CHI 97 Electronic Publications: Workshops
Speech User Interface Design Challenges
Amir Mane
AT&T Laboratories
101 Crawfords Corner Road
Holmdel, NJ 07733 USA
+1 908 949 7049
amir.mane@arch4.att.com
Susan Boyce
AT&T Laboratories
101 Crawfords Corner Road
Holmdel, NJ 07733 USA
+1 908 949 4651
sjboyce@att.com
Demetrios Karis
GTE Laboratories
40 Sylvan Road
Waltham, MA 02254 USA
+1 617 466 2153
dkaris@gte.com
Nicole Yankelovich
Sun Microsystems Laboratories
Two Elizabeth Drive
Chelmsford, MA 01824 USA
+1 508 442 0441
nicole.yankelovich@east.sun.com
Keywords
Automatic Speech Recognition, Natural Language
Processing
© 1997 Copyright on this material is held by the authors.
SUMMARY
There have been dramatic improvements during the last
decade in the performance of both automatic speech
recognition (ASR) systems and the computers on which
they run. Speaker independent recognition with an active
vocabulary of over 1,000 items is now possible even
under the difficult conditions imposed by the public
switched telephone network. The impressive raw
recognition power of commercial recognizers has led to
the development of a wide range of complex information,
call management, and transaction services that rely on
ASR. Despite this progress, it has become clear that
recognition performance in the lab is not a good predictor
of success in the field, and that extensive work on
dialogue design and human factors "tuning" is required
before most services can be used successfully by the
general population. Since recognizer capabilities
strongly influence user-interface design, and since these
capabilities have been changing rapidly over the past
decade, there is no clear body of knowledge that a
designer can turn to when developing new services that
rely on speech.
Last year we organized a CHI workshop of both
researchers and practitioners to discuss the current state
of ASR technology and its implications for design [1].
We discussed a wide range of topics, including dialogue
management, error handling, and design methodologies
and tools. The purpose of this year's workshop is to take
the next step and translate the ideas and techniques
discussed in 1996 into actual designs. The 1997
workshop will bring together a similar group of
researchers and practitioners to collaborate on solutions
to a variety of real-world speech interface design
problems.
Workshop participants will work in small groups to
develop solutions to three design exercises. The design
exercises will be derived from design problems submitted
in the position papers from workshop participants. The
chosen design exercises will focus on specific problems.
Examples of design problems that might be discussed
are:
- How can a list of items be effectively presented if the
list contains 3 items, 10 items, or more than 10
items?
- In a form-filling application, what is the best way to
present default choices?
- In multimodal applications that include speech, how
should input focus be determined? Should it be
based on the window system's scheme of focus or
some other scheme?
The small groups of participants will have an opportunity
to share their solutions with all the workshop participants
and critique the designs of others.
References
[1] Mane, A, Boyce, S, Karis, D. Yankelovich, N.
"Designing the User Interface for Speech Recognition
Applications." SIGCHI Bulletin, 1996, Volume 4, pp. 29-34.
CHI 97 Electronic Publications: Workshops
