Robustness in Speech Based Interfaces:

Sharing the Tricks of the Trade
A CHI 2002 Workshop

Sunday April 21

Call for Participation


Workshop Goals

Workshop structure



Workshop proposal

Workshop papers

Preliminary schedule

Call for Participation

This one-day workshop will bring together researchers, designers, developers, and early adopters of speech based interface technology to study how greater user satisfaction can be obtained, not by increasing the accuracy of the underlying technology, but by applying the tricks and tools of the trade to create a more robust interaction.

The following questions will be discussed:

  • Which techniques can be used to increase robustness in speech-based interfaces?
  • What are the dimensions for distinguishing between different classes of speech based interfaces, and how do these dimensions impact the techniques discussed?

Each participant should submit a position paper (no more than three pages) describing lessons-learned and recommendations for increasing the robustness of a speech based interface. Ideally, the participants will describe two or more, "tricks of the trade" that they have tried and their experience with these. While it always is interesting to hear about and learn from success stories, perhaps even more can be learned from failure stories. By sharing knowledge about approaches tried without success, other workers and project teams need not walk down the same cul-de-sac.

Another important issue in learning from experience is knowing in which contexts the lessons learned apply and in which contexts they can not be applied. What we hope will emerge from the workshop is not only a list of 'this works' and 'this doesn't work', but also qualifications of these statements with respect to different conditions.

Extended deadline for submission of papers: Februari 15, 2002

Notification of acceptance: February 20, 2002

The papers will be selected based on their relevance and originality. All participants will be asked to come prepared to discuss their experience with the suggestions put forward in the other workshop position papers.

Position papers should include in addition to the description of the technique:
  • Characteristics and demographics of user population (e.g. naïve speech users);
  • Primary context of use;
  • Brief description of underlying technology;
  • Impact and results;


Jennifer Lai, IBM T.J. Watson Research Center
Nils Dahlbäck, Linköping University, Sweden
Arne Johnson, Linköping University, Sweden


Nils Dahlbäck
Department of Computer and Information Science
Linköping University
SE-581 83 Linköping, Sweden