Talking head
This project explores the use of a 3D head model for lip sync animation, given an audio file and its phoneme segmentation data obtained from word-level transcription. A comparison is done with the traditional method of rendering a sequence of 2D images for animation, showing how using a 3D model can...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2011
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/44745 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| id |
sg-ntu-dr.10356-44745 |
|---|---|
| record_format |
dspace |
| spelling |
sg-ntu-dr.10356-447452023-03-03T20:24:44Z Talking head Koh, Hui Ling. Chng Eng Siong School of Computer Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Computer graphics This project explores the use of a 3D head model for lip sync animation, given an audio file and its phoneme segmentation data obtained from word-level transcription. A comparison is done with the traditional method of rendering a sequence of 2D images for animation, showing how using a 3D model can be advantageous. Research was done on how animators map all the phonemes into a set of visemes, and how software and modelling techniques can be used to blend these visemes to produce a talking head with realistic-looking mouth movements. Some commercial uses for a 3D talking head and suggestions for further enhancements are also discussed. Bachelor of Engineering (Computer Engineering) 2011-06-03T06:39:33Z 2011-06-03T06:39:33Z 2011 2011 Final Year Project (FYP) http://hdl.handle.net/10356/44745 en Nanyang Technological University 46 p. application/pdf |
| institution |
Nanyang Technological University |
| building |
NTU Library |
| continent |
Asia |
| country |
Singapore Singapore |
| content_provider |
NTU Library |
| collection |
DR-NTU |
| language |
English |
| topic |
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Computer graphics |
| spellingShingle |
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Computer graphics Koh, Hui Ling. Talking head |
| description |
This project explores the use of a 3D head model for lip sync animation, given an audio file and its phoneme segmentation data obtained from word-level transcription. A comparison is done with the traditional method of rendering a sequence of 2D images for animation, showing how using a 3D model can be advantageous. Research was done on how animators map all the phonemes into a set of visemes, and how software and modelling techniques can be used to blend these visemes to produce a talking head with realistic-looking mouth movements. Some commercial uses for a 3D talking head and suggestions for further enhancements are also discussed. |
| author2 |
Chng Eng Siong |
| author_facet |
Chng Eng Siong Koh, Hui Ling. |
| format |
Final Year Project |
| author |
Koh, Hui Ling. |
| author_sort |
Koh, Hui Ling. |
| title |
Talking head |
| title_short |
Talking head |
| title_full |
Talking head |
| title_fullStr |
Talking head |
| title_full_unstemmed |
Talking head |
| title_sort |
talking head |
| publishDate |
2011 |
| url |
http://hdl.handle.net/10356/44745 |
| _version_ |
1759853105103503360 |