Arabic-L:LING:Query on Spoken Arabic Corpus tools

[Dilworth Parkinson]

------------------------------------------------------------------------
Arabic-L: Fri 19 Sep 2013
Moderator: Dilworth Parkinson <dilworth_parkinson at byu.edu>
[To post messages to the list, send them to arabic-l at byu.edu]
[To unsubscribe, send message from same address you subscribed from to
listserv at byu.edu with first line reading:
           unsubscribe arabic-l                                      ]

-------------------------Directory------------------------------------

1) Subject: Query on Spoken Arabic Corpus tools

-------------------------Messages-----------------------------------
1)
Date: 19 Sep 2013
From:  David Wilmsen <david.wilmsen at gmail.com>
Subject: Query on Spoken Arabic Corpus tools

I see we have a great many tools (or at least some) with which to construct
(or attempt to construct) corpora of written Arabic.

I have a query involving what I think would involve corpora of much greater
complexity:

Does anyone know of or is anyone working on programs that can handle spoken
Arabic corpora?

By now, thousands - maybe hundreds of thousands - of hours of spoken
language data are available in the form of Arab serials, archived on many
web sites, including those of the channels that originally broadcast them.
This is to say nothing of the unscripted spoken language available on sites
such as Utube.

Some researchers (including myself) are already utilizing language-use data
gleaned from Arabic-language serials. Imagine the potential for being able
to search and compare thousands of instances of usage of whatever word or
construct is under investigation.

I think I'm too old to begin trying to learn how to construct software that
might be able to handle such a task. Is there anyone in our younger
generation of scholars with the know-how to approach it?


David Wilmsen
Associate Professor of Arabic
Chair, Department of Arabic and Near Eastern Languages
American University of Beirut
Bliss Street, Hamra
Beirut, Lebanon
1107 2020
tel:  +961-1-350000 ext. 3850/1

--------------------------------------------------------------------------
End of Arabic-L: 19 Sep 2013
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listserv.linguistlist.org/pipermail/arabic-l/attachments/20130919/6745bd59/attachment.htm>