--- Forwarded Message from "Thomas Hammond" <[log in to unmask]> ---

>From: "Thomas Hammond" <[log in to unmask]>
>To: "Language Learning and Technology International Information Forum"   
<[log in to unmask]>
>Subject: Automated pronunciation checking
>Date: Thu, 16 Mar 2006 07:47:01 -0500

Has anyone had recent experience with software that uses acoustical modelling to
compare 
learners' pronunciation and intonation with that of a native speaker? I have
seen this 
sort of thing demonstrated in the past and found it both inaccurate (not even
able to 
distinguish NS input from NNS input) and puzzling in terms of the feedback
generated --  
generally some kind of acoustical representation that looks like thermal
satellite 
imagery.

Recently, however, a faculty member urged me to take a fresh look at this,
saying that 
there have been enormous technological advances even in the past year. But all I
can find 
are a couple recent academic papers saying the technology just isn't there yet,
or 
commercial products making fantastic claims (and smelling slightly of snake
oil).

Anyone have recent experiences to share?

-Thom

------------------------------------------
Thomas Hammond, Director
Language Resource Center
Harvard University
Cambridge, MA


***********************************************
LLTI is a service of IALLT, the International Association for
Language Learning, and The Consortium for Language Teaching and
Learning (http://consortium.dartmouth.edu).
Join IALLT at http://iallt.org.
Otmar Foelsche, LLTI-Editor ([log in to unmask])
***********************************************