Skip to main content

Shibboleth: An Automated Foreign Accent Identification Program


Abstract The speech of non-native (L2) speakers of a language contains phonological rules that differentiate them from native speakers. These phonological rules characterize or distinguish accents in an L2. The Shibboleth program creates combinatorial rule-sets to describe the phonological pattern of these accents and classifies L2 speakers into their native language. The training and classification is done in Shibboleth by support vector machines using a Gaussian radial basis kernel. In one experiment run using Shibboleth, the program correctly identified the native language (L1) of a speaker of unknown origin 42% of the time when there were six possible L1s in which to classify the speaker. This rate is significantly better than the 17% chance cla... (more)
Created Date 2013
Contributor Frost, Wende Kara (Author) / Van Gelderen, Elly (Advisor) / Perzanowski, Dennis (Committee member) / Gee, Elisabeth (Committee member) / Arizona State University (Publisher)
Subject Linguistics / accent recognition / computational linguistics / foreign accent / linguistics / phonology / second language acquisition
Type Doctoral Dissertation
Extent 122 pages
Language English
Copyright
Reuse Permissions All Rights Reserved
Note Ph.D. English 2013
Collaborating Institutions Graduate College / ASU Library
Additional Formats MODS / OAI Dublin Core / RIS


  Full Text
1.7 MB application/pdf
Download Count: 1488

Description Dissertation/Thesis
  AppendixC.csv
22.4 MB text/plain
Download Count: 206

Description Appendix C
  AppendixE.xls
33.5 KB application/vnd.ms-excel
Download Count: 178

Description Appendix E
  AppendixF.xls
41.0 KB application/vnd.ms-excel
Download Count: 179

Description Appendix F