| Presentation | 2009-09-11 Contribution of Visual Information to Speech Cognition Kazuhiro ITO, Kaname MOCHIZUKI, Hitoshi OHNISHI, Naoto NAKAMURA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | When we talk with somebody, not only the voice of speaker but also his or her facial expressions play an important role in mutual understanding. This report examined the contribution of visual information of speaker's face to speech cognition. In our experiment, participants were presented two types of materials: (1) voice only, (2) motion picture of speaker with voice and face under four different levels of background noise conditions and were asked to repeat precisely what speaker said. The results showed that accuracy of repeat was same or higher in the voice only material than motion picture when materials were presented without noise. But when the noise added, accuracy was higher in motion picture. The analysis of gaze tracking data showed that participants tended to look at speaker's eyes when the motion picture presented without noise, but they looked at speaker's mouth when noise added. These results clearly show the contribution of the visual information of speaker's face to speech cognition. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Audio-visual integration / Speech recognition / Gaze tracking |
| Paper # | CQ2009-34 |
| Date of Issue |
| Conference Information | |
| Committee | CQ |
|---|---|
| Conference Date | 2009/9/3(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Communication Quality (CQ) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Contribution of Visual Information to Speech Cognition |
| Sub Title (in English) | |
| Keyword(1) | Audio-visual integration |
| Keyword(2) | Speech recognition |
| Keyword(3) | Gaze tracking |
| 1st Author's Name | Kazuhiro ITO |
| 1st Author's Affiliation | Chiba Institute of Technology() |
| 2nd Author's Name | Kaname MOCHIZUKI |
| 2nd Author's Affiliation | Teikyo University |
| 3rd Author's Name | Hitoshi OHNISHI |
| 3rd Author's Affiliation | The Open University of Japan |
| 4th Author's Name | Naoto NAKAMURA |
| 4th Author's Affiliation | Chiba Institute of Technology |
| Date | 2009-09-11 |
| Paper # | CQ2009-34 |
| Volume (vol) | vol.109 |
| Number (no) | 191 |
| Page | pp.pp.- |
| #Pages | 4 |
| Date of Issue | |