Paper Info
Title
Voice Interaction for Augmented Reality Navigation Interfaces with Natural Language Understanding
Abstract
Voice interaction with natural language understanding (NLU) has been extensively explored in desktop computers, handheld devices, and human-robot interaction. However, there is limited research into voice interaction with NLU in augmented reality (AR). There are benefits of using voice interaction in AR, such as high naturalness and being hands-free. In this project, we introduce VOARLA, an NLU-powered AR voice interface, which navigate courier driver delivery a package. A user study was completed to evaluate VOARLA against an AR voice interface without NLU to investigate the effectiveness of NLU in the navigation interface in AR. We evaluated from three aspects: accuracy, productivity, and commands learning curve. Results found that using NLU in AR increases the accuracy of the interface by 15%. However, higher accuracy did not correlate to an increase in productivity. Results suggest that NLU helped users remember the commands on the first run when they were unfamiliar with the system. This suggests that using NLU in an AR hands-free application can make the learning curve easier for new users.
Year
DOI
Venue
2020
10.1109/IVCNZ51579.2020.9290643
2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ)
Keywords
DocType
ISSN
Augmented Reality,speech recognition,natural language understanding (NLU),speech interaction,artificial intelligence,intelligent interface
Conference
2151-2191
ISBN
Citations 
PageRank 
978-1-7281-8580-4
0
0.34
References 
Authors
9
5
Name
Order
Citations
PageRank
Junhong Zhao1277.02
Christopher James Parry200.34
Rafael Kuffner dos Anjos3128.79
Craig Anslow414025.77
Taehyun Rhee520919.42