Support system of active learning for hearing impaired student by using 360 degree camera
| Project/Area Number |
26350300
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Educational technology
|
|---|
| Research Institution | Kinjo College |
|---|
Principal Investigator |
Seto Shuichi 金城大学短期大学部, その他部局等, 教授 (90196973)
|
|---|
| Co-Investigator(Renkei-kenkyūsha) |
KAWABE HIROYUKI 金城大学, 社会福祉学部, 教授 (60249167)
SHIMOMURA YUUKO 金城大学, 社会福祉学部, 教授 (70171006)
NAMBO HIDETAKA 金沢大学, 電子情報学系, 講師 (30322118)
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2016: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2015: ¥1,040,000 (Direct Cost: ¥800,000、Indirect Cost: ¥240,000)
Fiscal Year 2014: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | アクティブラーニング / 発話検出 / 聴覚障害学生 / 支援システム / パノラマカメラ |
|---|
| Outline of Final Research Achievements |
In this study, we cut out the face of a student sitting on a seat in a hearing impaired student and tried to detect the speaker from the mouth image. Hearing impaired students became possible to participate in active learning class through transparent HMD and found that it is effective for identifying speakers.
The probability that the speaker detection result could be correctly recognized as utterance during utterance from the mouth image by the method of inertia moment was 28.6%, and the probability of misrecognition when not speaking was 16.5%. It is understood that the recognition rate is still low, subjects tend not to speak with a big mouth opened, and there are many misrecognition as there are many laughs and nods etc.
In the future there is a necessity to study HMD which can be used without incongruous feeling even for wearing for a long time, and also to study natural language analysis by speech recognition at the same time
|
Report
(4 results)
Research Products
(6 results)
