Evaluating the effectiveness of Microsoft Transcribe for automating the assessment of pronunciation in language proficiency tests
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.041 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".