Labview for Vocal Processing

[John Starrett]

Does anyone here have experience using Labview for vocal processing? I
am beginning a project that requires real-time extraction of vocal
formants (Fourier modes) and it would be nice to have Labview do this.

I have used Labview a little on a previous project and I am pretty sure
it *can* be done, but I am hoping to find someone who has already done
this or something like it to get a few pointers.

--
John Starrett



-----= Posted via Newsfeeds.Com, Uncensored Usenet News =-----
http://www.newsfeeds.com - The #1 Newsgroup Service in the World!
-----== Over 100,000 Newsgroups - 19 Different Servers! =-----

[gazoo]

John,

It is definitely possible to do formant analysis in LabVIEW; my knowledge on formant analysis is very basic, but here is a VI to get you started. j

Here is a small description:

1. 
   Opens the included wav file (just a vowel from a voice recording).
2. 
   Send the data to the find single tone vi to get the main tone in the signal.
3. 
   The Single tone vi exports the original signal minus the tone and we pass this again to the analysis.
4. 
   The resulting arrays of Frequencies, amplitudes and phases are then used to generate the vowel again.
5. 
   The second for loop generate all the tones with the specs extracted from the original signal and adds them all up.
6. 
   Then we obtain the power spectrum of the original and the generated
   data and compare them.
   
   

   
   The white plots represent the original recorded signal and the red plots represent the generated signal.
   
   To run the exampl just open the "Format Excercise.vi" select the number of tones to extract, select the wav file and run the vi.
   
   This example does not uses any toolkit, however you may want to look into the Sound and Vibration Toolset (octave analysis, zoom FFT, weighting filters, etc.) or the Order Analysis Toolset.
   
   I hope this helps.
   
   Regards,
   
   Juan Carlos
   N.I.