| Presentation | 1996/3/6 A Real-time Media Conversion from Speech to Image for Realizing Communication between Virtual Agent and User Naoya Miyashita, Jun Sato, Tatsumi Sakaguchi, Shigeo Morishima, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A facial image synthesis to generate a facial expression and conversation scenes is proceeding as the basic research to realize intelligent human interface or communication system. The communication with a virtual personized agent requires a real-time image synthesis and natural motion synthesis as well as synchronization between face image and voice to acheive a virtual face-to-face communication. This paper presents a real-time media conversion system to realize a high quality mouth shape control based on a captured voice signal at video rate. Moreover using this real-time media conversion technique, the system realizing communication between a virtual personized agent and a user in display is mentioned. Finally, to realize the interactive communication between the virtual personized agent and the user, analysis and synthesis of emotion speech is also mentioned. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Media Conversion / Neural Network / Emotion Speech |
| Paper # | MVE95-62 |
| Date of Issue |
| Conference Information | |
| Committee | MVE |
|---|---|
| Conference Date | 1996/3/6(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 | Media Experience and Virtual Environment (MVE) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A Real-time Media Conversion from Speech to Image for Realizing Communication between Virtual Agent and User |
| Sub Title (in English) | |
| Keyword(1) | Media Conversion |
| Keyword(2) | Neural Network |
| Keyword(3) | Emotion Speech |
| 1st Author's Name | Naoya Miyashita |
| 1st Author's Affiliation | Seikei University() |
| 2nd Author's Name | Jun Sato |
| 2nd Author's Affiliation | Seikei University |
| 3rd Author's Name | Tatsumi Sakaguchi |
| 3rd Author's Affiliation | Seikei University |
| 4th Author's Name | Shigeo Morishima |
| 4th Author's Affiliation | Seikei University |
| Date | 1996/3/6 |
| Paper # | MVE95-62 |
| Volume (vol) | vol.95 |
| Number (no) | 553 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |