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 we designed different personalities for voice assistants and compared them in a real world driving study. Voice assistants have become important for a wide range of use cases, yet current interfaces are using the same style of auditory response in every situation, despite varying user needs and personalities. To close this gap, we designed four assistant personalities (Friend, Admirer, Aunt, and Butler) and compared them to a baseline (Default) in a between-subject study in real traffic conditions. Our results show higher likability and trust for assistants that correctly match the user’s personality while we observed lower likability, trust, satisfaction, and usefulness for incorrectly matched personalities, each in comparison with the Default character. We discuss design aspects for voice assistants in different automotive use cases.



braun2019chi.jpg 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]