message |
khanna
Joined: 13 Sep 2003
Posts: 9
|
 09 Mar 2004 8:05 voice recognition using MATLAB?? |
|
|
|
is it possible to seperate different voice signals based on quality(timbre) using MATLAB
thanx in advance
|
|
| Back to top |
|
 |
spauls
Joined: 17 Dec 2002
Posts: 547
Helped: 19
|
| 29 Mar 2004 17:07 Re: voice recognition using MATLAB?? |
|
|
|
| U can use sppech proessing S/w , It is basially demodulation using different sampling rates.
|
|
| Back to top |
|
|
mami_hacky
Joined: 28 Mar 2002
Posts: 679
Helped: 4
Location: Some where
|
| 29 Mar 2004 18:17 voice recognition using MATLAB?? |
|
|
|
| I do not understand exactly what you want. would you please describe more. What do you want to recognize? words? consonant , vowels? continous speech? or just voice, such as the sound of a door, or sound of a breaking window? For each of the above situations, there is a solution using matlab. Example: want to detect, the breaking window sound ( A thief detector ) then matlab's wavelet toolbox can be used greatly. I addition you may want to use Matlab's neural network toolbox, to develope some simple nets for recognizing special sounds. Want to use HMM, for word recognition or Vowel consonant classification? then you can find one good library of HMM related fucntions for matlab using a simple search in google. I do not remember the name now, But I'm sure it is available. Now, please indicate your application exactly. thanks.
|
|
| Back to top |
|
|
panda
Joined: 29 Jan 2004
Posts: 41
|
| 30 Mar 2004 17:15 voice recognition using MATLAB?? |
|
|
|
| possible, i saw this kind of project using matlab and also c++
|
|
| Back to top |
|
|
GS74
Joined: 22 Apr 2004
Posts: 2
|
| 22 Apr 2004 22:37 Re: voice recognition using MATLAB?? |
|
|
|
Be more specific describing your problem.
Voice recognition and voice separation are very different problems.
In the last case, you could use the ICA (Independent Component Analysis) approach. There is a free matlab-based toolbox called FastICA. You can find it in google. With this technique you will need as many signals as sources (at least).
Another techniques are BSS (blind source separation) and BSD (blind source deconvolution), which is necesary when the voices are recorded in a room with high reverberation.
Good luck.
|
|
| Back to top |
|
|
haerifar
Joined: 02 Feb 2004
Posts: 113
Helped: 1
Location: Iran - Tehran
|
| 26 May 2004 6:31 voice recognition using MATLAB?? |
|
|
|
does anyone have some code about this tupic?
i need it too
|
|
| Back to top |
|
|
