While a wide range of work exists in automatic co-speech gesture generation, the automatic generation of meaningful (iconic) gestures is still an open issue. First, we will focus on speech-gesture generation and understanding from cognitive theoretical & empirical perspectives to dig into the topic. In this part, we will review the literature about predominant cognitive approaches to speech and gesture which forms the base of our seminar. Second, we will address the advanced applied perspective. Whereby, the primary focus of the seminar will be on the up-to-date approaches to automatic gesture generation.
The seminar will be structured as follows: for each session, 1-2 student presentations (30 min. + 15 min. discussion) about the selected papers will be given. Other participants will read one of these papers in order to be able to take part in the discussion (~15 min.). For each session, the others have to complete small exercises (like posting 2-3 questions to one of the papers or practical tasks).
In order to complete the module you need:
- active participation in the seminar (reading+exercises)
- 1 oral presentation
- essays written at the end of the seminar.
Some background knowledge in machine learning techniques is beneficial.
Frequency | Weekday | Time | Format / Place | Period |
---|
Module | Course | Requirements | |
---|---|---|---|
39-Inf-KMI Kognitive Mechanismen sozialer Interaktion | Kognitive Mechanismen sozialer Interaktion | Ungraded examination
Graded examination |
Student information |
The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.
A corresponding course offer for this course already exists in the e-learning system. Teaching staff can store materials relating to teaching courses there: