Ph.d. Defense of Dissertation Announcement

 Daniel Kyu Hwa Kohlsdorf

Title: DATA MINING IN LARGE AUDIO COLLECTIONS OF DOLPHIN SIGNALS

Date: Monday, July 13, 2015

Time: 11:00am

Location: TSRB 223

COMMITTEE:

Dr. Thad Starner, School of Computer Science, Georgia Tech (Advisor) Dr. Irfan Essa, School of Computer Science, Georgia Tech Dr. Charles Isbell, School of Computer Science, Georgia Tech Dr. Denise Herzing, Wild Dolphin Project Dr. Michael Beetz, Computer Science, University Bremen

ABSTRACT:

-- The study of dolphin cognition involves intensive research of animal vocalizations recorded in the field. In this thesis I address the automated analysis of audible dolphin communication. I propose a system called the signal imager that automatically discovers patterns in dolphin signals. These patterns are invariant to frequency shifts and time warping transformations. The discovery algorithm is based on feature learning and unsupervised time series segmentation using hidden Markov models. Researchers can inspect the patterns visually and interactively run comparative statistics between the distribution of dolphin signals in different behavioral contexts. The required statistics for the comparison describe dolphin communication as a combination of the following models: a bag-of-words model, an n-gram model and an algorithm to learn a set of regular expressions. Furthermore, the system can use the patterns to automatically tag dolphin signals with behavior annotations. My results indicate that the signal imager provides meaningful patterns to the marine biologist and that the comparative statistics are aligned with the biologists’ domain knowledge.