Biography

Dr. Michael T. Johnson is an Associate Professor of Electrical and Computer Engineering at Marquette University in Milwaukee, Wisconsin.  His primary research focus is speech and signal processing, with other research interests including natural language processing and artificial intelligence.  Dr. Johnson holds a Ph.D. degree from School of Electrical and Computer Engineering at Purdue University, as well as an M.S. degree in Electrical Engineering from the University of San Antonio and B.S. degrees in Electrical Engineering and Computer Science Engineering from LeTourneau University in Longview, Texas.  Prior to pursuing his Ph.D. degree, he worked as a hardware systems engineer and engineering manager for a number of years.  His current research efforts include the Dr. Dolittle project (http://speechlab.eece.mu.edu/dolittle), a collaborative project focused on application of speech technology to the analysis and classification of animal vocalizations. Dr. Johnson and his wife Patricia live near Milwaukee and have one daughter, Evelyn Su Mei.

Abstract

Current approaches to automated methods for analyzing and classifying animal vocalizations are still significantly behind the capabilities that exist in the field of human speech processing.  Cross-fertilization with other fields offers a tremendous opportunity for making advancements in this area.  The Dr. Dolittle Project brings together expertise from such fields as psychology, biology, linguistics, machine learning, and signal processing, for the purpose of making significant advancements to the current state-of-the-art in bioacoustics algorithms and animal communications research.

The Dr. Dolittle Project, funded by the National Science Foundation, represents collaboration between Marquette University’s Speech and Signal Processing Lab and several other institutions, including Disney’s Animal Kingdom, the University of Central Florida, the University of Connecticut, and Fauna Communications Research Institute.  The algorithms developed through this collaboration are being applied to a wide range of important tasks, including automatic vocalization classification and labeling, individual identification, call type classification, and behavioral-vocalization correlations.  Species being studied include African elephants, Beluga whales, Ortolan bunting songbirds, and prairie dogs, plus several domestic and agricultural species.

One of the primary practical motivations for this work is the preservation of endangered species and the improvement of care and habitats for animals in captivity.  The differentiation of vocalization patterns during different parts of the female elephant’s ovulation cycles has the potential to improve breeding methods, by reducing the stress on the animals associated with frequent blood collection for hormonal analysis.  Individual identification algorithms, i.e. “voice-printing”, may enable more accurate and less invasive censusing of animal populations in the wild.  Overall, the project provides researchers with clues on understanding social structure and behavior patterns ? information that can then be used to enhance the treatment of wild and captive animals.