Effects of Wording and Gendered Voices on Acceptability of Voice Assistants in Future Autonomous Vehicles

Abstract

Voice assistants in future autonomous vehicles may play a major role in supporting the driver during periods of a transfer of control with the vehicle (handover and handback). However, little is known about the effects of different qualities of the voice assistant on its perceived acceptability, and thus its potential to support the driver's trust in the vehicle. A desktop study was carried out with 18 participants, investigating the effects of three gendered voices and different wording of prompts during handover and handback driving scenarios on measures of acceptability. Participants rated prompts by the voice assistant in nine different driving scenarios, using 5-point Likert style items in a during and post-study questionnaire as well as a short interview at the end. A commanding/formally worded prompt was rated higher on most of the desirable measures of acceptability as compared to an informally worded prompt. The 'Matthew' voice used was perceived to be less artificial and more desirable than the 'Joanna' voice and the gender-ambiguous 'Jordan' voice; however, we caution against interpreting these results as indicative of a general preference of gender, and instead discuss our results to throw light on the complex socio-phonetic nature of voices (including gender) and wording of voice assistants, and the need for careful consideration while designing the same. Results gained facilitate the drawing of insights needed to take better care when designing the voice and wording for voice assistants in future autonomous vehicles. CCS CONCEPTS• Human-centered computing → Empirical studies in HCI.

Deceptive AI Ecosystems: The Case of ChatGPT

“…The CUI community has continuously demonstrated a strong inclination for addressing ethical aspects of emerging technologies, especially issues regarding smart home voice assistants' implications [20,33,36,37,60,61,66]. ChatGPT, encompassed within the significant themes of 'text-based conversational interfaces' and 'chatbots' at CUI, possesses tremendous potential to evolve and influence technologies within the realm of 'multimodal interaction involving speech, text, or other language-based interfaces'.…”

Who are CUIs Really For? Representation and Accessibility in the Conversational User Interface Literature

“…Using the conference proceedings in the ACM Digital Library, we analysed paper abstracts, introductions, and methodologies, comparing them against the themes and demographics from the original review paper. In total, we found eight papers (17%) exploring topics around accessibility [4,8,27], social interaction [6,11,12], and the performance of gender by CUIs [10,25]. By contrast, around half of the provocation papers at CUI 2022 explored questions related to ethics.…”

“…Two focused on expanding communication with CUIs to encompass speech acts and emotions [11,12], and one on the effect of accented synthetic speech on peoples' responses [6]. Finally, the two papers on performance of gender explored sensitivity when designing gender for voice interfaces [25] and user acceptability of speech with varying genderlinked characteristics [10].…”