IoT as a Service. Third International Conference, IoTaaS 2017, Taichung, Taiwan, September 20–22, 2017, Proceedings

Research Article

Using Nonverbal Information for Conversation Partners Inference by Wearable Devices

Download
180 downloads
  • @INPROCEEDINGS{10.1007/978-3-030-00410-1_22,
        author={Deeporn Mungtavesinsuk and Yan-Ann Chen and Cheng-Wei Wu and Ensa Bajo and Hsin-Wei Kao and Yu-Chee Tseng},
        title={Using Nonverbal Information for Conversation Partners Inference by Wearable Devices},
        proceedings={IoT as a Service. Third International Conference, IoTaaS 2017, Taichung, Taiwan, September 20--22, 2017, Proceedings},
        proceedings_a={IOTAAS},
        year={2018},
        month={10},
        keywords={Conversational partner inference Nonverbal information Social interaction analysis Wearable devices},
        doi={10.1007/978-3-030-00410-1_22}
    }
    
  • Deeporn Mungtavesinsuk
    Yan-Ann Chen
    Cheng-Wei Wu
    Ensa Bajo
    Hsin-Wei Kao
    Yu-Chee Tseng
    Year: 2018
    Using Nonverbal Information for Conversation Partners Inference by Wearable Devices
    IOTAAS
    Springer
    DOI: 10.1007/978-3-030-00410-1_22
Deeporn Mungtavesinsuk1,*, Yan-Ann Chen2,*, Cheng-Wei Wu1,*, Ensa Bajo1,*, Hsin-Wei Kao1,*, Yu-Chee Tseng1,*
  • 1: National Chiao Tung University
  • 2: Yuan Ze University
*Contact email: deeporn@nctu.edu.tw, chenya@saturn.yzu.edu.tw, cww0403@nctu.edu.tw, bajoensa@gmail.com, scott02308@gmail.com, yctseng@cs.nctu.edu.tw

Abstract

In this paper, we propose a framework called conversational partner inference using nonverbal information (abbreviated as CFN). We use the wrist-based wearable device that has an accelerometer sensor to detect the user’s hand movement. Besides, we propose three different methods, named , and , to integrate the detected movement behaviors with the sound data sensed by microphones to effectively infer conservational partners. In experiments, we collect real data to evaluate the proposed framework. The experimental results show that the accuracy of is better than and . Moreover, our approach shows higher accuracy than the state-of-the-art approach for conversational partner inference.