Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

University of Waterloo

$35,000.00

Towards the Inclusive Design of Conversational Voice Interfaces for Underrepresented Users

EF 2023-24

Résumé
Artificially intelligent (AI) computer agents such as Amazon Alexa, that use voice user interfaces (VUIs), are often marketed as helpful to underrepresented users such as older adults (OAs). Yet research suggests that not only OAs do not fully benefit from such technologies and that adoption levels are low, but in fact the design of such novel interfaces may effectively lead to OAs becoming "digitally marginalized" when services shift to being primarily offered through such platforms. The commercial success of VUIs prompted the transition of many essential services (e.g. financial, health) or that of several social applications from desktop or mobile to "voice first" interfaces. This is facilitated by recent algorithmic advances such as deep learning and its application to voice recognition. However, this rapid transformation of the commercial space is currently outpacing several threads of research in this space, such as those focused on the interface design considerations. This creates gaps in our knowledge about how best to design VUIs that are adoptable by underrepresented users such as OAs. These gaps encompass several key aspects of designing inclusive interfaces: usability issues, socio-cultural and personal models of interaction (e.g. perception, trust), design principles, or the specific implementation of functional aspects of the underlying technology. Failure to properly consider such factors may result in VUIs further entrenching the algorithmic discrimination that affected other AI applications or simply result in lower adoption of such potentially-beneficial technologies by OAs. As such, I plan to conduct HCI research on the design considerations to be followed when implementing VUIs that are inclusive of underrepresented groups such as OAs. I focus primarily on VUIs that are conversational (such as seen in e.g. smart speakers or mobile voice assistants) as the most available in the consumer market. In particular, I plan to: investigate the human and socio-technical factors that may affect the adoption of VUIs by OAs, adapt Human-Computer Interaction (HCI) design approaches to address these issues, and develop appropriate technical resources (from heuristic design guidelines to training corpora) for improving the adoptability of VUIs by OAs. The proposed research agenda will focus on two example application areas that are relevant to OAs: social interactions and essential services (e.g. financial). Through a mixed-method approach, I aim to bring contribution to A) methodology, in the form of new HCI approaches and resources to designing inclusive interactive intelligent interface such as VUIs, B) design, filling in a significant gap in the design of VUIs for marginalized users such as OAs, and C) implementation, in the form of improvements to the development of VUIs (design guidelines, training corpora, etc.) to better fit OAs' socio-cultural and information practices.
Programme
Discovery Grants Program - Individual
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2022-05310
Name nom
Munteanu, Cosmin
Department département
Systems Design Engineering - Systems Design Engineering
Organization id
33
Institution établissement
University of Waterloo
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2022
Award amount
35000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
2801
Research subject group en
Artificial intelligence
Research subject group fr
Natural language and speech understanding
Research subject en
Intelligence artificielle
Research subject fr
Langage naturel et reconnaissance de la parole
Application title
Towards the Inclusive Design of Conversational Voice Interfaces for Underrepresented Users
Keyword
Accessible Interfaces; Conversational User Interaction; Inclusive Interfaces; Marginalized Users; Older Adults; User-Centred Design; Voice Interaction
Application summary
Artificially intelligent (AI) computer agents such as Amazon Alexa, that use voice user interfaces (VUIs), are often marketed as helpful to underrepresented users such as older adults (OAs). Yet research suggests that not only OAs do not fully benefit from such technologies and that adoption levels are low, but in fact the design of such novel interfaces may effectively lead to OAs becoming "digitally marginalized" when services shift to being primarily offered through such platforms. The commercial success of VUIs prompted the transition of many essential services (e.g. financial, health) or that of several social applications from desktop or mobile to "voice first" interfaces. This is facilitated by recent algorithmic advances such as deep learning and its application to voice recognition. However, this rapid transformation of the commercial space is currently outpacing several threads of research in this space, such as those focused on the interface design considerations. This creates gaps in our knowledge about how best to design VUIs that are adoptable by underrepresented users such as OAs. These gaps encompass several key aspects of designing inclusive interfaces: usability issues, socio-cultural and personal models of interaction (e.g. perception, trust), design principles, or the specific implementation of functional aspects of the underlying technology. Failure to properly consider such factors may result in VUIs further entrenching the algorithmic discrimination that affected other AI applications or simply result in lower adoption of such potentially-beneficial technologies by OAs. As such, I plan to conduct HCI research on the design considerations to be followed when implementing VUIs that are inclusive of underrepresented groups such as OAs. I focus primarily on VUIs that are conversational (such as seen in e.g. smart speakers or mobile voice assistants) as the most available in the consumer market. In particular, I plan to: investigate the human and socio-technical factors that may affect the adoption of VUIs by OAs, adapt Human-Computer Interaction (HCI) design approaches to address these issues, and develop appropriate technical resources (from heuristic design guidelines to training corpora) for improving the adoptability of VUIs by OAs. The proposed research agenda will focus on two example application areas that are relevant to OAs: social interactions and essential services (e.g. financial). Through a mixed-method approach, I aim to bring contribution to A) methodology, in the form of new HCI approaches and resources to designing inclusive interactive intelligent interface such as VUIs, B) design, filling in a significant gap in the design of VUIs for marginalized users such as OAs, and C) implementation, in the form of improvements to the development of VUIs (design guidelines, training corpora, etc.) to better fit OAs' socio-cultural and information practices.