What are the usability issues surrounding speech-based interaction systems, particularly in mobile and pervasive computing
What are the challenges in enabling speech as a modality for mobile interaction
What are the differences between the commercial ASR systems' accuracy claims and the needs of mobile interactive applications
How has the history of speech interface advancements led to the design processes that currently exist in industry, and the current problems that exist in developing such interfaces.
How do current heuristic guidelines apply to voice interfaces, and how are these influenced by engineering limitations
What are the current practices of industry VUI designers, and what are the tools currently in use
Learning about a new set of developed VUI guidelines, and applying them in practice
New to 2025 is a renewed focus on theoretical and practical review of most recent research on developing design guidelines for conversation user interfaces, as recent research has put efforts to explore. In particular, a new set of guidelines that have been developed and published in 2023, will be presented to participants, representing the most universally proposed principles of VUI design in academic literature, developed by the first-author. The review and exploration of these guidelines is meant to provide a springboard for the adoption and improvement for future tools and resources for speech interface development.
The course also includes several interactive, hands-on activities. The first activity will engage participants in proposing design alternatives for the error-handling interaction of a smartphone’s voice-based search assistant, based on an empirical assessment of the type of ASR errors exhibited (e.g. acoustic, language, semantic). The second activity will center around uncovering speech processing errors of a home-based personal assistant and designing interactions that maintain a positive user experience in the face of unexpected variations in speech processing accuracy. The third activity will center around hands-on practice with the guidelines presented during the presentations, with participants conducting a heuristic evaluation of a readily-available system (e.g Alexa, Google Assistant, Siri) as guided by these heuristic guidelines. This activity will allow include brainstorming about the benefits and limitations of the guidelines.