SiMPE: Fourth Workshop on Speech in Mobile and
IBM India Research Lab
4,Block-C, Institutional Area
Vasant Kunj, New Delhi, India.
School of Computer Science
Carnegie Mellon University
Pittsburgh, PA 15213, USA.
Dept. of Computer Science
University of Tampere
A. L. Kun
Elec. and Comp. Engg.
Univ. of New Hampshire
New Hampshire, USA
With the proliferation of pervasive devices and the increase
in their processing capabilities, client-side speech processing
has been emerging as a viable alternative.
SiMPE 2009, the fourth in the series, will continue to ex-
plore issues, possibilities, and approaches for enabling speech
processing as well as convenient and effective speech and
multimodal user interfaces.
SiMPE 2009 is to increase the participation of speech/multimodal
HCI designers, and increase their interactions with speech
Multimodality got more attention in SiMPE 2008 than it
has received in the previous years. In SiMPE 2007 , the
focus was on developing regions. Given the importance of
speech in developing regions, SiMPE 2008 had “SiMPE for
developing regions” as a topic of interest. We think of this
as a key emerging area for mobile speech applications, and
will continue this in 2009 as well.
One of our major goals for
Categories and Subject Descriptors
H.5.2 [User Interfaces]: Voice I/O
Design, Human Factors, Experimentation, Performance
Speech Processing, Mobile Computing, Pervasive Comput-
1. BACKGROUND AND MOTIVATION
The proliferation of pervasive devices has stimulated the
development of applications that support ubiquitous access
via multiple modalities.Since the processing capabilities
of pervasive devices differ vastly, device-specific application
Copyright is held by the author/owner(s).
MobileHCI’09 September 15-18, 2009, Bonn, Germany
adaptation becomes essential. How does one do speech ap-
plication adaptation for pervasive devices with different re-
source (such as memory and power) constraints ?
Traditionally, voice-based applications are accessed using
dumb telephone devices through Voice Browsers that reside
on the server. With the increase in the processing capa-
bilities of pervasive devices, client-side speech processing is
emerging as a viable alternative. Client-side speech process-
ing leads to a reduction in server bottlenecks, round trip
costs, transmission errors as well as bandwidth and con-
nectivity requirements. The goal therefore is to leverage a
client’s capabilities to the fullest. Given the variety of per-
vasive clients, we need a flexible way of distributing speech
processing between the client and the server based on the
client’s capabilities and runtime considerations.
Given the penetration of mobile phones in emerging economies
(such as Africa, China and India), and that Voice-driven in-
terfaces to applications have been found to have immense
appeal for semi-literate and illiterate users , the need for
designing flexible, adaptive and robust voice UIs is immi-
Enabling conversational systems on pervasive devices will
require new models, algorithms, systems that are robust
across a variety of mobile and ubiquitous devices and dy-
namic and noisy environments. This will require novel meth-
ods for evaluating such systems. Several user-interface re-
lated questions will have to be answered.
1.1Goals of SiMPE
SiMPE has only two ambitious goals:
• To provide a platform that brings together researchers
from speech processing, algorithm design, application
development and UI design to fuel faster growth of this
• To pose interesting problems to this community that
will foster cross-pollination of ideas and hopefully de-
fine the course that SiMPE research should take over
the coming years.
2.TOPICS OF INTEREST
All areas that enable, optimise or enhance Speech in mo-
bile and pervasive environments and devices. Possible areas
include, but are not restricted to:
• Speech interfaces/applications for Developing Regions
• Speech User Interaction in Cars
• Multilingual Speech Recognition
• Robust Speech Recognition in Noisy and Resource-
• Memory/Energy Efficient Algorithms
• Multimodal User Interfaces for Mobile Devices
• Protocols and Standards for Speech Applications
• Distributed Speech Processing
• Mobile Application Adaptation and Learning
• Prototypical System Architectures
• User Modelling
2.1 Seed Questions
1. How to do speech recognition in noisy environments ?
2. What are the usability issues with speech on mobile
3. Are there efficient ways of enabling voice search on the
4. How to make voice UIs flexible and adaptive ?
5. Are there any novel and easier ways to handle multiple
languages and dialects ?
6. How do we construct speech systems with small foot-
prints of memory and power consumption ?
7. How can we distribute processing more efficiently given
the increased available computing power on handhelds
? How do we trade this off with a remote server to
conserve energy ?
8. How do we make such devices adapt automatically to
the user, task and environment ?
9. What kind of components and frameworks should be
built to enable rapid application creation ?
10. How can we leverage context (such as location) to
make more intelligent UIs that reduce the ‘cognitive
burden’ of semi-literate/illiterate users ?
11. How can we design scalable speech applications?
12. How to design speech interfaces that are safe and ro-
bust for using in cars?
3. INTENDED AUDIENCE
This multi-disciplinary burgeoning area invites researchers
interested in any aspect of the intersection of Speech pro-
cessing and Mobile computing — speech recognition, speech
synthesis, multimodal interfaces, mobile HCI, distributed
speech processing, mobile applications, voice user interface
design, memory/energy efficient algorithms, UI design — to
meet and pave the way forward. We anticipate a good mix
of international industrial and academic participation which
should lead to lively discussions.
4.AGENDA AND SCHEDULE
We will advertise the workshop on several mailing lists,
the SiMPE wiki, as well as the SiMPE website. Over the
last two years, we have created a mailing list of about 200
researchers working in this area.
Committee has already been decided.
Same as last year, accepted papers will be made available
to all participants before the conference, to encourage more
The tentative Program
On September 15, 2009
We are proposing to have a full-day workshop. This will
be broken into 4 sessions, where three sessions will be based
on a theme: core speech processing, applications and usabil-
ity. The fourth session will be divided into two parts. In the
first part, we will review the state-of-the-art of SiMPE. The
second part will address methods and pose problems to fos-
ter collaboration between the speech community and the UI
designers. At the end of each session, there will be a short
discussion and a summary statement by the session panel.
We will summarise the findings of the workshop on the
SiMPE webpage  and encourage the participants to con-
tribute to the SiMPE wiki . Depending upon the type of
submissions, we will try to identify an appropriate venue for
publishing the papers.
• Amit Anil Nanavati, IBM Research, India Research
• Nitendra Rajput, IBM Research, India Research Lab-
• Alexander I. Rudnicky, Carnegie Mellon University.
• Markku Turunen, University of Tampere, Finland.
• Andrew Kun, University of New Hampshire, USA.
• Tim Paek, Microsoft Research, USA.
• Ivan Tashev, Microsoft Research, USA.
6. PROGRAMME COMMITTEE Download full-text
• Abeer Alwan, UCLA, USA.
• Alex Acero, Microsoft, USA.
• Matt Jones, Swansea University, UK.
• Anirudha Joshi, IIT Bombay, India.
• Yoon Kim, Novauris Technologies, USA.
• Lars Bo Larsen, Aalborg University, Denmark.
• Gary Marsden, Univ. of Cape Town, South Africa.
• Michael McTear, University of Ulster, Ireland.
• Shrikanth S. Narayanan, USC, USA.
• Sharon Oviatt, Incaa Designs, USA.
• Antonio M. Peinado, Universidad de Granada, Spain.
• Ian Pitt, University College Cork, Ireland.
• Jahanzeb Sherwani, CMU, USA.
• Yaxin Zhang, Nuance Communications, China.
 ITU World Telecommunication Indicators Database.
 T. S. Parikh and E. D. Lazowska. Designing an
Architecture for Delivering Mobile Information Services
to the Rural Developing World. In Proc. Intl. Conf. on
World Wide Web (WWW), May 2006.