Presentation 2004-12-17
Visual speech synthesis by selecting video subsequences from video corpus
Yukitaka NIMURA, Takayuki KITASAKA, Kensaku MORI, Yasuhito SUENAGA, Yasushi HIRANO, Kenji MASE, Tomoichi TAKAHASHl,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a visual speech synthesis method based on corpus. In the conventional method, the quality of the synthesized video sequence is significantly dependent on a morphing technique, because many morphed pictures are required to be inserted. The novel method obtains a synthesized video sequence from corpus by choosing and concatenating video subsequences. The method can treat the video subsequence with variable length, so the number of connecting points is fewer than that in the conventional method. The validity of the novel method was evaluated by the comparison experiment with the conventional method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) text to visual speech / corpus / talking heads / facial animation
Paper # PRMU2004-143
Date of Issue

Conference Information
Committee PRMU
Conference Date 2004/12/10(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Visual speech synthesis by selecting video subsequences from video corpus
Sub Title (in English)
Keyword(1) text to visual speech
Keyword(2) corpus
Keyword(3) talking heads
Keyword(4) facial animation
1st Author's Name Yukitaka NIMURA
1st Author's Affiliation Dept. of Computational Science and Engineering, Graduate of Engineering, Nagoya University:Advanced Telecommunications Research Institute International()
2nd Author's Name Takayuki KITASAKA
2nd Author's Affiliation Dept. of Media Science, Graduate School of Information Science, Nagoya University
3rd Author's Name Kensaku MORI
3rd Author's Affiliation Dept. of Media Science, Graduate School of Information Science, Nagoya University
4th Author's Name Yasuhito SUENAGA
4th Author's Affiliation Dept. of Media Science, Graduate School of Information Science, Nagoya University
5th Author's Name Yasushi HIRANO
5th Author's Affiliation Information Technology Center, Nagoya University
6th Author's Name Kenji MASE
6th Author's Affiliation Information Technology Center, Nagoya University:Advanced Telecommunications Research Institute International
7th Author's Name Tomoichi TAKAHASHl
7th Author's Affiliation Dept. of Information Engineering, Faculty of Science & Technology, Meijo University
Date 2004-12-17
Paper # PRMU2004-143
Volume (vol) vol.104
Number (no) 524
Page pp.pp.-
#Pages 6
Date of Issue