Technical report is available

NHATAOKA%vax1.tcd.ie@cunyvm.cuny.edu NHATAOKA%vax1.tcd.ie at cunyvm.cuny.edu
Thu Dec 21 13:38:00 EST 1989


The following technical report is available.
Unfortunately, I want to post this on this connectionists_mailing
list only, so "Please don't forward to other newsgroups or mailing lists."



                 Speaker-Independent Phoneme Recognition
                   on TIMIT Database  Using Integrated
                   Time-Delay Neural Networks (TDNNs)

                   Nobuo Hataoka(*) and Alex H. Waibel

                          November 27, 1989
                            CMU-CS -89-190
                     (also, CMU-CMT-89-115)

                      School of Computer Science
                      Carnegie Mellon University
                         Pittsburgh, PA 15213


Abstract:

This paper describes a new structure of Neural Networks (NNs) for speaker-
independent and context-independent phoneme recognition. This structure is
based on the integration of Time-Delay Neural Networks(TDNN, Waibel et al.)
which have several TDNNs separated according to the duration of phonemes.
As a result, the proposed structure has the advantage that it deals with
phonemes of varying duration more effectively.
   In the experimental evaluation of the proposed new structure, 16-English
vowel recognition was performed using 5268 vowel tokens picked from 480
sentences  spoken  by  140 speakers (98 males and 42 females) on the TIMIT
(TI-MIT) database.  The number of training tokens and testing tokens was
4326 from 100 speakers (69 males and 31 females) and 942 from 40 speakers
(29 males and 11 females), respectively. The result was a 60.5% recognition
rate (around 70% for a collapsed 13-vowel case), which was improved from
56% in the single TDNN structure, showing the effectiveness of the proposed
new structure to use temporal information.

(*) The author was a visiting researcher  from Central Research Laboratory,
    Hitachi, Ltd., Japan.   This work  has  been  done  on a collaborative
    research project between the Center for Machine Translation of CMU and
    Hitachi, Ltd.   Currently,  the author is working  for  Hitachi Dublin
    Laboratory in Trinity College, Ireland.

---------------------------------------------------

If you want to have a copy of this report, please send an e-mail or
a letter to the following address.

         nhataoka%vax1.tcd.ie at cunyvm.cuny.edu
       or            ^--(one)
         Alison Dunne
         Hitachi Dublin Laboratory
         O'Reilly Institute
         Trinity College
         Dublin 2, Ireland


P.S. Do not use your mailer's "reply" command.


More information about the Connectionists mailing list