[Corpora-List] Speech recognition/Persian

[Damon Davison]

Hi Amanda,

Your colleague might be interested in the Farsdat database:

http://www.elda.fr/cata/speech/S0112.html

"The Farsi Speech Database Farsdat comprises the recordings of
300 Persian speakers, who differ from each other with regards to
age, sex, education level, and dialect (10 dialect regions of
Iran were represented: Tehrani, Torki, Esfahani, Jonubi,
Shomali, Khorassani, Baluchi, Kordi, Lori, and Yazdi). Each
speaker uttered 20 sentences in two sessions, and 100 of these
speakers uttered 110 isolated words. 6000 utterances were
segmented and labelled phonetically and phonemically manually,
including 386 phonetically balanced sentences, using IPA
characters. The acoustic signal has been stored with a Wave file
standard, so that it can be used by any other application
software. The used sampling frequency reaches 22.5 KHz, and the
signal-to-noise ratio 34 dB. The ambiguities in segmentation
have been solved by reference to the corresponding spectrograms
extracted from DSP sona-Graph KAY 5500."

In addition, Karine Megerdoomian maintains a site:
http://lexicon.arizona.edu/~iranian/
It deals exclusively with Iranian linguistics.  You might also
send her a note in case she does not read this list;
http://members.cox.net/karinem/

There is an abstarct for a dissertation there that may produce
further leads:
http://lexicon.arizona.edu/~iranian/testabs/abs105.html

Kind regards,

Damon






On Monday 28 April 2003 21:38, Amanda Stent wrote:
> One of my colleagues would like me to inquire if there are any
> active speech recognition projects involving Persian, and/or
> any collections of Persian speech data suitable for such
> research.  He is particularly interested in
> speaker-independent, small vocabulary SR in Persian. If you
> would like, you may reply directly to me.  I will forward your
> replies to my colleague and produce a summary for the whole
> list in a week or so.
>
> Thanks!
>
> Amanda Stent

--

Damon Allen Davison
davison at uni-koeln.de

"A UNIX life is hard."