readme.1st

何家龙的说话人识别工具包

This package contains a set of speaker recogntion research tools,
they can also be used as general classifiers. Roughtly speaking,
the utilities can be divided into the following categories:

A. feature extraction and dimensional reduction programs

(1) cepstrum
(2) search
(3) randline
(4) bin2asc


B. MLP network training and test programs

(1) mlptrain
(2) mlptest

C. VQ codebook training and test programs

(1) lbglvq
(2) nearest

D. Gaussian mixture model (GMM) training and test programs

(1) gmmtrain
(2) gmmtest

---------------------------------------------------------------------
Copyright (c) 1996 by Jialong He.   All Rights Reserved.

THE SOFTWARE IS PROVIDED "AS IS" AND JIALONG HE DISCLAIMS ALL
WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS.  IN NO EVENT SHALL JIALONG
HE BE LIABLE FOR ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL
DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR
PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS
ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF
THIS SOFTWARE.
------------------------------------------------------------------------

Jialong He
Abteilung Neuroinformatik
University of ULM
89069 ULM, GERMANY
email: [e-mail]

April 9, 1996