Mutimedia Processing

Numbering Code U-ENG29 39140 LJ12 Year/Term 2022 ・ Second semester
Number of Credits 2 Course Type Lecture
Target Year Target Student
Language Japanese Day/Period Wed.1
Instructor name KAWAHARA TATSUYA (Graduate School of Informatics Professor)
NAKAMURA YUUICHI (Academic Center for Computing and Media Studies Professor)
MORI SHINSUKE (Academic Center for Computing and Media Studies Professor)
Outline and Purpose of the Course This course provides an overview of technologies to handle, analyze, recognize and generate a variety of information media or pattern data such as image, speech and text.
Course Goals to master basic methods to deal with image, speech and text, and also processing of their analysis, recognition and synthesis.
Schedule and Contents Speech processing (Kawahara)
1. Information in speech and music
2. Speech analysis
3. Speech recognition and synthesis
4. Spoken dialogue systems

Natural language processing (Mori)
5. Natural language analysis
6. Language model and Kana-Kanji conversion
7. Machine translation and Question Answering

Image Processing (Nakamura)
8. Composition and handling of image media
9. Color and perception
10. Signal Processing and Filtering (1): Basics of Filtering
11. Signal processing and filtering (2): feature extraction
12. Projection and reflection models and computer graphics
13. 3-D Perception and Computer Vision
14. Image recognition and neural networks

15. Examination and Feedback
Evaluation Methods and Policy Based on the examination following the course
Course Requirements None
Study outside of Class (preparation and review) Exercises included in lecture slides.
Textbooks Textbooks/References Lecture slides are provided via PandA CMS.
PAGE TOP