Social robots can help us in many areas: teaching, learning, taking care of us. Because they are designed to interact with humans, they are designed to put us at ease, and that includes the way they speak. But how should they speak? Some research suggests that people like robots to use a familiar accent or dialect, while others suggest the opposite.
“Surprisingly, people have mixed feelings about robots speaking a dialect: some like it, while others prefer a standard language,” said Katharina Kühne of the University of Potsdam, lead author of the study. In Frontiers of robotics and AI. “This made us think: Maybe it’s not just the robot, but also the people involved who shape these preferences.”
Talk about the speech
Many factors affect people’s comfort level with social robots. Bots work best when they seem more reliable and competent, and a human-like voice helps with that. But whether that speaking voice uses a dialect or standard form of language can impact the perception of its reliability or competence. Using a standard language is often considered more intelligent, but speaking in a dialect considered friendly or familiar can be comforting.
“Imagine a robot that can switch to a dialect,” Kühne said. “Now think about what is more critical in your interaction with a robot: feeling a connection (think of a friendly conversation in a nursing home) or perceiving it as competent (like in a service environment where standard language is important).”
I am a Berliner
To test the impact of dialect use on robot acceptance, the scientists recruited 120 people living in Berlin or Brandenburg to complete an online survey. They asked participants to watch videos in which a robot using a male human voice spoke either in standard German or in Berlin dialect, considered working-class and sometimes used by the media to give an informal, friendly impression.
“The Berlin dialect is generally understandable by most German speakers, including those who are not native German speakers but are fluent in the language,” Kühne explained.
The scientists asked participants to rate the robot’s reliability and competence, and to fill out a demographic questionnaire including age, gender, how long they had lived in Berlin, their fluency in the Berlin dialect, and how often they were using it. The survey automatically recorded the type of device participants used to view the videos: a phone, tablet or computer.
Speak the same language
There is a clear link between trustworthiness and competence, with higher perceived competence predicting higher perceived trustworthiness. In general, respondents preferred a standard German speaking robot. However, respondents who were more comfortable with the Berlin dialect preferred the robot-speaking dialect.
“If you speak a dialect well, you’re more likely to trust a robot that speaks the same way,” Kühne said. “It seems that people trust the robot more because they find a similarity in it.”
Respondents who used a phone or tablet rather than a computer to view the videos also tended to give lower ratings to the standard German-speaking robot. The scientists think this could be because small handheld devices meant that respondents were more distracted by videos and had a higher cognitive load, so the confidence signal of standard German had less impact.
“This leaves us with no clear evidence for or against the idea that people facing difficulties might find more comfort in social robots speaking in a familiar dialect,” Kühne said. “But if a robot uses standard language and it is essential that people perceive it as competent in the interaction, it could be beneficial to minimize cognitive load. We plan to dig deeper by testing cognitive load during conversations .”
Scientists have pointed out that speaking or understanding a dialect can be part of an identity within a group, allowing robots to take advantage of in-group prejudices: people tend to prefer robots that are more similar to them. one way or another. However, the prestige of a dialect can affect how it is received by the people who hear it.
“Context matters a lot in our conversations, and that’s why we plan to conduct more studies in real-world situations,” Kühne said.
More information:
“Ick bin een Berlina”: mastery of dialect has an impact on the reliability and assessment of a robot’s skills, Frontiers of robotics and AI (2024). DOI: 10.3389/frobt.2023.1241519
Quote: Speaking with a local accent could make social robots seem more trustworthy and competent, scientists say (January 29, 2024) retrieved January 29, 2024 from
This document is subject to copyright. Except for fair use for private study or research purposes, no part may be reproduced without written permission. The content is provided for information only.