[microsound] Speech Analysis Question...

[trommer at sympatico.ca]

there's something (which is free) called praat, which is billed as 'doing phonetics by computer':

 

http://www.fon.hum.uva.nl/praat/
 
> From: hellomynameisphil+mcrsnd at gmail.com
> Date: Wed, 16 Dec 2009 10:29:13 -0800
> To: microsound at microsound.org
> Subject: Re: [microsound] Speech Analysis Question...
> 
> fscape has a utility that can split a sound into chunks of
> user-defined length, analyze and compare the chunks and then arrange
> the chunks according to their similarity in a certain regard, for
> example, amplitude or noisiness. It may not do exactly what you want
> it to do, but still might be useful to try or to generate ideas.
> That's what i can think of off the top of my head.
> 
> ~pt
> 
> 
> On Wed, Dec 16, 2009 at 9:50 AM, Greg Pond <gregpond at gmail.com> wrote:
> > This was posted to the PD list just a few days ago:
> > http://williambrent.conflations.com/mov/timbreID-vowel.mov
> >
> > Pure Data can likely accomplish what you are trying to do. I would
> > check out the examples here: http://puredata.info/docs/tutorials,
> > especially if you have not tried using it or Max/MSP before. The pd
> > list archives and the PD forum may also yield more.
> >
> > best,
> >
> > Greg
> >
> >
> >
> >
> > On Wed, Dec 16, 2009 at 10:53 AM, Timothy Leonido
> > <timothy.leonido at gmail.com> wrote:
> >> Hello,
> >>
> >> I am wondering if anyone can recommend an approach to isolating sounds of
> >> speech, say vowels of a particular quality or certain fricatives. Is there a
> >> program that can take a small section of a waveform and, using this
> >> selection as a model,  extract sounds of a similar quality? Ideally,
> >> reducing the waveform to silence and those selected sounds? (fricatives,
> >> formants of a certain frequency) I am currently looking at Praat and
> >> Supercollider, but if anyone can point me in a better direction...
> >>
> >> In looking for sounds of speech hesitation or disfluency, someone mentioned
> >> that I might be able to use supercollider to extract quieter sounds which
> >> are in proximity to silence... though I'm not sure how this is possible.
> >> thanks!
> >>
> >> tim
> >> _______________________________________________
> >> microsound mailing list
> >> microsound at microsound.org
> >> http://or8.net/mailman/listinfo/microsound
> >>
> >>
> > _______________________________________________
> > microsound mailing list
> > microsound at microsound.org
> > http://or8.net/mailman/listinfo/microsound
> >
> 
> 
> 
> -- 
> "'Experimental' means the seats are full at the start and empty before
> the performance is over."
> 
> ~~~~~~~~~~~~~~~~~~~~~~~~~
> ~ Phil Thomson
> ~ http://philthomson.ca/
> ~~~~~~~~~~~~~~~~~~~~~~~~~
> _______________________________________________
> microsound mailing list
> microsound at microsound.org
> http://or8.net/mailman/listinfo/microsound
 		 	   		  
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://or8.net/pipermail/microsound/attachments/20091216/92d0f207/attachment.html>