August 20–23, 2007
New York Marriott Marquis
New York, NY
The Tipping Point and Blink
◗ VUI Design ◗ Call Centers ◗ Tips & Tuning
◗ New Technology ◗ Voice Search ◗ Hosted Services
◗ Applications ◗ Customer Experience ◗ Best Practices
Silver Sponsors: Bronze Sponsors: Media Sponsors:
Organized and produced by
SpeechTEK New York 2007
Welcome to SpeechTEK 2007 Program Advisory Committee
The speech industry is at a tipping point. Speech Jerry Carter, Director of Network Speech
technology companies are consolidating and differentiating Architecture & Standards, Nuance
themselves from each other. How will this affect speech technology Communications, Inc.
consumers? SpeechTEK 2007 is where you can meet the key players Deborah Dahl, Principal, Conversational
in this rapidly changing environment and find out firsthand about Technologies
current products and future directions. Tom Houwing, Director, Voiceandvision
The way we use our phones is at a tipping point. Today Judith Markowitz, J. Markowitz Consultants
we use our telephones, especially mobile phones, as a continuous
Bill Meisel, President, TMA Associates, & Editor,
source of information and a pathway to perform transactions at any
Speech Strategy News
time of day or night—at our convenience. SpeechTEK 2007 is the
best source for expert perspective and in-depth analysis of the Dan Miller, Senior Analyst, Opus Research
changing use of telephones and speech technology and what this Tim Moynihan, Vice President, Global
means to your business. Marketing & Sales Support, Envox Worldwide
Organizations deploying speech technology are also at a Ron Owens, Vice President, Product Strategy,
tipping point. Should you replace touchtone technology with First Data Voice Services
speech recognition? Should you switch to the new IP protocols, or Walter Rolandi, The Voice User Interface
adopt automated call routing and speaker verification technologies? Company, LLC
How will these technologies affect your call center and your K. W. “Bill” Scholz, President & Founder,
customers? Make your own informed decisions based on SpeechTEK NewSpeech, LLC
sessions devoted to these topics. Thomas Schalk, Vice President,
In today’s competitive environment, successful businesses need to Voice Technology, ATX Group, Inc.
understand what opportunities speech technology offers, and more
importantly, how to harness those opportunities. At SpeechTEK 2007,
you’ll hear from real speech consumers who have deployed speech Conference Chairs
to provide better service to their customers and to generate revenue
to improve their bottom line. James A. Larson
We invite you to review the following pages to see the many sessions ,
VP Larson Technical Services
that can help your business grow by using speech technologies. We
look forward to seeing you in New York City at SpeechTEK 2007 Susan L. Hura
August 20–23. Principal, SpeechUsability
Hear these topics and more: Who Should Attend?
◗ Meeting business goals ◗ Hot topics in VUI design ◗ C-level executives
◗ Solving speech application ◗ Enterprise IT decision makers
◗ VUI for VUI designers problems ◗ Telecom IT decision makers
◗ Speech to grow your PLUS SPECIAL TRACKS: ◗ Customer service managers
Advanced Speech ◗ Contact center professionals
◗ Tools and environments Technology Symposium ◗ Speech solutions managers and
◗ Designing the speech ◗ A 2-day track organized by developers
customer experience AVIOS ◗ Marketing executives
◗ Tips and techniques for The Year of Living Virtually: ◗ Voice user interface designers
implementing or fixing Hosted and Managed ◗ Consumer electronics designers
your speech applications Services
◗ A 1-day track organized by ◗ Anyone who wants to learn about
◗ Planning and managing Opus Research deploying speech technology for
successful speech business applications
2 August 20–23, 2007 ◗ New York Marriott Marquis, New York
MALCOLM GLADWELL, Author
The Tipping Point and Blink
The market for speech technology topped the $1 billion mark in 2006, up 100%
Tuesday, August 21
from 2 years ago. As adoption of speech systems increases in all parts of our lives,
9:00 a.m. – 10:00 a.m. from our computers to our cars to customer relationships, it is clear that speech
technology is at the tipping point. Hear from Malcolm Gladwell, who coined this
phrase, about how he sees ideas, behaviors, and patterns moving through a
population in much the same way as an epidemic. He posits that ideas can become
contagious and reach a tipping point, just as a virus reaches critical mass. Learn what
it takes to start a social epidemic and create change and how to push speech
technology, and your businesses, toward the tipping point.
Senior VP of Web/IVR CONVERSATIONS
Customer Service Wednesday, August 22, 9:00 a.m. – 10:00 a.m.
What are they doing? What is on their minds? How did
they come to important decisions about their speech
technology projects? Do their systems work as promised?
Where are the headaches and pitfalls? Listen to this high-
SCOTT ABBOTT powered customer panel and learn what customers of
Program Director of
speech technology systems are thinking and how they
AOL are making their decisions. Find out what is important to
them—and how they are coping with the challenges of
procurement, deployment, and implementation of
speech systems. If you are a customer or thinking about
implementing a speech technology system, you’ll gain
SANJAY NAIR valuable insights and learn best practices. If you are a
Customer Contact Strategy speech vendor, this keynote panel takes you behind the
& Performance scenes into what customers are really thinking and
9:00 a.m. –
10:00 a.m. Welcome & Opening Keynote
Track A Track B Track C
MEETING BUSINESS GOALS VUI FOR VUI DESIGNERS ADVANCED SPEECH
WITH SPEECH TECHNOLOGY SYMPOSIUM
(Organized by AVIOS)
Speech and Self-Service Whose VUI Is It, Anyway? Advances in Speech
10:15 a.m. –
11:15 a.m. Strategy User Versus Business Requirements Recognition Processing
Tony Lorentzen, Nancy Gardener Erin Smith, Eduardo Olvera Veeru Ramaswamy, Fil Aleva
Beyond Usability: How Good Usability Surveys: Advances in Text-to-
11:30 a.m. – Is Your Speech Application? Practical Techniques Speech Processing
Silke Witt-Ehsani, Melanie Polkosky Peter Leppik Daniel Burnett, Patrizio Bergallo
12:30 p.m. – LUNCH – SPONSORED BY VOICE OBJECTS
Success Criteria for the Speech Controlling Prompts for Advances in Natural Lanuage Processing
1:45 p.m. –
2:45 p.m. Customer Experience Maximum Usability Roberto Pieraccini, Jonathan Brown,
Carrie Nelson, Michael Guillet Tom Houwing Krishna Govindarajan
3:00 p.m. – New Business Models for Speech You Be the Expert! Speech & the Speech-to-Speech Translation
4:00 p.m. John Hibel, John Roswech End-to-End Customer Experience Jan Kleindienst, Kirti Vashee
Simulating the Personal Touch Communication Strategies for Voice Search
4:15 p.m. –
5:00 p.m. Tim Moynihan Speech Projects Leo Chiu
Melanie Polkosky, Maria Aretoulaki
5:00 p.m. –
7:00 p.m. WELCOME RECEPTION IN EXHIBIT HALL
9:00 a.m. –
10:00 a.m. Keynote: At the Tipping Point, Malcolm Gladwell
10:00 a.m. –
BREAK IN THE EXHIBIT HALL
Track A Track B Track C
THE YEAR OF LIVING DESIGNING THE SPEECH ADVANCED SPEECH
VIRTUALLY: HOSTED & CUSTOMER EXPERIENCE TECHNOLOGY SYMPOSIUM
(Organized. by Opus Research)
10:45 a.m. –
The Outsourcer’s Perspective Para Continuar en Espanol … New Approaches to Dialog Design
12:00 p.m. Aimee Piercy, Prabha Sundaram Dominique Boucher, Cliff Harlow,
12:00 p.m. –
1:30 p.m. LUNCH BREAK
1:30 p.m. – Contrasting Service Provider Getting the VUI Right When Artificial Intelligence & VUI Design
2:30 p.m. Approaches Recognition Goes Wrong Mahesh Rajagopalan, and Jacek Jarmulak,
John Hibel, Mark Wilbur, Ron Owens Kristie Goss, Daniel Padgett Peter Trompetter
2:45 p.m. –
Meeting Business Challenges Making It Personal Advances in Video & Multimedia
Tim Moynihan, Steven Pollack Barb Mackraz, Cory Wright Application Design
Valentine Matula, Jan Sedivy
3:45 p.m. –
4:15 p.m. BREAK IN THE EXHIBIT HALL
4:15 p.m. – View of the Global Future Watch Your Grammar Speech-to-Text Transcription
Juan Ceballos, Mark Plakias Judi Halperin, David Thomson Michael Picheny, Marie Meteer
5:30 p.m. –
9:00 a.m. –
Keynote: Customer Conversations
10:00 a.m. – BREAK IN THE EXHIBIT HALL
Track A Track B Track C
PLANNING & MANAGING THE V-FILES: HOT TOPICS IN NOW READY FOR
SUCCESSFUL SPEECH VUI DESIGN PRIME TIME!
10:30 a.m. – Mainstream Speech? Stakeholder Retire the Horse & Buggy Natural Language Processing
11:30 a.m. Views from 360 Degrees Phillip Hunter Aaron Fisher, Marko Petroni
Tim Pearce, Mike Bergelson
11:45 a.m. – Positioning Speech Applications Special Cases in VUI Design Who’s Really Calling:
12:45 p.m. for Success David Martin, Vasuveda Akula Speaker Authentication
Oren Hertz, Nava Shaked, Caroline Leathem Brian Rowland, Melinda Charlesworth
12:45 p.m. –
2:00 p.m. LUNCH BREAK – EXHIBIT HALL CLOSES AT 2:00 p.m.
The Future of Speech Whither VUI Standards? Using Multimodal Technology to
2:00 p.m. –
3:00 p.m. Scott McGlashan, Moshe Yudkowsky, Phil Shinn, Fran McTernan Improve Language Skills
Mark Rayburn David Topolewski, Deborah Dahl
3:15 p.m. – Top 25 Speech Project “Gotchas” The Ultimate VUI Showdown Video & Speech
4:15 p.m. Ron Owens Greg Simsar Andrew Fulle, Rob Marchand
4 August 20–23, 2007 ◗ New York Marriott Marquis, New York
Monday, August 20 Thursday, August 23
Track D Track E SpeechTEK
SPEECH TO GROW TOOLS & ENVIRONMENTS
YOUR BUSINESS University
If you are considering deploying
Speech in the Mainstream Open Source Development a speech application or looking
Bill Meisel, Daniel Hong Environments to increase your knowledgebase,
Phil Shinn, Ken Osowski
Using Analytics to Understand Windows Vista Development
be sure to attend a SpeechTEK
Your Customer Environment University course. SpeechTEK
Scott Witter Michael Dunn, Fabrizo Giacomelli University courses are in-depth,
focused, 3-hour seminars on
Speech to Generate Revenue New Language Specifications
topics of special interest to speech
& Decrease Costs James Barnett, David Thomson technology and information
Mike Uhlenkamp, Dottie Verkade technology professionals. Taught
Speech Enables Self-Service Which Tools Are Right for You? by experienced instructors, STK
Richard Grant, Chester Anderson John Fuentes, Moshe Yudkowsky University courses offer a structured
Kostas Darivakis, Alexandros Papanikolaou
Speech Drives CRM Techniques for Reusability
learning experience. These are
Brian Gebert, Jangwoo Shin Jerry Carter, Rob Marchand, Ken Rehor separately priced or may be
purchased as part of your
conference registration. See pages
16 – 17 for detailed course
Tuesday, August 21 information.
THURSDAY, AUGUST 23
9:00 a.m. – 12:00 p.m.
Track D Track E
INNOVATIVE SPEECH TIPS & TECHNIQUES FOR STKU-1
APPLICATIONS IMPLEMENTING YOUR Effective Application Design
SPEECH APPLICATIONS Patterns Using VoiceXML &
Scott McGlashan & Ian Sutherland
Speech Applications for Speech Synthesizers on Steroids
Emergencies Davide Bonardo, Quiang Bai STKU-2
Howard Wood, Klaus Schaefer
Synthetic Agents that Speak Tips & Techniques for Using Moshe Yudkowsky
& Listen Grammars
Matt Nickerson, Antonio Gentile Sunil Issar, Padma Ramesh, Krishnan Srinivasan
Speech in Banking Web Services & Speech
Stephan Schneider, Marc Seltier Michael Codini, Chris Passaretti Processing
Touch to Voice Deploying Speech Applications User-Focused VUI Design
Ava J. Baker, R. J. Fox Bob Cooper, R. J. Auburn
Susan L. Hura
THURSDAY, AUGUST 23
1:30 – 4:30 p.m.
Wednesday, August 22 STKU-5
Applications with SCXML
Track D Track E R. J. Auburn
SOLVING SPEECH TIPS & TECHNIQUES FOR STKU-6
APPLICATION PROBLEMS FIXING YOUR SPEECH Developing Applications
APPLICATIONS Using System.Speech and
Managing Voice Fraud & Threats Tuning Speech Applications, Part 1
SAPI on Windows Vista
Jens Henrichsen, Valene Skerpac Joe Alwan, Bernhard Suhm
Legal issues with Speech Tuning Speech Applications, Part 2 STKU-7
Cleg Ivy Dave Pelland, Emmett Coin Let’s Write Some Prompts!
Is Paul English Right? Collecting, Managing, & Analyzing
Walter Rolandi, Kirsty McCarthy, User Feedback Assessing & Improving
Michael Zirngibl Elisa Elderbaum, Jenni McKienzie Caller Experience
Worst Practices The Lighter Side of Greg Simsar & Eduardo Olvera
Mike Bergelson, Michael Perry Speech Deployments
Michael Picheny, Richard Feinberg
Monday, August 20
human agents. How can we make good use of automation without losing
TRACK A the personal touch that’s so important to customers? In this session, panelists
MEETING BUSINESS GOALS consider all customer communications as one flow, fusing contact with live
WITH SPEECH agents with automated processes. Attendees will learn from the panelists’ real-
world experiences about how customer service organizations are using new
A101 technologies to bridge the human-automation divide.
Speech & Self-Service Strategy
MONDAY, AUGUST 20
10:15 a.m. – 11:15 a.m.
Tony Lorentzen, Director, Consulting Services, Viecore, Inc. TRACK B
Nancy Gardener, Senior Analyst, Convergys VUI FOR VUI DESIGNERS
Speech-enabled applications in the call center make a myriad of self-service
options available to the end user. However, the idea of “if we build it, they will B101
come” has proven false for many organizations deploying speech. Why are Whose VUI Is It, Anyway?
some speech applications well-tolerated and some avoided at all costs? What User Versus Business Requirements
are the factors that cause users to abandon automated systems in favor of live 10:15 a.m. – 11:15 a.m.
agents? Experts in this session consider speech technology as a part of an
overall self-service strategy. Learn techniques for strategic planning, data Erin Smith, Staff Engineer, VUI Design, Intervoice
collection, and analysis that will help create self-service applications that end Eduardo Olvera, Senior Speech Analyst, Syntellect
users actually want to use. A voice user interface is a balancing act between the goals of the business and
those of the end users. These goals are often in conflict—businesses want to
Beyond Usability: How Good Is A102
push more calls to self-service, users want total access to live agents—often to
Your Speech Application? the detriment of the success of the application. When should user requirements
11:30 a.m. – 12:30 p.m. win out? In what cases are business requirements more important? The experts
in this session provide the knowledge you need to answer these questions.
Silke Witt-Ehsani, Director, VUI Design and Speech
Science, TuVox, Inc. Usability Surveys: B102
Melanie Polkosky, Cognitive Psychologist, IBM AIM Lab Services Practical Techniques
Usability is widely recognized as a measure of the quality of a voice user interface, 11:30 a.m. – 12:30 p.m.
and usability testing is a must-have in all VUI design projects. But does usability
tell the whole story? These experts agree that excellent speech applications are
Peter Leppik, CEO, Vocal Laboratories
more than just easy-to-use. In this session, hear cutting-edge ideas about what Surveys are an important method of getting opinion feedback from users of
to measure beyond usability and how it can improve your speech application. speech applications. At best, surveys provide quantifiable data that clarifies
user opinions, but many do-it-yourself surveys do not achieve this result. In
LUNCH KEYNOTE this session, you will learn how to craft surveys that deliver reliable, accurate
Sponsored by Voice Objects data to improve the performance of your speech application. Attendees will
gain a basic understanding of survey theory, methods, techniques, and
12:30 p.m. – 1:45 p.m. analysis.
Success Criteria for the Speech A103
Customer Experience Sponsored by Voice Objects
1:45 p.m. – 2:45 p.m.
12:30 p.m. – 1:45 p.m.
Carrie Nelson, Speech Solutions Team Technical Lead, Nortel
Michael Guillet, Product Manager, Speech Analytics, Controlling Prompts for B103
Nuance Communications, Inc. Maximum Usability
How do you know if your speech application is living up to your objectives?
Is the application meeting the goals you set when you started the project?
1:45 p.m. – 2:45 p.m.
You’ll only know the answer to these crucial questions if you establish success Tom Houwing, Director, VoiceandVision
criteria, tied to specific metrics, before the project begins. In this session, learn Prompts are at the heart of any VUI design. Prompts are the embodiment of
how to develop rigorous, meaningful criteria that will allow ongoing evaluation the sound and feel of the application and convey both affective and
and improvement of your speech applications. informational content. In a very real sense, the usability of a speech application
is largely determined by the quality of its prompts. Crafting effective prompts
New Business Models for Speech A104 is a creative and scientific endeavor, requiring a diverse skill set. This expert VUI
3:00 p.m. – 4:00 p.m. designer outlines an approach for writing, recording, coaching, and processing
prompts to ensure the highest quality possible.
John Hibel, Vice President of Marketing, Voxeo
John Roswech, Senior Vice President of Sales,1-800-FREE411 You Be the Expert! Speech and B104
In years past, the decision to deploy speech was all about cost reduction—
companies used speech applications to offload tasks from more-expensive live
the End-to-End Customer
agents. Many organizations are realizing that this simplistic model does not Experience
always work as advertised, and that speech can do more than just reduce 3:00 p.m. – 4:00 p.m.
costs. Experts in this session detail new ideas for maximizing the value of speech
applications and using speech for more than cost savings.
Lizanne Kaiser, Customer Experience Designer, Genesys
Simulating the Personal Touch A105 Come share your experience! Audience members will actively participate in this
4:15 p.m. – 5:00 p.m. session, sharing insights and anecdotes on the do’s and don’ts of how to use
speech automation to create a better end-to-end customer experience. End users
Moderator: Tim Moynihan, Vice President, Global don’t evaluate speech automation in isolation--they view it as part of an integrated
Marketing & Sales Support, Envox Worldwide customer service chain. So in designing the optimal VUI, it’s important to take
Sixty percent of calls fail to achieve productive results. Incessant routing by into account what might happen before, during, and after the automated
automated systems keeps callers longing for the good old days of talking to speech interaction in order to create a seamless customer experience.
6 August 20–23, 2007 ◗ New York Marriott Marquis, New York
B105 enough. There is little dispute that out-of-grammar handling is generally poor
Communication Strategies when an active grammar is large. In-grammar accuracy for extensive
for Speech Projects vocabularies has been achieved by using large amounts of speech data to
4:15 p.m. – 5:00 p.m. extract statistical information to represent acoustical units. Likewise, statistical
approaches have been applied to advance natural language understanding.
Melanie Polkosky, Cognitive Psychologist, IBM AIM Lab Services Most recently, statistical approaches are being applied to voice interface design
MONDAY, AUGUST 20
Maria Aretoulaki, Senior Engineer, VUI Design, Intervoice with the goal of improving user experience. This session reveals some exciting
Speech projects always involve multiple contributors, often with diverse advances in natural language that will affect the future of the user experience.
backgrounds and differing levels of understanding of project goals and speech
technology itself. The voice user interface designer often sits squarely in the Speech-to-Speech C104
middle of a group of project sponsors, developers, call center and telephony
managers, and others who have a stake in the success of a speech project.
In this session, experts suggest effective techniques for facilitating 3:00 p.m. – 4:00 p.m.
communication both within the team delivering the speech application and Moderator: Bill Scholz, President, NewSpeech, LLC
between the team and project sponsors. Speakers: Jan Kleindienst, R&D Manager,
Conversational Technologies & Interfaces, IBM
TRACK C Kirti Vashee, Vice President of Sales and Marketing,
ADVANCED SPEECH TECHNOLOGY Language Weaver, Inc.
SYMPOSIUM (Organized by AVIOS) Recent innovative integration of recognition and synthesis technology has led
to the realization of fully automatic speech-to-speech translation. This session
Advances in Speech Recognition C101 explores the latest techniques for implementing automated language
Processing translation and considers the technology behind the integration: how to
manage out-of-grammar responses, the effects of using robust parsing versus
10:15 a.m. – 11:15 a.m. SLMs, and incorporating an open source speech analytics solution called
Moderator: Tom Schalk, VP Voice Technology, ATX Group Unstructured Information Management Architecture.
Speakers: Veeru Ramaswamy, Chief Technology Officer, Vianix C105
Fil Aleva, Research Scientist, Microsoft
4:15 p.m. – 5:00 p.m.
Advances and improvement in core speech recognition technology are difficult
to demonstrate, since accuracy is strongly dependent on application, particular ,
Moderator: Tom Schalk, VP Voice Technology, ATX Group
speakers, background noise, and other variables. Beyond accuracy, speech Speaker: Leo Chiu, Chief Technology Officer, Apptera
recognition technology can be improved by better handling of complex or Voice search is perhaps the hottest topic in recent speech deployments.
"natural" dialogs. Audio channels and speech platforms are important Analogous to searching the Web with text, voice search can encompass a
components of today’s speech applications. In this session, speakers explore number of services, including directory search and searches for specific
the advances in core speech technology, audio channel processing, and information, such as news or sports scores. What are the requirements for
speech platform integration and go behind the scenes of Vista to expose achieving effective dialogs when searching by voice? How does dynamic
interesting aspects of the integration of speech technology. content, such as location-based ads, fit into the voice-user interface? What other
C102 analogies are there between voice searching and Web searching? This session
Advances in Text-to-Speech Processing is a must for those interested in learning about the trends in voice search.
11:30 a.m. – 12:30 p.m.
Moderator: Tom Schalk, VP Voice Technology, ATX Group TRACK D
Speakers: Daniel Burnett, Speech Standards Lead
Engineer, Nuance Communications, Inc.
SPEECH TO GROW
Patrizio Bergallo, Senior System Architect, Loquendo
Text-to-speech synthesis is getting better, more flexible, and is now used globally D101
in a wide spectrum of speech applications. Advances in standards have improved Speech in the Mainstream:
text-to-speech quality. The Speech Synthesis Markup Language (SSML) provides Top Trends
a standard way to control speech synthesis and text processing parameters. The
10:15 a.m. – 11:15 a.m.
Pronunciation Lexicon Specification (PLS) is designed to enable interoperable
specification of pronunciation information. This session reviews some much Bill Meisel, President, TMA Associates
needed clarifications about how text in multiple languages should be annotated Daniel Hong, Lead Analyst, Datamonitor
and describes work being done to link SSML and PLS more seamlessly. The maturation of speech recognition technology is leading to new business
opportunities in a consolidating market. Where are customer wins occurring?
LUNCH KEYNOTE What are the top trends and drivers in the speech industry? And what factors
Sponsored by Voice Objects will influence the speech industry in coming years? Two respected industry
analysts map where the speech industry is right now and where it is headed.
12:30 p.m. – 1:45 p.m.
C103 Using Analytics to Understand D102
Advances in Natural Language
Processing Your Customer
1:45 p.m. – 2:45 p.m. 11:30 a.m. – 12:30 p.m.
Moderator: Tom Schalk, VP Voice Technology, ATX Group
, CCS Scott Witter, The Hardford Insurance Co.
Speakers: Roberto Pieraccini, Chief Technology Officer, Analytics can take many forms within an enterprise. Two that involve speech
processing are showcased in this session. One approach examines the
and Jonathan Bloom, Senior VUI Designer, SpeechCycle
communication channels (IVR, agent, Web, etc.) and the paths within the
Krishna Govindarajan, Speech Science Global Discipline channels that customers follow as they interact with an enterprise. The second
Leader, Nuance Communications, Inc. delves into the spoken content of interactions between customers and call
The demand for natural language has reached an all-time high as directed- center agents. Each approach extracts information from its analysis that delivers
dialog applications continue to be criticized for being inefficient and not flexible important business intelligence to the enterprise.
Monday, August 20
LUNCH KEYNOTE TRACK E
Sponsored by Voice Objects DEVELOPMENT TOOLS & ENVIRONMENTS
12:30 p.m. – 1:45 p.m.
Speech to Increase Revenue D103 Open Source Development E101
MONDAY, AUGUST 20
& Decrease Costs Environments
1:45 p.m. – 2:45 p.m. 10:15 a.m. – 11:15 a.m.
CCS Mike Uhlenkamp, Call Center Technology Manager, Phil Shinn, Principal Consultant, Genesys
DIRECTV, Inc. Ken Osowski, Vice President of Product Development &
CCS Dottie Verkade, Head of Speech Innovations, Atena Marketing, Pactolus Communications Software
Speech applications are being used to increase revenue and decrease costs In this technical session about open source development environments, Phil
by revolutionizing business processes and customer interactions. In this session, Shinn will analyze & compare the scalability, subscriber feature flexibility,
hear lessons learned from customers and industry leaders who have pioneered multiservice integration potential, and other key service enablement
the implementation and deployment of successful speech applications. Learn characteristics of leading and emerging open source telecom technologies.
how you can increase customer service and save money at the same time Ken Osowski will demonstrate the use of open source Visio custom stencils,
from developers who have successfully improved the bottom line in their VB code, and Python code that allow designers to create and maintain VUI
organizations. designs and test plans.
Speech Enables Self-Service D104 Windows Vista Development E102
3:00 p.m. – 4:00 p.m. Environment
Richard Grant, Chief Technology Officer, and 11:30 a.m. – 12:30 p.m.
Chester Anderson, Vice President, Business Development, Michael Dunn, Consultant, Magenic Technologies
Order Catcher, Inc. Fabrizo Giacomelli, CEO, Mediavoice (MOAI Group)
Kostas Darivakis, General Manager, and Windows Vista supports speech interfaces to many of its applications. In this
Alexandros Papanikolaou, Sales Manager, Village session, attendees will see demonstrations about how to use Visual Studio to
Roadshow Greece develop SALT and IVR applications for the Microsoft Office Communication
Hear how to improve customer service by enabling customers to use phones Server. This session will also demonstrate and discuss the Speaky Media Center
and cell phones to place orders with automated speech systems instead of for controlling a Windows Vista-based media center.
waiting in lines to purchase tickets or place orders. A fast food company and a LUNCH KEYNOTE
cinema theater chain explain how automated speech systems that save money
and improve customer satisfaction were successfully implemented and deployed. Sponsored by Voice Objects
Hear how such problems as menu navigation, recognition of non-English words, 12:30 p.m. – 1:45 p.m.
real-time menu updates, and peak call processing were overcome. E103
New Language Specifications
Speech Drives CRM D105
1:45 p.m. – 2:45 p.m.
4:45 p.m. – 5:00 p.m. James Barnett, Technical Director, Aspect Software
CCS Brian Gebert, Director of Corporate Sales,
David L. Thomson, Chief Technical Officer, SpeechPhone
Shunra Software Ltd. This session reviews two emerging languages. The W3C State Chart XML
Jangwoo Shin, Chief Technology Officer, WebForPhone (SCXML) will be a fundamental part of VoiceXML 3.0, as well as a stand-alone
By speaking on a telephone, users can retrieve and update data on control language. The VoiceXML Forum’s Data Logging Specification will
accounts, contacts, opportunities, and calendar applications. Learn how to describe a format for log files created by speech applications and used by log
overcome the difficult problems of CRM applications, including recognition report generators and database management systems.
of custom vocabulary and database searches. These industry experts will Which Tools Are Right for You? E104
present demonstrations and share key learnings. 3:00 p.m. – 4:00 p.m.
John Fuentes, Principal Solutions Architect, Intervoice
Moshe Yudkowsky, President, Disaggregate
CUSTOMER With the high cost of developing speech applications, businesses are turning
to speech application development tools to decrease the time and effort
CASE STUDIES CS needed to develop speech applications. This session discusses the types of
development tools, identifies criteria for useful development tools, and
marked with a Customer Case Studies icon ( CCS ) suggests some development tool characteristics that should be avoided. The
discuss experiences with real applications, usually speakers will also identify missing tool functionality, recommend strategies for
presented by a customer. These presentations will tool interoperability, and characterize desirable tool user interfaces.
Techniques for Reusability
◗ Problem(s) to be solved 4:45 p.m. – 5:00 p.m.
◗ Technology used to solve the problem Jerry Carter, Director of Network Speech Architecture
◗ Problems encountered and how they were solved & Standards, Nuance Communications, Inc.
Rob Marchand, Senior Director of Product Management, Genesys
◗ Benefits derived from the solution Ken Rehor, Consultant
◗ Key learnings The expense of developing speech application software has caused enterprises
◗ Short demonstration to look at ways to decrease development costs. This panel explores ways to reuse
existing code and offers suggestions about how to construct code to improve
its usability. The panel will also discuss the problems and benefits of reusable
grammars, subdialogs, packaged applications, and other strategies for reusability.
8 August 20–23, 2007 ◗ New York Marriott Marquis, New York
Tuesday, August 21
application and how best to approach the design of new multilingual
TRACK A applications.
THE YEAR OF LIVING VIRTUALLY:
HOSTED AND MANAGED SERVICES LUNCH BREAK
(Organized by Opus Research) 12:00 p.m. – 1:30 p.m.
TUESDAY, AUGUST 21
The Outsourcer’s Perspective Getting the VUI Right When B202
10:45 a.m. – 12:00 a.m. Recognition Goes Wrong
Outsourcing is a common practice and is often the best practice for cost-
1:30 p.m. – 2:30 p.m.
effective, high-quality customer service and self-service. In this session, leading
service providers and their customers introduce and describe the criteria that Kristie Goss, VUI Designer, Convergys
influenced their decision to outsource, and their experiences with the team Daniel Padgett, Senior Voice User Interface Consultant,
of application developers, carriers, and hosted services providers. Versay Solutions
LUNCH BREAK Recognition errors are a fact of life for speech systems. The job of a good voice
user interface is to make the errors as inconsequential as possible to the end
12:00 p.m. – 1:30 p.m.
user. Learn how to handle confirmations to build user confidence without
Contrasting Service A202 becoming a burden, and hear about new approaches to error-handling for
natural language applications.
1:30 p.m. – 2:30 p.m. Making It Personal B203
John Hibel, Vice President of Marketing, Voxeo 2:45 p.m. – 3:45 p.m.
Mark Wilbur, Senior Product Manager, Hosted IVR, Barb Mackraz, Principal, Mackraz Design Group
Verizon Business Cory Wright, Senior Marketing Manager, Customer Contact,
Ron Owens, Vice President, Product Strategy, First Data Cisco
Voice Services Speech applications used to be conceived of as one-size-fits-all interactions in
Nearly every service provider offers savings in capital expense and contact which every user had the same experience. Increasingly, organizations are
center operating costs. Increasingly, service providers differentiate themselves capitalizing on data they already know about customers to tailor the
through partnering strategies, technology in use, application development experience specifically for them. Whatever you know about the customer can
and management resources, and support of multiple modalities of customer be used to predict the likely reason for the call, and present relevant
care and self-service. information and services proactively. Learn techniques for creating
personalized interactions that make calls seem efficient, productive, and
Meeting Business Challenges A203 surprisingly satisfying.
2:45 p.m. – 3:45 p.m. B204
Tim Moynihan, Vice President, Global Marketing & Sales
Watch Your Grammar
Support, Envox Worldwide 4:15 p.m. – 5:15 p.m.
Steven Pollack, Executive Vice President & Co-Founder, TuVox Judi Halperin, Staff Engineer, Global Consulting Services, Intervoice
This has been the year of the end user. With so much emphasis on the David L. Thomson, Chief Technical Officer, SpeechPhone
customer experience, being able to identify snags in self-service applications Speech applications are only as effective as the grammars used to recognize
at a highly granular level and make corrections dynamically is crucial. In this user responses. Grammars must be broad enough to cover typical responses
session, application framework providers describe how they support while constrained as tightly as possible to improve recognition accuracy. Learn
application development that meets customer service objectives. how to craft grammars that strike the right balance, and hear about new
developments in standardized grammars in this important session.
View of the Global Future A204
4:15 p.m. – 5:15 p.m.
Juan Ceballos, Chief Technology Officer, Ydilo ADVANCED SPEECH TECHNOLOGY
Mark Plakias, Vice President, Strategy, France Telecom SYMPOSIUM
In this session, the biggest stakeholders in global, outsourced communications (Organized by AVIOS)
discuss how the distributed, virtualized contact center will integrate speech
automation with multimodal communications (blending live agents with IM, chat, C201
and video messaging) and what this means for the future of customer service.
New Approaches to Dialog Design
10:45 a.m. – 12:00 p.m.
Moderator: Bill Scholz, President, NewSpeech, LLC
TRACK B Speakers: Dominique Boucher, Lead Software
DESIGNING THE SPEECH Developer, Nu Echo, Inc.
CUSTOMER EXPERIENCE Clifford Harlow, Vice President, Client Services,
Para Continuar en Espanol … B201 Joachim Stegmann, Head of Department, T-Systems
10:45 a.m. – 12:00 p.m. As designers are urged to create ever-more sophisticated self-service
applications, the pressure for evolving new techniques grows in importance.
Aimee Piercy, Associate, Mackraz Design Group, LLC New Eclipse-based graphical tools oriented around the identification,
Prabha Sundaram, Speech Specialist, Nortel definition, and reuse of hierarchical dialog patterns and novel nonlinear call
The world is getting smaller, and increasingly this is reflected in speech flows assisted by agents are described in this dialog design session.
applications that include more than one language. Enabling access to a
speech application in another language is not a simple matter of translating
the prompts and switching the recognition algorithm to the other language. LUNCH BREAK
Experts in this session offer tips on adding a second language to an existing 12:00 p.m. – 1:30 p.m.
Tuesday, August 21
C202 held devices. Recent applications of speech-to-text for searching and
Artificial Intelligence & VUI Design transcribing voice data will be illustrated for other applications including medical
1:30 p.m. – 2:30 p.m. data transcription and the near-real-time conversion of voice mail to text.
Moderator: Bill Scholz, President, NewSpeech, LLC
Speakers: Mahesh Rajagopalan, Chief Operating Officer TRACK D
TUESDAY, AUGUST 21
and Vice President, Engineering, and Jacek Jarmulak, INNOVATIVE SPEECH APPLICATIONS
Senior Scientist, Resolvity
Peter Trompetter, Vice President, Global Development,
Speech Applications for Emergencies D201
The growing sophistication of VUI designs demands the incorporation of new 10:45 a.m. – 12:00 p.m.
technologies, including those borrowed from other disciplines. This session CCS Klaus Schaefer, Head of Fire Department–Dortmund,
focuses on the novel application of artificial intelligence technology using a Institute of Fire and Rescue Technologies, Fire Department of
dialog engine and a problem-solving engine working concurrently. It also Dortmund (Germany)
illustrates the use of natural language to understand the semantics and context
of any phrase being processed, making it much easier to develop the answers.
Howard Wood, Executive Vice President, Reliance
Advances in Video & Multimedia C203
This session shows two case studies that illustrate how speech technology
Application Design can be used in emergency situations. Schools use speech technology to deliver
2:45 p.m. – 3:45 p.m. both emergency messages (i.e., school closures, lockdowns, illness outbreaks)
and personalized messages (i.e., absence date, periods/classes missed, current
Moderator: Bill Scholz, President, NewSpeech, LLC cafeteria account balance, bus route schedule change) to parents. Fire fighters
Speakers: Valentine Matula, Director, Multimedia use advanced, multimodal, mobile services enabling on-the-move rescuers to
Research, Avaya Inc. communicate and to share structured multimodal information resources
including audio, video, text, graphics, and location information.
Jan Sedivy, Researcher, IBM Czech Republic
The availability of a robust 3G infrastructure throughout Europe and much of Lunch BREAK
Asia has released pent-up customer demand to add live video to extend the
12:00 p.m. – 1:30 p.m.
utility of voice communications. This session illustrates how video menus,
pictures of products, live video clips, and video commercials can be managed, Synthetic Agents that Speak & Listen D202
as well as how sample speech/video-enabled self-service applications for
universities, travel, retail, and home health can be developed. Also, the use 1:30 p.m. – 2:30 p.m.
of the Adobe Flash Player, a popular standard for delivering rich Web content, CCS Matt Nikerson, Special Projects Librarian and Honors
to develop multimedia content will be explained and illustrated. Program Director, Southern Utah University
CCS Antonio Gentile, Assistant Professor, Department of
Speech-to-Text Transcription C204
Automatics and Computer Science, University of Palermo (Italy)
4:15 p.m. – 5:15 p.m. Synthetic interviews enable callers to go beyond the picture or cultural object
Moderator: Bill Scholz, President, NewSpeech, LLC to better understand the event or concept it represents. For instance, callers
Speakers: Michael Picheny, Researcher, IBM may conduct synthetic interviews with individuals in photographs of historical
events in a museum or objects in a cultural heritage site. Synthetic interviews
Marie Meteer, Researcher, Podzinger represent a new way of interacting with objects that are usually only viewed.
Recognition technology has matured to the point where recorded telephone- The first case study in this session describes a cell-phone application, and the
quality audio from unknown speakers can be accurately transcribed. second shows a multimodal application that contains a chat-bot. When
Applications such as speech-enabled e-mail have become highly needed in the applied to the world of advertising, synthetic agents will enable people to talk
mobile environment because typing is not always practical when using hand- with advertisements in magazines, on billboards, and other advertising media.
Grand Opening Invited Workshops
Each year, SpeechTEK hosts day-long, invitation-only
Reception workshops in which participants collaborate to solve
common speech application problems. Previous workshops
have produced guidelines for designing successful VUIs,
All SpeechTek attendees are
criteria for measuring effective VUIs, guidelines for handling
invited to the Grand Opening speech recognition errors, and specification techniques for
Reception taking place from advanced speech dialogs. This year's VUI Designer’ Working
Group will address the VUI designers’ career ladder, job
5:00 p.m. – 7:00 p.m. descriptions, and educational requirements. If you would like
to participate in this workshop or organize another one,
in the Exhibit Hall on Monday. please contact Susan Hura (firstname.lastname@example.org)
or Jim Larson (email@example.com).
10 August 20–23, 2007 ◗ New York Marriott Marquis, New York
Speech in Banking D203 LUNCH BREAK
2:45 p.m. – 3:45 p.m. 12:00 p.m. – 1:30 p.m.
CCS Stephan Schneider, Project Manager, Voice Portal,
Tips & Techniques for Using Grammars E202
TUESDAY, AUGUST 21
CCS Marc Seltier, Communication Technologies Manager, 1:30 p.m. – 2:30 p.m.
HypoVerreinsbank Deutschland Sunil Issar, Director, Speech Science, Global Custom
Around the world, speech applications are being used to update account Development Services, Convergys Corp.
information and transfer billions of dollars among accounts. Learn how two
Padma Ramesh, Senior VUI Developer, and Krishnan
of Europe’s major banks have successfully deployed speech applications that
revolutionized their operations. Speakers will describe solutions to problems Srinivasan, Senior Solutions Manager,
they encountered during development and deployment. Nuance Communications, Inc.
Specifying grammars that cover the words spoken by users is one of the major
Touch to Voice: Creating a WOW D204 keys to designing and implementing speech applications. Tuning grammars
is a complex task and requires automated techniques to analyze large amounts
Experience for AARP Consumers of data. What techniques can designers and implementers use to build and
4:15 p.m. – 5:15 p.m. tune grammars to handle unexpected events in caller responses such as
CCS Ava J. Baker, CEO and President, AJ Waters, LLC background talk, side conversations, nonspeech events, restarts, and
CCS R. J. Fox, Director of Quality Assurance, AARP corrections? Can some of these techniques be automated?
They said it couldn't be done, but in today's high-tech environment, more and E203
more callers are using speech IVR, including those older than 50. Hear the Web Services & Speech
latest research findings and how AARP is on the path to continuous 2:45 p.m. – 3:45 p.m.
improvement using speech to “wow” customers. Michael Codini, Chief Technical Officer, VoiceObjects, Inc.
Chris Passaretti, Software Development Manager, Research
TRACK E & Development, Nortel
TIPS & TECHNIQUES FOR A major problem facing speech application developers is integration with the
IMPLEMENTING YOUR SPEECH rest of an enterprise’s IT infrastructures. Learn how to integrate speech user
interfaces over a network with the rest of an enterprise’s IT infrastructure using
APPLICATIONS service-oriented architecture (SOA) technology and Web services. The benefits
of this approach include keeping your application portable and maintaining
E201 a clear separation of your call flow and your business logic.
Speech Synthesizers on Steroids
10:45 a.m. – 12:00 p.m.
Deploying Speech Applications E204
Davide Bonardo, Senior TTS Software Architect, Loquendo
4:15 p.m. – 5:15 p.m.
Qiang Bai, Vice President, Anhui USTC iFLYTEK Co., Ltd.
Text-to-speech synthesis is used to render dynamic data, such as newsfeeds R. J. Auburn, Chief Technology Officer, Voxeo
and e-mail, and to avoid costly, time-consuming prerecording. The use of Bob Cooper, Voice Portal Chief Architect, Avaya
speech synthesis will increase as functionality improves, including Even the most carefully planned deployments can go wrong. Experts in this
pronunciation accuracy, natural timbre, intonation, and expressive voices that session review lessons learned from years of customer deployments of
supply so much of an application’s persona. Special attention will be given in applications with two to 20,000 ports. They discuss the features of Session
this session to the challenging requirements of non-English-languages, Initiation Protocol (SIP), a lightweight, transport-independent protocol for
sentences containing mixed languages, and new extensions to the W3C messaging, and share tips on how to overcome the challenges of
Speech Synthesis Markup Language (SSML). deploying SIP .
Idea Markets Are you a VUI designer
Tuesday and Wednesday or interested in VUI?
7:45 a.m. – 8:45 a.m.
Don’t miss Track B on Monday, VUI for VUI
Plan your schedule to join a group of colleagues for Designers, that is planned just for you. Additional
breakfast at 7:45 a.m. on Tuesday and Wednesday VUI tracks are Track B, Tuesday, Designing the
mornings for “idea market” sessions. Idea markets Speech Customer Experience, and Track B,
are highly interactive, casual, collaborative Wednesday, The V-Files: Hot Topics in VUI
conversations about burning questions in speech Design. Also consider registering for STK University
technology or VUI design, or gatherings of people courses, STKU-4, User-Focused VUI Design;
working in market segments with common STKU-7, Let’s Write Some Prompts!; and
questions and interests. STKU-8, Assessing & Improving Caller
Wednesday, August 22
TRACK A TRACK B
PLANNING & MANAGING THE V-FILES: HOT TOPICS IN VUI DESIGN
WEDNESDAY, AUGUST 22
SUCCESSFUL SPEECH B301
DEPLOYMENTS Retire the Horse and Buggy
10:30 a.m. – 11:30 a.m.
A301 Moderator: Phillip Hunter, Vice President,
Mainstream Speech? Voice Interaction Group, SpeechCycle, Inc.
Stakeholder Views from Voice user interface design is a relatively young field, but are we already stuck
360 Degrees in our ways? Many of today’s designs cling to habits established when we
10:30 a.m. – 11:30 a.m. knew far less about the uses, users, environments, and capabilities of our
systems. This panel kicks it up a notch and challenges VUI designers to explore
Tim Pearce, Global Solutions Manager, Self-Service, new directions and reconceptualize the voice user interface in the light of
Dimension Data marked advances in speech.
Mike Bergelson, Director of Business Development for B302
Contact Centers, Cisco Special Cases in VUI Design
What are the critical success factors that need to be in place for speech to be 11:45 a.m. – 12:45 p.m.
truly mainstream? This 360-degree review presents the results of an ambitious David Martin, Solution Architect, Avaya
set of surveys with end users of speech applications, business decision makers,
Vasuveda Akula, Speech Scientist, Convergys Corp.
technical decision makers, and call center managers. The results will be
interpreted and debated by a panel of industry experts. The focus in VUI design is often to discover and apply universal principles to
guide all our designs. As voice user interfaces are used in more varied contexts
and with different user populations, we increasingly discover that there are
Positioning Speech A302 exceptions to the rules. Best practices that clearly work in some domains may
Applications for Success not be effective in others. Learn how to break the rules of design properly and
when to do so to create the most effective VUI designs.
11:45 a.m. – 12:45 p.m.
CCS Oren Hertz, Section Manager for Call Center, Hapoalim LUNCH BREAK
Bank, and Nava Shaked, A. L. M Liam Ltd. 12:45 p.m. – 2:00 p.m
Caroline Leathem, Head of Consultancy, Fluency Voice B303
Technology Whither VUI Standards?
The way a speech application is presented can have a huge impact on its
2:00 p.m. – 3:00 p.m.
ultimate success. Applications that are deployed with a solid understanding Phil Shinn, Consultant, Genesys Telecommunications Labs
of the views of the customers who will use them are more likely to succeed— Fran McTernan, Speech Operations Lead, Nortel
but what is the best way to obtain this understanding? Once an application Can we create VUI standards? Should we? What would VUI standards look
is ready to deploy, what’s the best way to roll it out to customers? Learn how like, and what would be their impact? Should we have global commands
positioning a speech application correctly can help achieve your goals. (such as “help” or “back up”) that are part of a global grammar for all
applications? These topics and more will be the subject of this thought-
LUNCH BREAK provoking panel.
12:45 p.m. – 2:00 p.m. The Ultimate VUI Showdown B304
3:15 p.m. – 4:15 p.m.
The Future of Speech A303 Moderator: Greg Simsar, Vice President Speech Services,
2:00 p.m. – 3:00 p.m. Syntellect, Inc.
Scott McGlashan, Distinguished Technologist, Back for an encore from SpeechTEK 2006 is Greg Simsar’s provocative,
interactive, and fun debate on hot topics in VUI design. Noted industry experts
Hewlett Packard will offer their often opposing viewpoints on the state of VUI 2007, and the
Moshe Yudkowsky, President, Disaggregate audience is highly encouraged to enter the fray. Come for lively discussion,
Mark Rayburn, President and CEO, DemandVoice LLC friendly feuding, and strong opinions, and leave with many new perspectives
What’s the next big thing in speech? What challenges lie ahead and how can on VUI design.
we overcome them? Speakers in this session tell us what to look for in the
coming months and years and help us understand where we are today. Learn
about latest developments in VXML 3.0, and gain insight into the role of TRACK C
speech in a GUI-dominated world. NOW READY FOR PRIME TIME!
Top 25 Speech Project A304 C301
Natural Language Processing
“Gotchas” 10:30 a.m. – 11:30 a.m.
3:15 p.m. – 4:15 p.m. Aaron Fisher, IT Manager Professional Services, West Interactive
Moderator: Ron Owens, Vice President, Product Strategy, Marko Petroni, Principal Solutions Architect, Nuance
First Data Voice Services Communications, Inc.
Anyone who has ever worked on a speech project has them—war stories of Natural language (NL) is used (and misused) to mean many different
missteps we wish we could have avoided. This panel of experts represents a capabilities, ranging from continuous speech recognition to complete
wealth of experience with real speech deployments, and they offer these understanding of conversational English. Aaron Fisher will overview various
experiences to help save you from their bloopers. Panelists will offer their best types of NL and discuss how it works. Marko Petroni describes best practices
tips and tricks of the trade about how to avoid the “oops” factor and to keep for implementing a popular type of natural language call steering, which
your speech projects on track. automatically routes callers to one of several destinations.
12 August 20–23, 2007 ◗ New York Marriott Marquis, New York
Who’s Really Calling? C302 Legal Issues with Speech D302
Speaker Authentication 11:45 a.m. – 12:45 p.m.
WEDNESDAY, AUGUST 22
11:45 a.m. – 12:45 p.m. Cleg Ivy, Vice President, Mergers & Acquisitions,
CCS Brian Rowland, Director, Contact Centre Technology & General Counsel, Voxeo
Member Experience, Aeroplan Speech technology deployments raise new political and legal issues. Should
CCS Melinda Charlesworth, Operations Manager, Australian the FTC be able to place severe restrictions on outbound IVR calls? Should the
government mandate how personal data should be made secure? Who owns
Health Management your “voice print”? How should the speech industry react to government efforts
Speaker authentication is a form of biometric-based security that uses features to exercise controls? Hear this panel discuss these and other legal issues
of a person’s voice to validate that they are who they claim to be. It secures surrounding speech applications and technology.
sensitive transactions made over the telephone and ensures that only
authorized individuals have access to sensitive information and mission-critical
resources. This session addresses the major authentication issues of premise- LUNCH BREAK
based or managed service, registration procedures, challenge dialogs, and 12:45 p.m. – 2:00 p.m.
Is Paul English Right? D303
LUNCH BREAK 2:00 p.m. – 3:00 p.m.
12:45 p.m. – 2:00 p.m.
Walter Rolandi, Human Factors Psychologist, The Voice
User Interface Company, LLC
Using Multimodal Technology C303
Kirsty McCarthy, Vice President, Sales & Marketing,
to Improve Language Skills Inference Communications
2:00 p.m. – 3:00 p.m. Michael X. Zirngibl, CEO, Angel.com
CCS David Topolewski, Chairman, EnglishXchange, Pte Ltd. Paul English presented the getHuman.com guidelines for improving IVR
Deborah A. Dahl, Principal, Conversational Technologies systems in a keynote address at last year’s SpeechTEK conference. The
New and exciting types of user interfaces are required to take full advantage guidelines attempt to eliminate IVR features that most anger customers, but
of multiple modes of input, such as speech and keypads/mouse pads. Two sometimes run counter to business goals and cost issues. How should the
case studies in this session describe how multimodal applications were speech industry react to these guidelines? Will consumers revolt against IVRs
developed, one for those learning how to speak English, and one for that fail to implement the guidelines? Members of this lively panel represent
individuals with aphasia, a loss of language ability resulting from brain injury, all viewpoints in this controversial discussion.
who needed speech therapy. The speakers describe how they used
Worst Practices D304
multimodal user interfaces to enable these applications, the problems
encountered, and best practices for developing multimodal applications. 3:15 p.m. – 4:15 p.m.
Mike Bergelson, Director of Business Development,
Video & Speech C304 Cisco
3:15 p.m. – 4:15 p.m. Michael Perry, Director, IVR & Speech Portfolio, Avaya
Andrew Fuller, Vice President, Engineering, Voxpilot Tired of guidelines that only tell you what to do? This session takes the opposite
approach and tells you what not to do. Hear when not to use speech
Rob Marchand, Senior Director of Product Management,
recognition, when not to use speech synthesis, and what not to do when
Genesys Telecommunications Laboratories
deploying a self-service solution into your integrated contract center.
Video adds a new dimension to speech applications, enabling users not only
to “speak and listen,” but to “see” as well. VoiceXML applications may be easily
augmented to become interactive video applications while retaining standard
speech services such as speech recognition and speech synthesis. Experts
describe existing implementations and video features in future standards such
as VoiceXML 3.0.
For video in
SOLVING SPEECH multimodal
Avoiding Voice Fraud & D301 applications
10:30 a.m. – 11:30 a.m.
See session C203 for how to enhance
Jens Henrichsen, Head of Technology Development,
Consumer Solutions, RSA, The Security Division of EMC speech applications with video, Session
Valene Skerpac, President, CISSP iBiometrics, Inc. (iBICS) C302 for uses of video, and Session
Identity theft and organized criminal activity to commit fraud have become
prevalent on the Web. Learn how to avoid fraudulent mechanisms that are C303 for case studies of multimodal
used to infiltrate the phone channel, including "product delivery confirmers,” applications.
change of billing attempts, phone number spoofing, and "voice phishing."
Learn how to mitigate risks associated with attacks that may compromise your
Wednesday, August 22
TRACK E LUNCH BREAK
TIPS AND TECHNIQUS FOR FIXING 12:45 p.m. – 2:00 p.m
YOUR SPEECH APPLICATION
WEDNESDAY, AUGUST 22
Collecting, Managing, & Analyzing E303
Tuning Speech Applications for E301 User Feedback
Maximum Performance, Part 1 2:00 p.m. – 3:00 p.m.
10:30 a.m. – 11:30 a.m. CCS Elisa Elderbaum, Project Manager, National
Joe Alwan, Vice President and General Manager, and Government Services (formerly Empire Medicare Services)
Bernhard Suhm, Director of Professional Services, AVOKE CCS Jenni McKienzie, VUI Designer, Travelocity
Call Center Analytics Division, BBN Technologies Learn how two companies use caller feedback from multiple sources to revise
Methods for tuning speech applications have grown and evolved with the and improve their respective IVR systems. Learn how to collect and analyze
industry. Learn how to manage a successful tuning project to get maximum the information and to determine how to modify the speech application. Most
value from your speech application. Topics include setting tuning objectives, important, find out how feedback improves performance.
understanding caller behavior and intent, measuring dissatisfiers and E304
inefficiencies, and identifying the highest-impact tuning opportunities.
The Lighter Side of
Tuning Speech Applications for E302 3:15 p.m. – 4:15 p.m.
Maximum Performance, Part 2 Michael Picheny, Senior Manager, Speech and Language
Technologies, IBM Watson Research Center
11:45 a.m. – 12:45 p.m.
Richard Feinberg, Professor, Purdue University
Dave Pelland, Director, Design Collaborative, Intervoice
In this lighthearted final session, Michael Picheny discusses a Shakespearian
Emmett Coin, Director of Speech Research and view of the status and future of speech recognition, leading us through
Development, Lucas Systems Shakespeare’s writings with lessons for speech technology use. To paraphrase
Learn how to improve speech recognition using computationally lightweight As You Like It, "All of SpeechTEK is a stage, And all the speech professionals
post-ASR information, and hear how an n-best list and other information from merely players." Professor Feinberg looks at the lighter side of call centers and
the ASR can be used to improve speech recognition accuracy. Experts will present customer satisfaction from a different perspective. Clips from movies and
several examples and techniques for developing dialogs that can improve the commercials illustrate that customer satisfaction is the only reason for speech
perceived recognition accuracy. These techniques can improve out-of-vocabulary technology and call centers. Caution: This is not the usual traditional
rejection and improve the correct recognition of user utterances. professorial dry lecture.
your exhibit space, sponsorships, and
promotional opportunities today!
For Information on sponsorships and
exhibiting, please contact:
La Shawn Fugate or Toll Free: 877-993-9767
2628 Wilhite Court, Suite 100
Lexington, KY 40503 Fax: 859-278-7364
14 August 20–23, 2007 ◗ New York Marriott Marquis, New York
Speech Technologies Have Evolved.
Find out where you can start with your FREE* subscription to
Speech Technology magazine. Now available in convenient
print or digital versions.
Log on and sign up for your FREE* subscription today:
*Print version free to U.S. subscribers only. Digital version free to all subscribers.
143 Old Marlton Pike • Medford, NJ 08055
SpeechTEK University courses are in-depth, focused, 3-hour seminars on topics of
special interest to speech technology and information technology professionals. Taught
THURSDAY, AUGUST 23
by experienced instructors, STK University courses offer a structured learning experience.
If you are considering deploying a speech application or looking to increase your
knowledgebase in one of these key areas, be sure to attend a SpeechTEK University course.
These are separately priced or may be purchased as part of your conference registration.
Thursday, August 23 SpeechTEK University
9:00 a.m. – STKU-1 STKU-2 STKU-3 STKU-4
12:00 p.m. Effective Application Hands-On CCXML Natural Language User-Focused VUI
Design Patterns Application Processing Design
Using VoiceXML & Workshop Deborah Dahl Susan L. Hura
CCXML/SCXML Moshe Yudkowsky
Scott McGlashan &
1:30 p.m.– STKU-5 STKU-6 STKU-7 STKU-8
4:30 p.m. Hands-On Voice Developing Let’s Write Some Assessing &
Applications with Applications Using Prompts! Improving Caller
SCXML System.Speech Jenni McKienzie Experience
R. J. Auburn and SAPI on Greg Simsar &
Windows Vista Eduardo Olvera
STKU-1 "smart" telephony applications. Participants should bring a laptop and should
Effective Application Design have a headset. Participants will receive advance instructions on how to
Patterns Using VoiceXML & CCXML/SCXML download and install a CCXML software package on their computers.
9:00 a.m. – 12:00 p.m. STKU-3
Scott McGlashan, Distinguished Technologist, Hewlett Packard
Natural Language Processing
9:00 a.m. – 12:00 p.m.
Ian Sutherland, Consulting Member of Technical Staff, Oracle
This course is for attendees with experience with VoiceXML (and related
Deborah Dahl, Principal, Conversational Technologies
languages such as CCXML or SCXML) who want to learn the latest best practices Natural language processing is used in more and more applications to support
for efficient and effective application design. Central to these techniques is the increasingly sophisticated speech dialogs. This tutorial will introduce natural
separation between presentation, flow, and data within an application. Since language processing and its role in speech applications. Attendees will learn
high-density deployments require efficient application design for maximum what natural language is; techniques for processing natural language; how
performance, you will learn how techniques such as HTTP resource caching to use Statistical Language Models (SLMs) and speech grammars with semantic
and data submission without page transitions contribute to efficiency and see tags for processing natural language; and about emerging standards and
their power with deployed applications using VoiceXML and CCXML. The course research and their roles in future applications. Attendees will have the
also covers how SCXML can be used to implement the flow of complex opportunity to develop tagged grammars illustrating the techniques discussed
applications, invoking VoiceXML interaction only when required. in the tutorial.
CCXML Application Workshop STKU-2 User-Focused VUI Design STKU-4
9:00 a.m. – 12:00 p.m. 9:00 a.m. – 12:00 p.m.
Moshe Yudkowsky, President, Disaggregate Susan L. Hura, Principal, SpeechUsability
Learn how to use CCXML by developing a useful program in just 3 hours in What are the rules for designing effective, intuitive, comfortable interactions
this applications workshop. CCXML, also known as Call Control XML, is a with automated speech systems? Voice user interface (VUI) design is a rapidly
standard language from the W3C that runs on a wide variety of platforms evolving field with few standards to rely upon. This practical tutorial details
from different vendors. By building a simple application, this course will teach how end users of speech systems can provide the information that you need
fundamental concepts and basic capabilities of the CCXML programming to create intelligent VUI designs that work for both users and businesses. It
language. The course will include information about how CCXML controls presents a philosophy of user-centered design applied throughout the speech
telephone calls, best practices to use when writing CCXML programs, and project lifecycle and shows how your users can teach you what you need to
how to incorporate information from databases and the Internet to build design quality VUIs.
16 August 20–23, 2007 ◗ New York Marriott Marquis, New York
STKU-5 be a little tough to translate theory into practice. This interactive tutorial will
Hands-On Voice Applications tackle the writing, pulling examples from actual deployments, designs, and
with SCXML some made-up scenarios. We’ll start by looking at some before and after
1:30 p.m. – 4:30 p.m. prompt pairs. What makes the original bad? What makes the rewrite good?
THURSDAY, AUGUST 23
Are there other possible good rewrites? We’ll share our thoughts and critique
R. J. Auburn, Chief Technology Officer, Voxeo each other. We’ll also look at sample conversations to make sure we add the
Learn the basics of using the next-generation W3C language SCXML to create context to our prompts, and start from scratch with a given scenario. And
speech applications. Developers will get a hands-on overview of the language once you’ve written great prompts, how important is the recording? We’ll look
and will work together to build several sample applications using free, publicly at several examples of how the recording contributes to the success or failure
available tools and the Prophecy SCXML browser. Expect to learn how and of the prompt.
when to use SCXML; the basics of Harel state charts; and ways that SCXML,
CCXML and VoiceXML can work together seamlessly. (Attendees will receive Assessing & Improving STKU-8
hardware specs and resources to download in advance.) Caller Experience
Developing Applications Using STKU-6 1:30 p.m. – 4:30 p.m.
System.Speech and SAPI on Greg Simsar, Vice President Speech Services, Syntellect
Windows Vista Eduardo Olvera, Senior Speech Technology Analyst, Syntellect
1:30 p.m. – 4:30 p.m. Have you called your own company recently? How would you rate that
experience? How would you identify and prioritize trouble spots? How would
Rob Chambers, Principal Development Lead and you go about improving them? If you’re looking for an intense, hands-on session
Architect, Microsoft about how to assess and improve your company's caller experience, this tutorial
Speech recognition and speech synthesis have come a long way at Microsoft is for you. Join us and your peers as we dial up a live 800-number and do a
in the past 10 years. The evolution of the developer APIs, the included TTS real-time assessment of the caller experience. Together we’ll benchmark the
and SR engines, and the integrated user experiences in Windows Vista will experience to see where the lucky company stacks up with current best practices
have a profound impact on the availability of Windows applications in the as well as the getHuman standard. Then you’ll witness a ''live'' evaluative
future. In this course, you will learn about both SAPI and System.Speech in a usability session to identify and pinpoint trouble spots, and together we’ll map
hands-on lab setting (bring your own laptop). Attendees with either COM and out how to go about improving them. The caller experience will include self-
C++ experience or managed code developers with C# experience will service, live-service, and the transition from one to the other.
experience Microsoft speech offerings for the desktop firsthand. (Attendees
will receive hardware specs and resources to download in advance.)
Enough with the Theory! STKU-7
Interested in using speech synthesis?
Let’s Write Some Prompts! Attend Session C102 for the latest details of new standards
1:30 p.m. – 4:30 p.m. for speech synthesis and Session E202 for tips and
Jenni McKienzie, VUI Designer, Travelocity techniques for using speech synthesis in your application.
There are lots of books, courses, and presentations on the principles of VUI
design. But when it comes time to put pen to paper and write prompts, it can
PRELIMINARY EXHIBITOR LIST
@International Services Interactions Syntellect
Apptera Intervoice Telus
Avaya iPing TuVox
Cisco IQ Services
Convergys Corp. Kirusa
CRM magazine Loquendo VocaLabs
Diaphonics LumenVox VoiceObjects, Inc.
Envox Worldwide Message Technologies Inc. VoiceVerified Inc.
Fluency Voice Technology NeoSpeech VoiceXML Forum
Laboratories Nexidia Voxify
GM Voices, Inc. Persay Ltd.
Walsh Media IVC
GyrusLogic, Inc. Product Support Solutions (PSS)
RSA, The Security Divison of EMC WebForPhone
IBM SimulScribe West Corporation
iFLYTEK Speech Technology magazine Witness Systems
For Information on sponsorships and exhibiting, please contact:
La Shawn Fugate or Sarah Fortney, 2628 Wilhite Court, Suite 100, Lexington, KY 40503
(As of 3/30/07) Toll Free: 877-993-9767 • Direct: 859-278-2223 • Fax: 859-278-7364
Hotel & Travel Information
Hotel Accommodations The Premier Pass Includes:
The New York Marriott Marquis is the official ◗ Participation in all Conference Sessions
conference hotel for SpeechTEK 2007. Discounted ◗ Admission to SpeechTEK University Courses
guest room rates at the Marriott Marquis have been ◗ Access to the Exhibit Hall
arranged for attendees through Meeting & Travel
Consultants, Inc. (MTC), the official housing bureau for ◗ Conference Materials
SpeechTEK. Please do not call the hotel directly. (The ◗ Lunch Breaks
rates are $275 single or double per night for
attendees who book reservations before August 3,
◗ Two Networking Receptions
2007.) Room blocks are subject to availability and Delegates are responsible for their own travel arrangements and
sales and occupancy tax, and therefore are not hotel accommodations.
guaranteed. SO, PLEASE BOOK EARLY!
4 easy ways to make your hotel reservation! Priority Discounts
◗ Online: www.mtcreservations.com Save up to $375 off the cost of your conference registration by
using the priority code that is on the mailing label of this brochure
◗ Phone: 732-549-3985/3986 when you register.
◗ Fax: 732-549-3987
◗ E-mail: firstname.lastname@example.org Registration Desk Hours
Sunday, August 19 . . . . . . . . . .4:00 p.m. – 7:00 p.m.
Conference Location ◗
New York Marriott Marquis Monday, August 20 . . . . . . . . . .7:00 a.m. – 7:00 p.m.
1535 Broadway Tuesday, August 21 . . . . . . . . . .7:30 a.m. – 5:30 p.m.
New York, NY 10036 Wednesday, August 22 . . . . . . .8:00 a.m. – 2:00 p.m.
Thursday, August 23 . . . . . . . . .8:00 a.m. – 1:30 p.m.
LaGuardia: Distance from hotel: 9 miles east; Exhibit Hours
taxi approximately $30. Monday, August 20 . . . . . . . . . .5:00 p.m. – 7:00 p.m.
JFK International: Distance from hotel: Grand Opening Reception
15 miles southeast; taxi approximately $45. Tuesday, August 21 . . . . . . . . .10:00 a.m. – 5:30 p.m.
Newark International: Distance from hotel:
15 miles west; taxi approximately $60. Wednesday, August 22 . . . . . .10:00 a.m. – 2:00 p.m.
✓ CHECK NOTE:The sponsors and management of SpeechTEK 2007 reserve the right to make necessary
changes in this program. Every effort will be made to keep presentations and speakers as
www.speechTEK.com represented. However, unforeseen circumstances may result in substitution of a presentation topic
and/or speaker. Information Today, Inc. assumes no liability for the acts of their suppliers nor for
for conference updates. the safety of any SpeechTEK 2007 participant while in transit to or from this event.The total liability
during the precise hours of the meeting will be limited to a refund of the delegate fee.
4 Easy Ways to Register
GO TO: PHONE: FAX: MAIL:
www.SpeechTEK.com 800-300-9868 or Registration form Registration form with
609-654-6266 with credit card # to: payment to:
When registering on the Web site,
please refer to the priority code 609-654-4309 Information Today, Inc.
above your name on your mailing 143 Old Marlton Pike
address label. Medford, NJ 08055
18 August 20–23, 2007 ◗ New York Marriott Marquis, New York
Registration EARLY RATE
LATE & ONSITE RATE
(After 7/20/07 )
❏ PREMIER PASS (Best Value) $1775 $1975 FREE Subscription to STM
MONDAY–THURSDAY $1598 $1778 Please fill out the following information.
INCLUDES: Admission to all SpeechTEK 2007 conference sessions, company workshops, lunches, exhibit hall,
keynotes, receptions and up to two Thursday SpeechTEK University workshops. ❏ YES! I want a FREE* subscription
Please choose your workshops below. to Speech Technology magazine.
❏ STKU-1 ❏ STKU-2 ❏ STKU-3 ❏ STKU-4 ❏ STKU-5 ❏ STKU-6 ❏ STKU-7 ❏ STKU-8 DELIVERY OPTIONS:
❏ PRINT ❏ DIGITAL ❏ BOTH
❏ CONFERENCE PASS $1595 $1795 *Print subscription free to qualified U.S. subscribers.
MONDAY–WEDNESDAY $1436 $1616 Digital subscription free to all qualified subscribers.
INCLUDES: Admission to all SpeechTEK 2007 conference sessions, Overseas print subscribers please visit www.speechtech
company workshops, lunches, exhibit hall, keynotes, and receptions. mag.com/subscribe for subscriptions.
❏ ONE-DAY-ONLY PASS $795 $895
PLEASE SELECT ONE: $716 $806 Date: __________________________________
❏ Monday ❏ Tuesday ❏ Wednesday PLEASE SIGN TO CONFIRM YOUR SUBSCRIPTION
INCLUDES: Admission to one complete day of SpeechTEK 2007 activities. IF COMPLETING IN PERSON.
Are you authorized to request a subscription
❏ SpeechTEK University Workshops $295 $395 on this person’s behalf? ❏ Yes ❏ No
THURSDAY $266 $356 Do you provide administrative support?
Please choose your workshops below. ❏ Yes ❏ No
❏ STKU-1 ❏ STKU-2 ❏ STKU-3 ❏ STKU-4 ❏ STKU-5 ❏ STKU-6 ❏ STKU-7 ❏ STKU-8
❏ BRONZE PASS $345 $445 Title:___________________________________
MONDAY–WEDNESDAY $311 $401
INCLUDES: Admission to exhibit hall, company workshops, keynotes, For BPA International circulation audit purposes,
and receptions only. Does not include access to conference sessions or lunches. we are required to ask for a personal identifier.
What color are your eyes? ________________
❏ EXHIBIT HALL PASS $75 $150
MONDAY–WEDNESDAY FREE FREE Today’s date:____________________________
INCLUDES: Admission to exhibit hall, company workshops only.
No access to conference sessions, keynotes, or other events. Demographic Profile
This information is required for registration.
PRIORITY CODE____________ 1. Primary business activity at your location:
(Code is located above your name on your mailing label. Must be provided to receive the discount shown) Total $________ (please check only one)
1 ❏ Application Service Provider
2 ❏ Call Center
Contact Information 3 ❏ Finance, Banking, Accounting, Insurance
4 ❏ Governmental, Legal, Education
5 ❏ Healthcare
First Name ___________________________ Last Name_____________________________________ 6 ❏ Internet Service Provider
7 ❏ Manufacturing Computers and Computer Software
Company ___________________________________________________________________________ 8 ❏ Manufacturing (other than computer hardware or
9 ❏ Media, Marketing, Advertising, Consulting
Title ________________________________________________________________________________ 10❏ Speech Technology Developer
11❏ Speech Technology Integrator
Address _____________________________________________________________________________ 12❏ Technology Developer
13❏ Telecommunications, NetworkCarriers
City ________________________________________________________________________________ 14❏ VAR/Systems Integrator
15❏ Other: _____________________
State/Province _________________Postal Code _______________________Country _____________ 2. Your job description: (please check only one)
1 ❏ C Level/Chairman/President/Owner
E-Mail_______________________________________________________________________________ 2 ❏ EVP/VP/Manager
3 ❏ Educator/Student
Phone _______________________________Fax ____________________________________________ 4 ❏ Engineer/Developer
5 ❏ Investor
6 ❏ Other: ______________________
Payment Information 3. Speech Technology Utilized: (please check only one)
Check or credit card number must Check number enclosed, in U.S. funds, made 1 ❏ Automatic Speech Recognition
2 ❏ Desktop
accompany conference registration form. payable to Information Today Inc. $ 3 ❏ Embedded Applications
4 ❏ Internet
❏ MasterCard ❏ VISA ❏ AMEX ❏ Discover 5 ❏ Telephony
6 ❏ Text-to-Speech
Card Holder’s Name: ___________________________________________________________ 7 ❏ Speaker Verification
8 ❏ Wireless/Mobile
Credit Card Number: __________________________________Expiration Date: __________ 9 ❏ None
10❏ Other: ____________________
Signature: _______________________________________________ Date:________________ 4. Cost of speech technology products which you buy,
specify, approve, sell, recommend, resell or
❏ Check here to receive FREE weekly e-mail news updates from Speech Technology magazine. 1 ❏ Over $10 million
❏ Check here to receive FREE Event Updates 2 ❏ $5 million to $9,999,999
3 ❏ $1 million to $4,999,999
CONFIRMATION: All registrants will receive confirmation of their registration by mail. Registration packets may be 4 ❏ $500,000 to $999,999
5 ❏ Less than $499,999
picked up at the on-site registration desk beginning Monday, August 20 at 4:00 p.m.
6 ❏ None of the above
CANCELLATION POLICY: Written cancellations received before 7/20/2007 will be accepted subject to a service
charge of $50. Subsequent cancellations are liable for the full conference registration fee. Substitutions are
permitted but must be made in writing to email@example.com or fax at 609-654-4309. FOR OFFICE USE ONLY
NOTE: All prices are per person. Faculty and schedules are subject to change; registrants should visit the Web site Responded by: ❏ Fax ❏ E-Mail ❏ Phone
at www.SpeechTEK.com to view specific schedules. ❏ Internet ❏ Postal Service Staff Initials________ 19
August 20–23, 2007
New York Marriott Marquis
New York, NY
At SpeechTEK 2007, you will:
◗ Get practical advice for planning and running
speech technology projects
◗ Learn techniques for optimizing existing
◗ Hear customer case studies and evaluations
SAVE UP TO $375!
of products and services
◗ Experience unparalleled opportunities to
network with peers
◗ Listen to multiple viewpoints on controversial
topics and practices
◗ Attend new advanced training courses for
143 Old Marlton Pike • Medford, NJ 08055 LEXINGTON, KY