Key points are not available for this paper at this time.
Conversational Voice User Interfaces (CVUIs) are widely used in commercial applications such as personal assistants. CVUIs are beneficial for most users as they enable interaction through speech and natural language. However, recent studies indicate that underrepresented user groups, such as individuals with speech impairments and specifically those with Down syndrome, face challenges in using voice commands to control CVUIs. The anatomical and physiological differences affecting the voice, speech, fluency, and prosody of users with Down syndrome hinder their experience with CVUIs. This article presents the results of 43 papers related to the use of voice user interfaces supporting individuals with Down syndrome, showing that (1) the most used form factor for voice assistants are displays with or without speakers; (2) although most of the papers related to speech-to-text technologies are about datasets aimed at supporting speech recognition, most of them are created involving a small sample size; and (3) there is high interest in including individuals with Down syndrome in evaluation phases mainly to address their communication skills, therapy, and general assistance. We discuss the design and evaluation stages, as well as how to make CVUIs more accessible and inclusive for individuals with Down syndrome in particular and neurodiverse users in general.
Cibrian et al. (Fri,) studied this question.