Title:
Speech Separation in Cell phones
Speaker:
Ahmed H. Tewfik
Univ. of Minnesota
Abstract:
The talk will begin with an overview of the problem of separating a speech source using the outputs of two or more microphones that provide recordings of the source mixed with other speech and non-speech audio signals. It will then discuss a speech source separation technique that is rooted in the theory of sparse signal representations and highlight recent progress in the areas of dictionary design and low complexity implementations. This work is a collaboration with Vikrham Gowreesunker and Dr. Vishu Viswanathan.
Bio:
Ahmed H Tewfik received his B.Sc. degree from Cairo University, Egypt, in 1982 and his M.Sc., E.E. and Sc.D. degrees from the Massachusetts Institute of Technology, MA, in 1984, 1985 and 1987 respectively. Dr. Tewfik worked at Alphatech, Inc., Burlington, MA in 1987. He is the E. F. Johnson professor of Electronic Communications with the department of Electrical Engineering at the University of Minnesota. He served as a consultant to several companies in Minnesota, California and New York in the areas of industrial measurements, multimedia protection and distribution, wireless communications, medical instrumentation and devices and gigabit Ethernet. Between 1997 and 2001, he was the President and CEO of Cognicity, an entertainment marketing software tools publisher that he co-founded. His current research interests are in sparse signal representations and applications in audio, genomics and proteomics, wearable health sensors for patients at cardiac risk, traumatic brain injury and autism, brain machine interfaces and programmable wireless networks.
Prof. Tewfik is a Fellow of the IEEE. He was a Distinguished Lecturer of the IEEE Signal Processing Society in 1997 – 1999, gave plenary lectures at numerous major IEEE conferences, received several awards, including the IEEE third Millennium award in 2000 and was elected to the board of governors of the IEEE Signal Processing Society in 2005.