Forced alignment performance on L2 English speech with difficult stimuli: early evidence from L1 Mandarin speakers
Bibliographic record
Abstract
This study investigates the accuracy of the Montreal Forced Aligner (MFA) for second language (L2) English speech produced by L1 Mandarin speakers.A recent study has shown that while the MFA's performance is less consistent for L2 speakers than for native speakers, current forced alignment methods remain accurate enough to be useful for studies of L2 English speech.However, the extent to which L2specific phonetic difficulty affects alignment accuracy remains unclear.In this study, sentences designed to present different levels of difficulty to L1 Mandarin speakers were recorded by five participants: four L1 Mandarin speakers of L2 English, and one L1 English speaker (control).Two experienced listeners ranked the L2 speakers in order of increasing accentedness.Results indicate that while alignment accuracy is acceptable in most cases, it is influenced by accentedness.In addition, errors are not uniformly distributed across phonemes or consistently aligned with misalignment patterns documented for L1 speech.This suggests that known L2 pronunciation difficulties, through their effect on mispronunciation, may impact forced alignment accuracy, with implications for the use of MFA for segmenting L2 speech, particularly in pronunciation training.
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 | 0.002 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 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".