ECE 417 Multimedia Signal Processing, Fall 2021

Characteristics of speech and image signals; important analysis and synthesis tools for multimedia signal processing including subspace methods, Bayesian networks, hidden Markov models, and factor graphs; applications to biometrics (person identification), human-computer interaction (face and gesture recognition and synthesis), and audio-visual databases (indexing and retrieval). Emphasis on a set of python machine problems providing hands-on experience.

4 undergraduate hours. 4 graduate hours. Prerequisites: (1) a course in digital signal processing, such as ECE 310 or ECE 401, and (2) a course in random variables, such as ECE 313 or CS 361 or STAT 400.

On-line Tools

  • CampusWire will be used for on-line question answering. If you need the code to enter this site, send an e-mail to the course instructors.

  • Gradescope will be used to submit all homework and machine problems, and will be used to grade exams. The code to enter this site will be posted on CampusWire.

  • Echo360 has the lectures from this semester.

  • MediaSpace has lectures from previous semesters, and some special videos.

  • Zoom is used for office hours. You can also watch lectures synchronously, remotely, via zoom. The URL for both lectures and office hours is the same, but is not posted here, to minimize the probability of zoombombers; please get it from the CampusWire.