Articulatory Comparison of L1 and L2 Speech for Mispronunciation Diagnosis

Subash Khanal, Michael T. Johnson, Narjes Bozorg

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

This paper compares the difference in articulation patterns between native (L1) and non-native (L2) Mandarin speakers of English, for the purpose of providing an understanding of mispronunciation behaviors of L2 learners. Consensus transcriptions from the Electromagnetic Articulography Mandarin Accented English (EMA-MAE) corpus are used to identify commonly occurring substitution errors for consonants and vowels. Phoneme level alignments of the utterances produced by speech recognition models are used to extract articulatory feature vectors representing correct and substituted sounds from L1 and L2 speaker groups respectively. The articulatory features that are significantly different between the two groups are identified along with the direction of error for the L2 speaker group. Experimental results provide information about which types of substitutions are most common and which specific articulators are the most significant contributors to those errors.

Original languageEnglish
Title of host publication2021 IEEE Spoken Language Technology Workshop, SLT 2021 - Proceedings
Pages693-697
Number of pages5
ISBN (Electronic)9781728170664
DOIs
StatePublished - Jan 19 2021
Event2021 IEEE Spoken Language Technology Workshop, SLT 2021 - Virtual, Shenzhen, China
Duration: Jan 19 2021Jan 22 2021

Publication series

Name2021 IEEE Spoken Language Technology Workshop, SLT 2021 - Proceedings

Conference

Conference2021 IEEE Spoken Language Technology Workshop, SLT 2021
Country/TerritoryChina
CityVirtual, Shenzhen
Period1/19/211/22/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

  • Articulatory features
  • Mispronunciation Diagnosis

ASJC Scopus subject areas

  • Linguistics and Language
  • Language and Linguistics
  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Hardware and Architecture

Fingerprint

Dive into the research topics of 'Articulatory Comparison of L1 and L2 Speech for Mispronunciation Diagnosis'. Together they form a unique fingerprint.

Cite this