Multimedia include many kinds of media, such as audio, speech, still images, video, texts, outputs from various sensors. This course first teaches signal processing, pattern recognition, and information retrieval for speech, images, and video. It then teaches signal processing and semantic analysis for various mobile sensors which form the Internet of Things (IoT). This course facilitates students' understanding of multimedia technology and development their ability of multilateral ways of thinking.
At the end of this course, students will be able to explain the multimedia technology and to design a system using multimedia.
speech analysis, speech recognition, speech synthesis, image recognition, gesture recognition, video information retrieval, mobile sensor, behavior understanding
|Intercultural skills||Communication skills||✔ Specialist skills||Critical thinking skills||Practical and/or problem-solving skills|
At the beginning of each class, basic principles and fundamental strategies are explained.
Towards the end of the class, case studies and application examples are introduced.
|Course schedule||Required learning|
|Class 1||Speech recognition: overview||Explain in the class.|
|Class 2||Speech analysis||Explain in the class.|
|Class 3||DP matching||Explain in the class.|
|Class 4||Hidden Markov model||Explain in the class.|
|Class 5||Language Modeling||Explain in the class.|
|Class 6||Speech recognition system||Explain in the class.|
|Class 7||Image analysis||Explain in the class.|
|Class 8||Image recognition||Explain in the class.|
|Class 9||Video analysis||Explain in the class.|
|Class 10||Mobile sensing||Explain in the class.|
|Class 11||Activity recognition||Explain in the class.|
|Class 12||GPS location analytics||Explain in the class.|
|Class 13||Wireless indoor localization||Explain in the class.|
|Class 14||Crowd sensing||Explain in the class.|
Three reports 90% (@30%), exercise (10%)
Students are required to have the knowledge on computer science of undergraduate levels.