Evaluating the effectiveness of Microsoft Transcribe for automating the assessment of pronunciation in language proficiency tests

Abstract

[EN] Improvements in Automatic Speech Recognition (ASR) have created opportunities for using it as a tool to facilitate second and foreign language (L2) assessment. These technical improvements have not only enabled automation of language proficiency test scoring but also reduced evaluator bias and errors, decreased processing time, and lowered costs for testing organizations. The purpose of this study was to evaluate English as a Second Language (ESL) pronunciation using the ASR feature in the Microsoft 365 product suite, Transcribe (MS-T). The study involved adult ESL learners at a Canadian university that partook in a language proficiency test. We examined the audio recordings of 56 candidates during the pronunciation portion of the test. Building on previous studies that found a strong correlation between scores from Google Voice Typing and human raters, the current study conducted a similar analysis comparing scores derived from MS-T to both human ratings and Google Voice Typing. Our findings indicate that the ASR capabilities of MS-T, similar to Google Voice Typing, can assume an important role in L2 speaking assessment by providing objectivity and reliability to the testing process, expediting scoring, and reducing costs.