Designing Voice Assistant Personalities to Improve Automotive User Interfaces

This paper investigates personalized voice characters for incar speech interfaces. In particular, we report on how wedesigned different personalities for voice assistants and compared them in a real world driving study. Voice assistantshave become important for a wide range of use cases, yetcurrent interfaces are using the same style of auditory response in every situation, despite varying user needs andpersonalities. To close this gap, we designed four assistantpersonalities (Friend, Admirer, Aunt, and Butler) and compared them to a baseline (Default) in a between-subject studyin real traffic conditions. Our results show higher likabilityand trust for assistants that correctly match the user’s personality while we observed lower likability, trust, satisfaction,and usefulness for incorrectly matched personalities, eachin comparison with the Default character. We discuss designaspects for voice assistants in different automotive use cases.

Publication

Michael Braun, Anja Mainz, Ronee Chadowitz, Bastian Pfleging und Florian Alt.At Your Service: Designing Voice Assistant Personalities to Improve Automotive User Interfaces.In Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems. CHI '19. ACM, New York, NY, USA.[Download Bibtex]