| Presentation | 2023-03-23 Mouth shape recognition for speech scene of patients with intractable neurological diseases Yuki Gondo, Yuya Nakamura, Takeshi Saitoh, Kazuyuki Itoh, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We are working on mouth shape recognition, which is the basic technology for the development of mouth-shape character method which is used as an alternative communication method for patients with intractable neurological diseases. It is important to collect utterance scenes of patients in order to proceed with research, and in this paper, we collected utterance scenes of six mouth forms from 31 patients, which is significantly more than the previous research. Using the collected utterance scenes, we worked on a mouth shape recognition experiment using Vision Transformer. In addition, multifaceted analyzes were conducted, including the number of days shooted and recognition accuracy corresponding to the number of data, the relationship between recognition accuracy with the number of elapsed days, and the tendency of recognition for each patient. This paper summarizes these analysis results. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Mouth shape recognition / patient with intractable neurological diseases / Vision Transformer |
| Paper # | WIT2022-24 |
| Date of Issue | 2023-03-15 (WIT) |
| Conference Information | |
| Committee | WIT / IPSJ-AAC |
|---|---|
| Conference Date | 2023/3/22(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Shinji Sakou(Nagoya Inst. of Tech.) / 小林 正朋(日本IBM) |
| Vice Chair | Tomohiro Amemiya(Univ. of Tokyo) |
| Secretary | Tomohiro Amemiya(Saitama Industrial Tech. Center) / (Teikyo Univ.) |
| Assistant | Minako Hosono(AIST) / Aki Sugano(Nagoya Univ.) / Tomoyasu Komori(NHK) |
| Paper Information | |
| Registration To | Technical Committee on Well-being Information Technology / Special Interest Group on Assistive & Accessible Computin |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Mouth shape recognition for speech scene of patients with intractable neurological diseases |
| Sub Title (in English) | |
| Keyword(1) | Mouth shape recognition |
| Keyword(2) | patient with intractable neurological diseases |
| Keyword(3) | Vision Transformer |
| 1st Author's Name | Yuki Gondo |
| 1st Author's Affiliation | Kyushu Institute of Technology(kyutech) |
| 2nd Author's Name | Yuya Nakamura |
| 2nd Author's Affiliation | Kyushu Institute of Technology(kyutech) |
| 3rd Author's Name | Takeshi Saitoh |
| 3rd Author's Affiliation | Kyushu Institute of Technology(kyutech) |
| 4th Author's Name | Kazuyuki Itoh |
| 4th Author's Affiliation | National Rehabilitation Center for Persons with Disabilities(NRCPD) |
| Date | 2023-03-23 |
| Paper # | WIT2022-24 |
| Volume (vol) | vol.122 |
| Number (no) | WIT-450 |
| Page | pp.pp.27-31(WIT), |
| #Pages | 5 |
| Date of Issue | 2023-03-15 (WIT) |