New York/New Jersey/Connecticut Resources
Presentations
December 3, 2007:
Unified Communications, “Please…Bumper Sticker it for Me” (.pdf)
John Geise
December 12, 2006:
Speech Service Creation (.pdf)
Bill Scholz, Ph.D.
Speaker Biometrics (.pdf)
Ken Rehor, Ph.D. March 28, 2006:
How
to Create a Compelling Customer Experience (.pdf)
Elaine Cascio, Vice President, Vanguard Communications
Corp
Customer experience is the next competitive
battleground. Good service isn't enough anymore - companies need
to truly differentiate themselves through clear strategy that drives
the customer experience. Many companies don't give much thought to
the importance of having the IVR, contact center, retail locations,
website, kiosks, advertising, written materials and correspondence
match the overall company brand, image and values. We'll look at
ways to create a consistent experience no matter how customers contact
you, some examples of good - and not so good - customer experiences,
and the role speech plays in enhancing the customer experience.
Overcoming
the Difficulties of Names (.ppt)
Murray Spiegel, Ph.D, Director, Speech Applications
Research, Telcordia Technologies
A key feature of useful speech recognition
services is name recognition accuracy - autoattendants, voice dialers
and routing systems all depend on accurate recognition of names.
If recognizers don't predict how names are pronounced with their
full variability - when the pronunciation for Casimir Skrzypczak
is a wild guess, the prediction for Alyssia Chaoui is wrong, or the
location variants for Bogota, Piaget or Quabeck are unknown - unsatisfactory
performance is the result.
Telcordia's name pronunciation package reduces
error rates for many players in the speech market. Developed over
more than 20 years, the software package has unparalleled accuracy
for the millions of names of people, places and businesses found
in the US. We'll describe the research behind its development, and
its flexibility that adapts to any speech engine on the market.
Proceedings
June
3, 2005 (.pdf)
Michael Picheny
Tomorrow
and Tomorrow and Tomorrow - A Shakespearian View of the Status
and Future of Speech Recognition
Keith Bain, Stan Armstrong
Liberated Learning
Julien Ghez and Jerome
Gue
Protitle Live
- ViaScribe for Broadcast Subtitling
Sarah Conrod
Enhancing
Accessibility in Interpretative Talks
Dr. David Nahamoo
Speech Transcription
and Analytics Opportunities
James Glass and Regina Barzilay
Automatic Processing of Spoken and Written Lecture Material
Mike Wald
Personalized Displays
Dimitri Kanevsky, Alex Faisman, Sara Basson
CaptionMeNow
|
|