Acoustic scene mapping for robots

Add to your list(s) Download to your calendar using vCal

• Dr Christine Evers, EPSRC Research Fellow, DEEE, Imperial College London
• Wednesday 31 January 2018, 12:00-13:00
• Room 611 (Gabor Seminar Room), Level 6, EEE Department.

If you have a question about this talk, please contact Joan P O'Brien.

Abstract: Recent advances in robotics are rapidly leading to the evolution of autonomous machines capable of assisting humans in everyday environments. For intuitive interaction between humans and robots. spoken dialogues are a fundamental prerequisite. However, in realistic environments, speech signals are adversely affected by reverberation, periods of speech inactivity, noise, and interference from competing sound sources. Moreover, motion of human talkers and of the robot itself lead to highly dynamic scenes, where the positional information of the sound sources as well as the microphones are unknown and difficult to predict. This talk will focus on recent advances in acoustic signal processing that equip robots with the situational awareness necessary to learn about, adapt to and interact with sound sources in their environment. In particular, we will focus on the recently pioneered topic of acoustic Simultaneous Localization and Mapping that provides three-dimensional representations of a robot’s acoustic environment.

Biography: Christine Evers is an EPSRC Research Fellow in the Department of Electrical and Electronic Engineering at Imperial College London. She received her PhD from the University of Edinburgh, UK, in 2010. After a position as a research fellow at the University of Edinburgh between 2009 and 2010, she worked as a senior systems engineer at Selex Electronic Systems, Edinburgh, UK, between 2010 and 2014. She joined Imperial College as a research associate in 2014. In 2017, she was awarded a fellowship by the UK Engineering and Physical Research Council (EPSRC) to advance her research on acoustic signal processing and scene mapping for socially assistive robots. Her research focuses on Bayesian learning for robot audition, including acoustic source tracking, Simultaneous Localization and Mapping (SLAM), as well as signal enhancement. She is a Senior Member of the IEEE and a member of the IEEE Signal Processing Society Technical Committee on Audio and Acoustic Signal Processing.

This talk is part of the Featured talks series.

This talk is included in these lists:

• Andrea Picciau's list
• COMMSP & CP list
• COMMSP Seminar
• Featured talks
• Room 611 (Gabor Seminar Room), Level 6, EEE Department
• SAP Talks

Note that ex-directory lists are not shown.