Speech recognition will one day revolutionize how humans and computers interact, and in turn, how and where computers are used. Before this can happen, speech recognition systems must become accurate and robust, all the while remaining computationally feasible. This talk will introduce current microphone array based robust speech processing research at the University of Toronto's Artificial Perception Laboratory.
We start by introducing novel sound source localization techniques, followed by microphone array based speech de-noising and separation. Finally, we shall discuss hardware acceleration and FPGA/VLSI implementation of our multi-microphone speech processing algorithms.
About the speaker:
Professor Parham Aarabi is a faculty member in the Department of Electrical and Computer Engineering at the University of Toronto, a Canada Research Chair in Multi-Sensor Information Systems, and the founder and director of the Artificial Perception Lab. Prof. Aarabi received his Ph.D. in Electrical Engineering from Stanford University in 2001, his M.A.Sc. in Electrical and Computer Engineering from the University of Toronto in 1999, and his B.A.Sc. in Engineering Science (Electrical Option) from the University of Toronto in 1998. Prof. Aarabi has been the recipient of numerous teaching and research awards, including the Ontario Distinguished Researcher Award, the 2002 Best Computer Engineering Professor Award, the Early Career Teaching Award, and the 2003 Professor of the Year Award. His current research, which includes multi-sensor information fusion, human-computer interactions, and FPGA/VLSI implementation of sensor fusion algorithms, has been extensively covered by a variety of newspapers and television shows including the Discovery Channel, CBC Newsworld, and Scientific American.
Parham Aarabi, M.A.Sc., Ph.D. (Stanford)
Assistant Professor, Canada Research Chair, and Director of the
Artificial Perception Laboratory
University of Toronto
10 Kings College Rd.
Canada M5S 3G4