Next Article in Journal
A Framework for Stakeholders’ Involvement in Digital Productions for Cultural Heritage Tourism
Previous Article in Journal
Inter- and Transcultural Learning in Social Virtual Reality: A Proposal for an Inter- and Transcultural Virtual Object Database to be Used in the Implementation, Reflection, and Evaluation of Virtual Encounters
 
 
Article

Is Natural Necessary? Human Voice versus Synthetic Voice for Intelligent Virtual Agents

School of Computing, Macquarie University, 4 Research Park Dr, Macquarie Park, NSW 2113, Australia
*
Author to whom correspondence should be addressed.
Academic Editors: Alexey Karpov and Heysem Kaya
Multimodal Technol. Interact. 2022, 6(7), 51; https://doi.org/10.3390/mti6070051
Received: 12 April 2022 / Revised: 20 June 2022 / Accepted: 22 June 2022 / Published: 27 June 2022
The use of intelligent virtual agents (IVA) to support humans in social contexts will depend on their social acceptability. Acceptance will be related to the human’s perception of the IVAs as well as the IVAs’ ability to respond and adapt their conversation appropriately to the human. Adaptation implies computer-generated speech (synthetic speech), such as text-to-speech (TTS). In this paper, we present the results of a study to investigate the effect of voice type (human voice vs. synthetic voice) on two aspects: (1) the IVA’s likeability and voice impression in the light of co-presence, and (2) the interaction outcome, including human–agent trust and behavior change intention. The experiment included 118 participants who interacted with either the virtual advisor with TTS or the virtual advisor with human voice to gain tips for reducing their study stress. Participants in this study found the voice of the virtual advisor with TTS to be more eerie, but they rated both agents, with recorded voice and with TTS, similarly in terms of likeability. They further showed a similar attitude towards both agents in terms of co-presence and building trust. These results challenge previous studies that favor human voice over TTS, and suggest that even if human voice is preferred, TTS can deliver equivalent benefits. View Full-Text
Keywords: embodied conversational agent; stress management; voice; text-to-speech; co-presence; trust; working alliance embodied conversational agent; stress management; voice; text-to-speech; co-presence; trust; working alliance
Show Figures

Figure 1

MDPI and ACS Style

Abdulrahman, A.; Richards, D. Is Natural Necessary? Human Voice versus Synthetic Voice for Intelligent Virtual Agents. Multimodal Technol. Interact. 2022, 6, 51. https://doi.org/10.3390/mti6070051

AMA Style

Abdulrahman A, Richards D. Is Natural Necessary? Human Voice versus Synthetic Voice for Intelligent Virtual Agents. Multimodal Technologies and Interaction. 2022; 6(7):51. https://doi.org/10.3390/mti6070051

Chicago/Turabian Style

Abdulrahman, Amal, and Deborah Richards. 2022. "Is Natural Necessary? Human Voice versus Synthetic Voice for Intelligent Virtual Agents" Multimodal Technologies and Interaction 6, no. 7: 51. https://doi.org/10.3390/mti6070051

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop