Speaker-based Accented English Clustering Using a World English Archive

H. P. Shen, N. Minematsu, T. Makino, S. H. Weinberger, T. Pongkittiphan, C. H. Wu

Research output: Contribution to conferencePaperpeer-review

2 Citations (Scopus)

Abstract

English is the only language available for global communication. Due to the influence of speakers’ mother tongue, however, those from different regions often have different accents in their pronunciation of English. The ultimate goal of our project is automatic creation of a global pronunciation map of World Englishes on an individual basis, for speakers to use to locate similar English pronunciations. Creating the map mathematically requires a matrix of pronunciation distances among all the speakers considered. Our previous study proposed a good algorithm for that purpose [1], where, using phonetic reference pronunciation distances calculated from labeled data, a pronunciation distance predictor was trained and built for unlabeled data. Due to space limit in [1], the procedure for calculating the reference distances was not described in detail. Then in this paper, detailed descriptions are given and 498 world-wide native and non-native speakers in the Speech Accent Archive [2] are clustered using the phonetic reference distances. Results show high validity of using the calculated distances as reference distances for training a distance predictor.

Original languageEnglish
Pages184-188
Number of pages5
Publication statusPublished - 2013
Event2013 ISCA International Workshop on Speech and Language Technology in Education, SLaTE 2013 - Grenoble, France
Duration: 2013 Aug 302013 Sep 1

Conference

Conference2013 ISCA International Workshop on Speech and Language Technology in Education, SLaTE 2013
Country/TerritoryFrance
CityGrenoble
Period13-08-3013-09-01

All Science Journal Classification (ASJC) codes

  • Computer Science (miscellaneous)
  • Computational Mathematics
  • Education

Fingerprint

Dive into the research topics of 'Speaker-based Accented English Clustering Using a World English Archive'. Together they form a unique fingerprint.

Cite this