| Project/Area Number |
21700577
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Rehabilitation science/Welfare engineering
|
|---|
| Research Institution | Nagoya University |
|---|
Principal Investigator |
TAKEUCHI Yoshinori Nagoya University, 情報連携統括本部情報戦略室, 准教授 (60324464)
|
|---|
| Project Period (FY) |
2009 – 2010
|
| Project Status |
Completed (Fiscal Year 2010)
|
| Budget Amount *help |
¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
Fiscal Year 2010: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2009: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
|---|
| Keywords | 情報システム / ユーザインタフェース / 福祉情報工学 / 情報保障 |
|---|
| Research Abstract |
In this research, we propose a method solving the problem of captioning when an instructor utters a mathematical formula with different interpretations, using remote PC transcription system. We adopt an approach to extract an image corresponding uttered mathematical formula from lecture slides. This method uses a fact that a instructor usually points a mathematical formula on the slide when he/she utters it. We use speech recognition software to detect pronunciations of mathematical formula. Then, we extract pointing gestures from the images of the lecture. We have conducted experiments by using recorded audio-visual signals from a real lecture. Experimental result shows that recall ratio is about 70% and relevance ratio 91%.
|
