Jihyun Kim
ABSTRACT
We aimed at investigating the effects of error recovery strategy that could enable the drivers to recover from the non-understanding error when interacting with the in-vehicle voice user interface (VUI). An experiment using a driving simulator was conducted with forty-seven participants who performed driving tasks with the VUI. One of three different error recovery strategies (ask repeat, re-prompt, and you can say) was suggested to recover from the non-understanding errors. A subjective questionnaire and semi-structured interviews were used to collect the participants' workload, perceived reasons for errors, and preference. Results showed participants felt that 'you can say' was more difficult than the 're-prompt' condition. However, preferences of 'ask repeat' and 'you can say' were significantly higher than 're-prompt' because the perceived reason for the non-understanding was 'input error' when the system used the 're-prompt' method. These findings provide insights into the design of the VUI in the context of driving.
- Dan Bohus and AIexander Rudnicky. 2005. Sorry, I Didn't Catch That! - An Investigation of Non-understanding Errors and Recovery Strategies. 6th SIGdial Workshop on Discourse and Dialogue. http://www.iscaspeech.org/archiveGoogle Scholar
- Julie Goldberg, Mari Ostendorf, and Katrin Kirchhoff. 2003. The Impact of Response Wording in Error Correction Subdialogs. In ISCA Tutorial and Research Workshop on Error Handling in Spoken Dialogue Systems. http://www.isca-speech.org/archiveGoogle Scholar
- Hwan Hwangbo, Seul Chan Lee, and Yong Gu Ji. 2016. Complexity Overloaded in Smart Car: How to Measure Complexity of In-vehicle Displays and Controls? Adjunct Proceedings of the 8th International Conference on Automotive User Interfaces and Interactive Vehicular Applications: 81--86. Google ScholarDigital Library
- Dasom Lee, Young June Sah, and Sangwon Lee. 2018. Improving Usability Perception of Error-Prone AI Speakers: Elaborated Feedback Mitigates Negative Consequences of Errors. International Journal of Human-Computer Interaction. Google ScholarCross Ref
- John D. Lee, Daniel V. McGehee, Timothy L. Brown, and Michelle L. Reyes. 2005. Collision Warning Timing, Driver Distraction, and Driver Response to Imminent Rear-End Collisions in a High-Fidelity Driving Simulator. Human Factors: The Journal of the Human Factors and Ergonomics Society 44, 2: 314--334. Google ScholarCross Ref
- Seul Chan Lee and Yong Gu Ji. 2019. Complexity of In-Vehicle Controllers and Their Effect on Task Performance. International Journal of Human-Computer Interaction 35, 1: 65--74. Google ScholarCross Ref
- Susan Mcroy. 1998. Preface: Detecting, repairing and preventing human --- machine miscommunication. International Journal of Human-Computer Studies 48, 5: 547--552. Google ScholarDigital Library
- Chelsea Myers, Anushay Furqan, Jessica Nebolsky, Karina Caro, and Jichen Zhu. 2018. Patterns for How Users Overcome Obstacles in Voice User Interfaces. Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems - CHI '18, January: 1--7. Google ScholarDigital Library
- David L Strayer, Jonna Turrill, James R Coleman, Emily V Ortiz, and Joel M Cooper. 2014. Measuring Cognitive Distraction in the Automobile II: Assessing In-Vehicle Voice-Based Interactive Technologies. Retrieved from http://web.csulb.edu/~rfritz/aaa-driving-study.pdfGoogle Scholar
- Amazon Web Services. 2019, Amazon Polly. Retrieved May 10, 2019 from https://aws.amazon.com/pollyGoogle Scholar
Index Terms
- "Why did this voice agent not understand me?": error recovery strategy for in-vehicle voice user interface
Recommendations
Interacting with the News Through Voice User Interfaces
Chatbot Research and DesignAbstractA key application area for voice user interfaces (VUIs) is news consumption, and there is a need to explore how such interactions are performed in practice. This paper presents a study exploring how novice users navigate the news through VUIs and ...
Qualitative Approaches to Voice UX
Voice is a natural mode of expression offered by modern computer-based systems. Qualitative perspectives on voice-based user experiences (voice UX) offer rich descriptions of complex interactions that numbers alone cannot fully represent. We conducted a ...
Understanding Differences between Heavy Users and Light Users in Difficulties with Voice User Interfaces
CUI '20: Proceedings of the 2nd Conference on Conversational User InterfacesVoice user interfaces (VUIs) are growing in popularity. At this stage of VUIs adoption, distinctions between heavy users and light users are becoming emerging challenge. Some studies have focused on investigating how general users interact with VUIs; ...
Comments