Exploration of small enrollment speaker verification on handheld devices

Thesis (M. Eng. and S.B.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2005.

Bibliographic Details
Main Author: Woo, Ram H. (Ram Han)
Other Authors: Timothy J. Hazen.
Format: Thesis
Language:eng
Published: Massachusetts Institute of Technology 2006
Subjects:
Online Access:http://hdl.handle.net/1721.1/33380
_version_ 1811087185004199936
author Woo, Ram H. (Ram Han)
author2 Timothy J. Hazen.
author_facet Timothy J. Hazen.
Woo, Ram H. (Ram Han)
author_sort Woo, Ram H. (Ram Han)
collection MIT
description Thesis (M. Eng. and S.B.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2005.
first_indexed 2024-09-23T13:41:30Z
format Thesis
id mit-1721.1/33380
institution Massachusetts Institute of Technology
language eng
last_indexed 2024-09-23T13:41:30Z
publishDate 2006
publisher Massachusetts Institute of Technology
record_format dspace
spelling mit-1721.1/333802019-04-12T16:05:59Z Exploration of small enrollment speaker verification on handheld devices Woo, Ram H. (Ram Han) Timothy J. Hazen. Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Massachusetts Institute of Technology. Dept. of Electrical Engineering and Computer Science. Electrical Engineering and Computer Science. Thesis (M. Eng. and S.B.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2005. Includes bibliographical references (p. 77-78). This thesis explores the problem of robust speaker verification for handheld devices under the context of extremely limited training data. Although speaker verification technology is an area of great promise for security applications, the implementation of such a system on handheld devices presents its own unique challenges arising from the highly mobile nature of the devices. This work first independently analyzes the impact of a number of key factors, such as speech features, basic modeling techniques, as well as highly variable environmental/microphone conditions on speaker verification accuracy. We then present and evaluate methods for improving speaker verification robustness. In particular, we focus on normalization techniques, such as handset normalization (H-norm), zero normalization (Z-norm) as well as model training methodologies (multistyle training) to minimize the detrimental impact of highly variable environment and microphone conditions on speaker verification robustness. by Ram H. Woo. M.Eng.and S.B. 2006-07-13T15:19:38Z 2006-07-13T15:19:38Z 2005 2005 Thesis http://hdl.handle.net/1721.1/33380 62558712 eng M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission. http://dspace.mit.edu/handle/1721.1/7582 78 p. 2661326 bytes 2664508 bytes application/pdf application/pdf application/pdf Massachusetts Institute of Technology
spellingShingle Electrical Engineering and Computer Science.
Woo, Ram H. (Ram Han)
Exploration of small enrollment speaker verification on handheld devices
title Exploration of small enrollment speaker verification on handheld devices
title_full Exploration of small enrollment speaker verification on handheld devices
title_fullStr Exploration of small enrollment speaker verification on handheld devices
title_full_unstemmed Exploration of small enrollment speaker verification on handheld devices
title_short Exploration of small enrollment speaker verification on handheld devices
title_sort exploration of small enrollment speaker verification on handheld devices
topic Electrical Engineering and Computer Science.
url http://hdl.handle.net/1721.1/33380
work_keys_str_mv AT wooramhramhan explorationofsmallenrollmentspeakerverificationonhandhelddevices