Keywords

aSR-based elicited imitation grading, improved EI language model development, corpus-driven EI test item creation

Abstract

In this study we discuss the development of an optimal ASR-based grading system for an L2 oral proficiency test with a method called elicited imitation (EI). We also discuss EI test item creation from a linguistic point of view. Based on two issues found in a previous study (Matsushita & LeGare, 2010) we also investigate creation of improved language models for EI grading with speech corpus data. Finally, we examine the effectiveness of new EI items in our empirical study and suggest a method to retrieve authentic EI test items from corpus data.

Original Publication Citation

Matsushita, H., Lonsdale, D. & Dewey, D. P. (2010). Japanese elicited imitation: ASR-based oral proficiency test and optimal item creation. In S. Ishikawa (Ed.), Proceedings of the 6th International Conference of the Society of Information and Communicative Technologies in Analysis, Teaching and Learning of Language (ICTATLL). Tokyo: Kobe University Press. https://drive.google.com/file/d/1ks6vkhSzulZzlbviQ6XN3dkjXe4Lvck6/view?usp=sharing

Document Type

Peer-Reviewed Article

Publication Date

2010

Publisher

Tokyo: Kobe University Press

Language

English

College

Humanities

Department

Linguistics

University Standing at Time of Publication

Full Professor

Download

Included in

Linguistics Commons

Share

COinS