Project Description
Third-cycle subject: Computer Science or Speech and Music Communication
We are looking for a doctoral student interested in AI, Machine Learning, Natural Language Processing and Human-Robot Interaction, that will work in a newly funded project at the Division of Speech, Music and Hearing (www.kth.se/is/tmh) within the School of Electrical Engineering and Computer Science at KTH. It is an internationally recognized research lab in speech and language technology, with a special research focus on human-like multimodal interaction with social robots.
The newly started project “Perceiving and communicating correct-by-design autonomous systems”, where the aim is to develop collaborative robots that can perform physical tasks in a smart home environment. The project is financed by the Swedish AI-program WASP (Wallenberg AI, Autonomous Systems and Software Program, www.wasp-sweden.org), which offers a graduate school with research visits, partner universities, and visiting lecturers.
The PhD candidate will collaborate with a team of researchers from the Division of Robotics, Perception and Learning (www.kth.se/is/rpl). The overall goal is to design robot behaviours that are not only guaranteed to be safe, but are also perceived as safe and accepted by people. The task of the candidate is to develop control methods for an adaptive conversational speech generation system that can convey the robot’s inner state as well as adapting the voice style to external factors, such as social situation or different robot appearances. Matching cues are useful not only in order to reduce human cognitive load, but also in terms of setting the right expectations regarding what the robot can do.
Supervision: The doctoral student will be supervised by Prof. Joakim Gustafsson.