Speaking of Trust -- Speech as a Measure of Trust

TL;DR

This paper proposes using speech cues as an objective, real-time measure of trust in human-robot interaction, aiming to improve robot calibration while addressing ethical concerns.

Contribution

It introduces a novel approach to quantify trust through speech analysis, enabling real-time calibration of robots in human interactions.

Findings

Speech cues can indicate trust levels in real-time

Potential for improved robot calibration based on trust measurement

Raises ethical considerations for trust monitoring

Abstract

Since trust measures in human-robot interaction are often subjective or not possible to implement real-time, we propose to use speech cues (on what, when and how the user talks) as an objective real-time measure of trust. This could be implemented in the robot to calibrate towards appropriate trust. However, we would like to open the discussion on how to deal with the ethical implications surrounding this trust measure.