Presentation | 1995/10/27 A Real-time Expression Modification System Driven by Voice : "Better Face Communication" at SIGGRAPH'95 Shigeo MORISHIMA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | A synchronization between voice and exppression image given by personified vertual agent and animation character is a very important theme recently. Expecially, there are many reports about a lip sync that synchronizes lip motion and voice. In this paper, a real-time lip sync method for communication system is presented. A spectrum information is calculated form natural voice captured by microphone, and then parameters are converted to a mouth feature parameters based on neural network. A 3D wire frame model is modified by this parameters, a texture of a person is projected onto this model, and the facial expression image is coming out. This algorithm was implemented on a graphics workstation as a real-time system. After capturing a frontal static image and a few voice data of any visitor, he can control his own lip motion and facial expression by himself in this prototype system. This was presented at interactive demonstration in SIGGRAPH'95 and was evaluated. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Virtual Agent / Real-time Face Synthesis / Media Conversion / Lip Sync / 3D Model / Intelligent Communication |
Paper # | MVE95-45 |
Date of Issue |
Conference Information | |
Committee | MVE |
---|---|
Conference Date | 1995/10/27(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 Expression Modification System Driven by Voice : "Better Face Communication" at SIGGRAPH'95 |
Sub Title (in English) | |
Keyword(1) | Virtual Agent |
Keyword(2) | Real-time Face Synthesis |
Keyword(3) | Media Conversion |
Keyword(4) | Lip Sync |
Keyword(5) | 3D Model |
Keyword(6) | Intelligent Communication |
1st Author's Name | Shigeo MORISHIMA |
1st Author's Affiliation | Faculty of Engineering, SElKEl University() |
Date | 1995/10/27 |
Paper # | MVE95-45 |
Volume (vol) | vol.95 |
Number (no) | 345 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |