Supervised and Unsupervised Classification of Sound Signals With Applications in Hearing Aids

Fatemeh Saki, Ph.D. student, University of Texas at Dallas

 

Date: 2017-02-28
Time: 1:00pm - 2:00pm
Location: Calit2 Room 4004, Atkinson Hall, UC San Diego

Guest Speaker: Fatemeh Saki, University of Texas at Dallas
Ph.D. Student and Research Assistant


Host: Hari Garudadri, QI


DESCRIPTION/ABSTRACT:

This seminar with University of Texas at Dallas Ph.D. student Fatemeh Saki is organized by the joint QI-ECE Hearing Aids project. 

Classification of sound signals is increasingly being used in hearing improvement devices such as hearing aids, cochlear implants, and smart headphones. Classification of sound signals enables adapting the speech enhancement/noise reduction algorithms in such devices to different sound environments in an automatic manner. The thrust of this presentation is on the development of sound signal classification approaches that are computationally efficient thus enabling their real time deployment in hearing improvement devices. Both supervised and unsupervised learning schemes are considered. To this end, effective and computationally efficient features and unsupervised clustering algorithms have been developed.


SPEAKER BIO:

FATEMEH SAKI  received the BS degree in electrical engineering from the Shahid Chamran University of Ahvaz in 2008, and the MS degree in electrical engineering from the Iran University of Science and Technology in 2010. She is currently a PhD candidate in the Department of Electrical Engineering at the University of Texas at Dallas and will be graduating in May 2017. Her research interests include real-time audio and image processing, pattern recognition and machine learning. Her research contributions have appeared in 4 journal papers (2 additional journal papers are under review) and 14 conference papers. She has also co-authored a textbook for Signals and Systems Laboratory courses using smartphones. She has been an active member of her research community as a reviewer of many journal and conference papers. Based on her academic record, she was awarded the Jonsson School Graduate Study Scholarship in 2012 and was also awarded twice the Louis Beecherl Jr. Graduate Fellowship in 2015 and in 2016 by the Erik Jonsson School of Engineering and Computer Science at the University of Texas at Dallas.