Visar Berisha

Assistant Professor
Joint appointment with Department of Speech and Hearing Science
ASU Directory Profile

Personal website

Coor Hall, 3472

Research expertise: Statistical signal processing, speech perception and processing, psychoacoustics

Visar Berisha received his Ph.D. in electrical engineering from Arizona State University in 2007. From 2007 to 2009, he was a member of the technical staff at MIT Lincoln Laboratory, where he worked on signal processing for radar applications. Following his appointment at MIT, Berisha joined Raytheon Co. in 2009 as a principal research engineer where he was PI on a number of basic research activities in machine learning and signal processing.

He has been a member of the faculty at ASU since fall 2013 with a joint appointment in the departments of Speech and Hearing Science and ECEE. The overarching goal of research conducted in his lab is to develop and apply new machine learning and statistical signal processing tools to better understand and model signal perception. With a focus on speech, the goal is to develop reliable, data-driven models that can mimic aspects of human cognition. Some recent projects include developing models of pathological speech perception, using natural language process to track cognitive-linguistic health, developing auditory perception models based on psychoacoustics and developing new machine learning tools for use with behavioral experiments. His research has been featured in the Science section of the New York Times, on National Public Radio and on a number of mainstream media outlets.

Making progress against these goals requires an interdisciplinary approach that spans multiple fields. Visar’s contributions to this effort are centered on developing computational models guided by collected behavioral data. If you have any interest in these topics, please feel free to contact him!
Selected publications:

A. Wisler, V. Berisha, A. Hero, and A. Spanias “Empirically Estimable Classification Bounds Based on a Non-parametric Divergence Measure,” IEEE Transactions on Signal Processing. Accepted for Publication, August, 2015.

Y. Jiao, V. Berisha, M. Tu, and J. Liss, “Convex Weighting Criteria for Speaking Rate Estimation,” IEEE Transactions on Audio, Speech, and Language Processing. Vol. 23, Issue No. 9, May 2015.

V. Berisha, S. Wang, A. LaCross, and J. Liss, “Tracking Discourse Complexity Preceding Alzheimer’s Disease Diagnosis: A Case Study Comparing the Press Conferences of Presidents Ronald Reagan and George Herbert Walker Bush,” Journal of Alzheimer’s Disease. Vol. 45, Issue No. 3, 2015.

T. Schwedt, V. Berisha, and C. Chong, “Temporal Lobe Cortical Thickness Correlations Differentiate the Migraine Brain from the Healthy Brain,” PLOS-ONE. Feb, 2015.

V. Berisha and A. Hero, “Empirical Non-Parametric Estimation of the Fisher Information,” IEEE Signal Processing Letters, Vol 22, Issue No. 7, 2015.

V. Berisha and D. Cochran, “Active Data Labeling for Improved Classifier Generalizability,” Signal Processing, October 2014.