TY - GEN
T1 - Design of Room-Layout Estimator Using Smart Speaker
AU - Joya, Tomoki
AU - Ishida, Shigemi
AU - Mitsukude, Yudai
AU - Arakawa, Yutaka
N1 - Publisher Copyright:
© 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.
PY - 2022
Y1 - 2022
N2 - In this study, we propose a room-layout-based appliance control for voice user interfaces (VUIs), such as smart speakers. VUI-based appliance control requires a control command including which device to do what. However, we often experience an ambiguous target problem: the control target device in a control command is ambiguous because an ambiguous room name and demonstrative words are frequently used to specify the target device. To address this problem, we utilized a room layout to estimate the control target. A user implicitly aims to control devices in a room where they are. Therefore, we estimate the room where the user is now based on the room layout, which is estimated on a smart speaker, to determine the control target. In this study, we present the design of a room-layout estimator as the first step toward room-layout-based appliance control. The experimental evaluations conducted in our 1-bedroom smart house revealed that our room-layout estimator estimates room directions and room types with accuracies of 0.850 and 0.714, respectively.
AB - In this study, we propose a room-layout-based appliance control for voice user interfaces (VUIs), such as smart speakers. VUI-based appliance control requires a control command including which device to do what. However, we often experience an ambiguous target problem: the control target device in a control command is ambiguous because an ambiguous room name and demonstrative words are frequently used to specify the target device. To address this problem, we utilized a room layout to estimate the control target. A user implicitly aims to control devices in a room where they are. Therefore, we estimate the room where the user is now based on the room layout, which is estimated on a smart speaker, to determine the control target. In this study, we present the design of a room-layout estimator as the first step toward room-layout-based appliance control. The experimental evaluations conducted in our 1-bedroom smart house revealed that our room-layout estimator estimates room directions and room types with accuracies of 0.850 and 0.714, respectively.
UR - http://www.scopus.com/inward/record.url?scp=85125265893&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125265893&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-94822-1_2
DO - 10.1007/978-3-030-94822-1_2
M3 - Conference contribution
AN - SCOPUS:85125265893
SN - 9783030948214
T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
SP - 24
EP - 39
BT - Mobile and Ubiquitous Systems
A2 - Hara, Takahiro
A2 - Yamaguchi, Hirozumi
PB - Springer Science and Business Media Deutschland GmbH
T2 - 18th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services, MobiQuitous 2021
Y2 - 8 November 2021 through 11 November 2021
ER -