Re: [Corpora-List] Speech recognition/Persian

From: Damon Davison (davison@uni-koeln.de)
Date: Mon Apr 28 2003 - 22:25:25 MET DST

  • Next message: Steven Krauwer: "[Corpora-List] ESS2003: Language and Speech Technology for Language Learning"

    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@uni-koeln.de

    "A UNIX life is hard."



    This archive was generated by hypermail 2b29 : Mon Apr 28 2003 - 22:25:01 MET DST