Hi Folks,
I'm interested in looking (in a beginner's amateurish way)
at prosodic/phonetic analysis of recorded speech.
In particular I would want to use R to formulate and
evaluate specific models.
So I would like to ask R people for their recommendations
for a program which would
a) Take as input a sound file in one of the common formats
(".wav", ".au")
b) perform at least basic phonetic analysis (formants, F0,
spectrograms, ... )
b) Save to file a representation of the basic phonetic
analysis which it has done, in a form which R can readily
import and use.
I've come across 'praat':
http://www.praat.org
which seems to offer a spohisticated range of analyses, though
it's not too clear from the above URL what can be saved and
in what format.
I'd be grateful for any comments on using 'praat' with R,
and/or for any suggestions for other software with commments.
I only want to hear about software which (like 'praat') is
GPL or similar.
Thanks,
Ted.
--------------------------------------------------------------------
E-Mail: (Ted Harding) <Ted.Harding at nessie.mcc.ac.uk>
Fax-to-email: +44 (0)870 094 0861 [NB: New number!]
Date: 26-Dec-04 Time: 10:31:14
------------------------------ XFMail ------------------------------
(Ted Harding) wrote:> Hi Folks, > > I'm interested in looking (in a beginner's amateurish way) > at prosodic/phonetic analysis of recorded speech. > > In particular I would want to use R to formulate and > evaluate specific models. > > So I would like to ask R people for their recommendations > for a program which would > > a) Take as input a sound file in one of the common formats > (".wav", ".au")Ted, see package tuneR for reading Wave files.> b) perform at least basic phonetic analysis (formants, F0, > spectrograms, ... )For F0 and spectograms see also tuneR. "Formants" is a bit more tricky. We tried some analyses, but since the definition of a formant is still not completly clear to me, we haven't provided anything for formants in the package yet. Do you know some good literature that gives a somwhat precise definition? At least musicias only talk about something like "raised" areas in the periodogram, which is not very helpful given the missing definition of "raised". Uwe> b) Save to file a representation of the basic phonetic > analysis which it has done, in a form which R can readily > import and use. > > I've come across 'praat': > > http://www.praat.org > > which seems to offer a spohisticated range of analyses, though > it's not too clear from the above URL what can be saved and > in what format. > > I'd be grateful for any comments on using 'praat' with R, > and/or for any suggestions for other software with commments. > I only want to hear about software which (like 'praat') is > GPL or similar. > > Thanks, > Ted. > > > -------------------------------------------------------------------- > E-Mail: (Ted Harding) <Ted.Harding at nessie.mcc.ac.uk> > Fax-to-email: +44 (0)870 094 0861 [NB: New number!] > Date: 26-Dec-04 Time: 10:31:14 > ------------------------------ XFMail ------------------------------ > > ______________________________________________ > R-help at stat.math.ethz.ch mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
You might want to look at EMU: http://emu.sourceforge.net/ Praat has a scripting language associated with it, their web page describes it, and others have tutorials on Praat scripting (just search on Google). People I know in this area use EMU as well as Praat. From your description of your needs the Praat scripting language is probably the starting point for you. On Sun, 26 Dec 2004 12:20:45 +0100, r-help-request at stat.math.ethz.ch> From: (Ted Harding) <Ted.Harding at nessie.mcc.ac.uk> > Subject: [R] Prosodic/phonetic analysis with R > To: r-help at stat.math.ethz.ch > Message-ID: <XFMail.041226103115.Ted.Harding at nessie.mcc.ac.uk> > Content-Type: text/plain; charset=iso-8859-1 > > Hi Folks, > > I'm interested in looking (in a beginner's amateurish way) > at prosodic/phonetic analysis of recorded speech. > > In particular I would want to use R to formulate and > evaluate specific models. > > So I would like to ask R people for their recommendations > for a program which would > > a) Take as input a sound file in one of the common formats > (".wav", ".au") > > b) perform at least basic phonetic analysis (formants, F0, > spectrograms, ... ) > > b) Save to file a representation of the basic phonetic > analysis which it has done, in a form which R can readily > import and use. > > I've come across 'praat': > > http://www.praat.org > > which seems to offer a spohisticated range of analyses, though > it's not too clear from the above URL what can be saved and > in what format. > > I'd be grateful for any comments on using 'praat' with R, > and/or for any suggestions for other software with commments. > I only want to hear about software which (like 'praat') is > GPL or similar. > > Thanks, > Ted. > > -------------------------------------------------------------------- > E-Mail: (Ted Harding) <Ted.Harding at nessie.mcc.ac.uk> > Fax-to-email: +44 (0)870 094 0861 [NB: New number!] > Date: 26-Dec-04 Time: 10:31:14 > ------------------------------ XFMail -------------------------------- Prof. Dr. Shravan Vasishth Tel (direct): +49-(0)331-977-2457 Juniorprofessor: Empirical Methods in Syntax Research Institute for Linguistics, Potsdam University, PO Box 601553 14415 Potsdam, Germany Tel (secretary): -2016; Fax: -2087 http://www.purl.oclc.org/NET/vasishth