Automated Scoring for Elicited Imitation Tests
Tim Ashwell, ティム アシュウェル · Institutional Repositories DataBase (IRDB) · 2014
Scoring oral tests of second language ability can be a time-consuming and labour-intensive task.Trained assessors can rate learners' oral profi ciency on the spot, but this is an expensive solution to the problem and takes time to administer to a large number of learners.With the advent of more advanced and reliable voice recognition software, however, using computers to do the scoring has now become a possibility.The focus in this paper is on the fi rst stage of a research project which eventually aims to automatically score an oral test of English second language profi ciency.This fi rst stage involves building up a database of audio fi les of Japanese university students recording English elicited imitation test items and performing on elicited imitation tests.This database will then be used in the next stage of the research to see if an open source automatic speech recognition (ASR) tool can be used to reliably score students' test performance.