Dear
Readers,
It's
hard to believe its March already. While this month
officially brings us spring, those of us here in the
Midwest won't have any high expectations for better
weather conditions until at least the end of April!
In any case, this March is an exciting month for the
VoiceXML community, as it marks the two-year anniversary
of the formation of the VoiceXML Forum. It's amazing
how quickly the technology has taken hold during these
two years. From the four original founding members in
1999, there are now over 420 organizations that have
joined the Forum at the various membership levels and
are involved in VoiceXML technology in one way or another.
The
feature articles in this month's issue of the VoiceXML
Review focus on speech technology--the stuff that makes
VoiceXML possible. Kimberlee Kemble gets us started
with her article entitled An
Introduction to Speech Recognition. Kimberlee's
article provides a thorough introduction to speech recognition
by introducing the basic terminology and concepts, and
a broad sketch of how it all works.
Juergen
Schroeter brings us up-to-date on the very latest in
text-to-speech (TTS) technology in his article
The Fundamentals
of Text-to-Speech Synthesis. The article begins
with overview of the various methods used traditionally
to synthesize intelligible speech from textual input,
and then focuses on how more recently the concatenative
approach is delivering more natural sounding results.
Concatenative TTS systems exploit advances in processing
power, information storage and retrieval, and automatic
labeling techniques to produce speech that is both intelligible
and natural sounding. This article will give you an
appreciation for the complexity of modern TTS technology,
as well as insight into what the possibilities are moving
forward.
As
I mentioned last month, the VoiceXML Forum is holding
its first annual Users Group Meeting in conjunction
with the AVIOS 2001 Conference on April 5, 2001 in San
Jose, Calif. If you haven't yet decided whether to attend,
read Greg Kohn's feature An
Inside Look at the VoiceXML Forum Users Group Meeting
for an explanation of why you should attend! In addition,
the final agenda and on-line registration instructions
have been posted at http://www.voicexml.org/users_group.html.
In
this month's Speak
& Listen column, Jeff Kunins finally got that
batch of questions he's been patiently waiting for you
to send him! This month Jeff answers your questions
on how to go about evaluating the performance of a VoiceXML
interpreter--a critical question if you are looking
to deploy a high-density VoiceXML application. Jeff
also gives us a few pointers regarding the "multi-modal"
question we seem to be hearing more and more about these
days. Thanks for sending in your questions last month.
If you have additional questions you'd like addressed
in this column, send them to speak.and.listen@voicexmlreview.org.
Are
you ready to write a real VoiceXML application? In this
month's First
Words column, Rob Marchand addresses the topic of
building large applications in VoiceXML. Rob identifies
constructs in the VoiceXML language that facilitate
the implementation of large applications. He also gives
some excellent guidelines on how to partition application
functionality between client and server.
Finally,
some of you may not have noticed the "feedback"
mailto link on the VoiceXML Review homepage. The members
of the VoiceXML Forum's Publication board would really
appreciate some feedback on what you think of the new
e-zine. Please send your comments along to editor@voicexmlreview.org.
Sincerely,
Jonathan
Engelsma
Editor-in-Chief, VoiceXML Review
Jonathan.Engelsma@voicexmlreview.org
back
to the top
Copyright
© 2000 - 2004 VoiceXML Forum. All rights reserved.
The VoiceXML Forum is a program of the
IEEE Industry Standards
and Technology Organization (IEEE-ISTO).
|