Real-time speaker detection for user-device binding
Bergem, Mark J.
MetadataShow full item record
This thesis explores the accuracy and utility of a framework for recognizing a speaker by his or her voice called the Modular Audio Recognition Framework (MARF). Accuracy was tested with respect to the MIT Mobile Speaker corpus along three axes: 1) number of training sets per speaker, 2) testing sample length and 3) environmental noise. Testing showed that the number of training samples per speaker had little impact on performance. It was also shown that MARF was successful using testing samples as short as 1000ms. Finally, testing discovered that MARF had difficulty with testing samples containing significant environmental noise. An application of MARF, namely a referentially-transparent calling service, is described. Use of this service is considered for both military and civilian applications, specifically for use by a Marine platoon or a disaster-response team. Limitations of the service and how it might benefit from advances in hardware are outlined.
Approved for public release; distribution is unlimited
Showing items related by title, author, creator and subject.
Consortium for Robotics and Unmanned Systems Education and Research (CRUSER) (Monterey, California: Naval Postgraduate School, 2015-03);Abstract: Dramatic progress in the science and engineering of robotics, alongside the perceived success of the US’s predator and Reaper drones in Iraq and Afghanistan, has led many commentators to conclude that the wars ...
Clark, Eric S. (Monterey, California: Naval Postgraduate School, 2016-03);This thesis examines the effect of the timing of graduation education attainment on retention of officers within the Surface Warfare community. Navy Surface Warfare Officers (SWOs) commissioned between fiscal years 1999 ...