SUNMONTUEWEDTHUFRISAT
Events for September 23, 2015
-
Behavioral Signal Processing
Wed, Sep 23, 2015 @ 12:30 PM - 01:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Matthew P. Black, Research Computer Scientist, ISI-USC
Talk Title: Behavioral Signal Processing
Abstract: Understanding human behavior is a central goal of many fields in human-centered science and engineering. This includes not only understanding how people move, communicate, and interact, but also understanding how people judge human behavior. Human judgments on behavior occur everywhere (e.g., everyday life, educational settings, human-centered research, clinical/medical settings) and are an important part of interpersonal interactions and many assessment and intervention designs. While people have evolved to be adept at processing behavioral information, there are some basic challenges. Human descriptions on behaviors are oftentimes qualitative, and there is natural variability between people's judgments due to the subjective nature of the judgment process. These challenges present many exciting research opportunities for high-impact signal processing work that supports and enhances human decision-making with machine decision-making. Automatic engineering methods may be better suited at quantifying aspects of human behavior (e.g., a speaker's pitch) and could provide an invaluable ancillary in some cases and enable novel insights in others.
In this talk, I will discuss the emerging field of Behavioral Signal Processing (BSP), which entails the development of computational methods that model abstract human behaviors in real-life scenarios. Specifically, I will describe how we automatically quantified and predicted human subjective judgments on human behavior from speech signals in the context of three societally-significant domain applications explored in my Ph.D. dissertation: education (children's literacy assessment), family studies (couples therapy research), and health (autism diagnosis). I will describe the unique technical challenges in BSP (e.g., multiple sources of variability, including heterogeneity of the human behavior and subjectivity in human perception) and highlight the technological contributions of this work. Finally, I will end the talk with ongoing and intended future work and discuss how these research efforts can make an impact by being employed in real-life applications.
Biography: Matthew P. Black received his B.S. in Electrical Engineering (EE) with highest distinction and thesis honors from The Pennsylvania State University in 2005, with minors in Mathematics and Physics. While a member of the Signal Analysis and Interpretation Laboratory, directed by Prof. Shrikanth Narayanan, he received his M.S. (2007) and Ph.D. (2012) in EE from the University of Southern California (USC). Matthew is currently a research computer scientist at the Information Sciences Institute (ISI). From 2012-2014, he worked as a freelance technical consultant in speech and language processing and as an actuary at Farmers Insurance Group, Los Angeles, CA. In the summer of 2007, Matthew was a graduate research intern at the IBM T.J. Watson Research Center in the Human Language Technologies Dept., Yorktown, NY.
Matthew's research interests are in behavioral signal processing (BSP) and informatics, human-centered engineering, speech and language processing, automatic speech recognition and assessment, computational paralinguistics, emotion recognition, affective computing, multi-person interaction modeling, human-computer interaction, pattern recognition, machine learning, and societally-significant applications of technology. He is a member of IEEE and ISCA and a member of the honors societies: Phi Kappa Phi, Tau Beta Pi, and Eta Kappa Nu. Matthew was an EE Ming Hsieh Institute Ph.D. Scholar at USC (2011-2012) and was awarded the Alfred E. Mann Innovation in Engineering Doctoral Fellowship (2010-2012), the Simon Ramo Fellowship (2009-2010), and the Dean's Fellowship (2005-2009) at USC. He won the Best Student Paper Award for the Ming Hsieh Dept. of EE at USC (2010-2011), the ISCA Interspeech Best Paper Award (2010), and was a multi-year winning team member of the ISCA Interspeech Computational Paralinguistics Challenge Award (2011, 2014, 2015). Matthew has authored or co-authored 40 refereed journal, conference, and workshop publications.
Host: Professor Sandeep Gupta, sandeep@usc.edu
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Mayumi Thrasher
-
Communications, Networks & Systems (CommNetS) Seminar
Wed, Sep 23, 2015 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Majid Zamani, Technische Universität München
Talk Title: When Lyapunov meets Church, automated synthesis of complex systems emerges
Series: CommNetS
Abstract: Software plays a crucial role in many everyday applications. Modern vehicles and airplanes, for instance, use interacting software and hardware components to control steering, fuel injection, and airbag deployment. These applications are examples of cyber-physical systems (CPS), where software components interact tightly with physical systems. Recent advances in device manufacturing, computation, storage, and networking have made tremendous advances in hardware and systems platforms for CPS. However, the development of core software controllers that run on these systems is still ad hoc and error-prone. Many CPS applications are safety-critical, and much of the engineering costs today are consumed with ensuring that software works correctly. In this talk, I will proposes a transformative design process, in which the controller code is automatically synthesized from higher-level correctness requirements. Requirements for modern CPS applications go beyond conventional requirements in control theory (stability, synchronization, and tracking) and beyond traditional protocol design in computer science. Accordingly, I will propose unified methodologies for automatic controller synthesis by combining techniques from discrete systems theory from computer science with continuous dynamical systems from control theory. The proposed automated synthesis of correct-by-construction controllers holds the potential to develop complex yet reliable CPS applications while considerably reducing verification and validation costs.
Biography: Majid Zamani is an assistant professor in the Department of Electrical and Computer Engineering at Technische Universität München where he leads the Hybrid Control Systems Group. He received a Ph.D. degree in Electrical Engineering and an MA degree in Mathematics both from University of California, Los Angeles in 2012, an M.Sc. degree in Electrical Engineering from Sharif University of Technology in 2007, and a B.Sc. degree in Electrical Engineering from Isfahan University of Technology in 2005. From September 2012 to December 2013, he was a postdoctoral researcher in the Delft Centre for Systems and Control at Delft University of Technology. Between December 2013 and May 2014, he was an assistant professor at Delft University of Technology.
Host: Prof. Ashutosh Nayyar
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Annie Yu
