| Presentation | 2024-03-02 Estimation of willingness to participate in other's conversation by using deep learning of facial expression measurements Kohei Yamamoto, Jiro Okuda, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent years, there has been much interest in developing agents that can join conversations among multiple people and activate the dialog. In order for such an agent to assist people in joining a conversation, it is necessary to estimate people's willingness to join in a conversation. In this study, in order to estimate a person's willingness to participate in a multi-person conversation, we conducted an experiment in which the willingness to participate in a conversation was continuously obtained in a four-person conversation and identified the characteristics of the stages of willingness to participate in a conversation. We constructed a deep neural network model that could estimate five levels of willingness to enter a conversation from the input data of distances between facial feature points of the people in the conversation. We evaluate the model and discuss its applicability to a conversation entry assistant agent. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Group Communication / Conversation-Aid Agent / Group Discussion Experiment / Facial Landmarks / Deep Neural Network / Estimation of Level of Willingness to Communicate |
| Paper # | HCS2023-92 |
| Date of Issue | 2024-02-24 (HCS) |
| Conference Information | |
| Committee | HCS |
|---|---|
| Conference Date | 2024/3/2(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Tokoha University(Shizuoka-Kusanagi Campus) |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Measuring and understanding interactions, and general |
| Chair | Tomoko Koda(Osaka Inst. of Tech.) |
| Vice Chair | Sachiko Takagi(Tokiwa Univ.) / Masashi Komori(Osaka Electro-Comm. Univ.) |
| Secretary | Sachiko Takagi(Ritsumeikan Univ.) / Masashi Komori(Kanagawa Univ.) |
| Assistant | HUANG HUNGHSUAN(Univ. of Fukuchiyama) / Jun Ichikawa(Shizuoka Univ.) / Kazuki Takashima(Tohoku Univ.) / Hiroto Saito(Tokyo Denki Univ.) / Ryo Ishii(NTT) |
| Paper Information | |
| Registration To | Technical Committee on Human Communication Science |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Estimation of willingness to participate in other's conversation by using deep learning of facial expression measurements |
| Sub Title (in English) | |
| Keyword(1) | Group Communication |
| Keyword(2) | Conversation-Aid Agent |
| Keyword(3) | Group Discussion Experiment |
| Keyword(4) | Facial Landmarks |
| Keyword(5) | Deep Neural Network |
| Keyword(6) | Estimation of Level of Willingness to Communicate |
| 1st Author's Name | Kohei Yamamoto |
| 1st Author's Affiliation | Kyoto Sangyo University(Kyoto Sangyo Univ.) |
| 2nd Author's Name | Jiro Okuda |
| 2nd Author's Affiliation | Kyoto Sangyo University(Kyoto Sangyo Univ.) |
| Date | 2024-03-02 |
| Paper # | HCS2023-92 |
| Volume (vol) | vol.123 |
| Number (no) | HCS-408 |
| Page | pp.pp.25-30(HCS), |
| #Pages | 6 |
| Date of Issue | 2024-02-24 (HCS) |