Title: An Overview of Speaker Recognition Technology
Speaker: Tina Kohler, Department of Defense
Date: Friday, December 5, 2008 11:00 - 12:00 pm
Location: DyDAn Center, CoRE Bldg, Room 431, Rutgers University, Busch Campus, Piscataway, NJ
Abstract:
Speaker recognition algorithms attempt to determine whether a speech segment matches a previously created speaker model. Although speaker recognition in realistic environments (e.g. conversational speech over a telephone channel with background noise) is far from perfect, several speaker recognition models currently provide relatively high accuracy that can be used for many applications. This talk will describe some of the most popular speaker recognition algorithms and realistic data used to evaluate the algorithms as well as an interactive demonstration of one of the recognition algorithms.
See our new DyDAn Student-organized Seminar Series
Back to DyDAn Home Page
Back to DIMACS Home Page