Exploring automatic speech recognition for corrective and confirmative pronunciation feedback
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Abstract Given that second language pronunciation errors are typically variable, learners would benefit from feedback that both flags errors ( corrective feedback ) and confirms correct pronunciation ( confirmative feedback ). We investigated Google Translate (GT) automatic speech recognition (ASR) transcription accuracy to determine its capacity to provide such feedback, based on Quebec francophone recordings of correctly/incorrectly realized English th-initial, h-initial and vowel-initial items in predictable/unpredictable sentence contexts. Recordings from male and female speakers were used to verify possible gender bias. In predictable contexts, transcription accuracy rates were higher for correct vs incorrect pronunciations; rates in unpredictable contexts for correct or incorrect pronunciations fell midway between the two. GT ASR is thus better at providing confirmative feedback in predictable contexts but corrective feedback in unpredictable contexts. Regardless of context, accuracy was considerably higher on errors leading to real-word than nonword output. Contra the anticipated pattern, female speakers were transcribed with higher accuracy than male.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it