Presentation 2002/1/18
Intelligibility Assessment and Pronunciation Error Diagnosis for a CALL System
Antoine RAUX, Tatsuya KAWAHARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A method to automatically assess the pronunciation of Japanese ESL students and identify pronunciation errors most critical to their intelligibility is presented. In an experimental study, we evaluate students intelligibility on a 5-level scale and detect their pronunciation errors using Automatic Speech Recognition. We demonstrate which errors characterize each level of intelligibility. We propose an algorithm based on the statistical distributions of the error rates to assess students intelligibility. A given student's error rates are compared to those of students of the same intelligibility level to determine which errors should be studied in priority. This algorithm was implemented in a pronunciation learning system that diagnoses the student's pronunciation on situational skits and guides the student towards adapted pronunciation drills. Preliminary results on intelligibility estimation confirm the validity of the approach.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) CALL / Intelligibility Assessment / Pronunciation Errors / Error Diagnosis / ASR
Paper #
Date of Issue

Conference Information
Committee SP
Conference Date 2002/1/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Speech (SP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Intelligibility Assessment and Pronunciation Error Diagnosis for a CALL System
Sub Title (in English)
Keyword(1) CALL
Keyword(2) Intelligibility Assessment
Keyword(3) Pronunciation Errors
Keyword(4) Error Diagnosis
Keyword(5) ASR
1st Author's Name Antoine RAUX
1st Author's Affiliation Kyoto University, Graduate School of Informatics, Speech Media Laboratory()
2nd Author's Name Tatsuya KAWAHARA
2nd Author's Affiliation Kyoto University, Graduate School of Informatics, Speech Media Laboratory
Date 2002/1/18
Paper #
Volume (vol) vol.101
Number (no) 604
Page pp.pp.-
#Pages 8
Date of Issue