This paper describes the user-centered design of ALADIN, a speech recognition system targeted at people with physical disabilities, many of who also have speech impairments. ALADIN is a self-learning system, designed to allow users to use their own specific words and sentences, adapting itself to the speech characteristics of the user. The test iterations described in this paper focus on the interaction issues associated with adaptive speech technology. We investigated how users address a speech interface, observing the amount of variation in wording and sentence structure, and determining the specific requirements of speech-impaired users. We discuss how the results have informed the design of ALADIN, and how these design choices aligned with the technical implementation of the speech system.
No takes yet. Share an insight, caveat, or question.
Derboven et al. (2014) studied this question.