Events Calendar

Behavioral Signal Processing

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