Learn More
In this paper, the problem of identifying in-set versus out-of-set speakers using extremely limited enrollment data is addressed. The recognition objective is to form a binary decision regarding an input speaker as being a legitimate member of a set of enrolled speakers or not. Here, the emphasis is on low enrollment (about 5 sec of speech for each enrolled(More)
v ACKNOWLEDGEMENTS There are so many people who helped me complete this thesis, it becomes nearly impossible for me to enlist everyone's name and contributions in a single paragraph. Special thanks to my family, specially my mom and dad and my elder brother Rajib, for being part of every bit of my life: their endless motivations, constant mental support and(More)
This document is dedicated to my parents who persuaded me to do my masters' and funded my education. iv ACKNOWLEDGMENTS I would like to take this opportunity to thank everyone who, directly or indirectly, helped me complete this thesis. First, I would like to thank my committee chair, Dr. Debra Harris, for all the encouragement and guidance rendered to me(More)
  • 1