Impact of stimulus difficulty on forced alignment performance in L2 English learners: A focus on L1 Mandarin
Bibliographic record
Abstract
This study investigates the performance of forced alignment algorithms and tools for second language (L2) English speech, more specifically L2 English speech produced by L1 Mandarin speakers. A recent study has shown that while the aligner's performance is less consistent with L2 speakers than with native speakers, current forced alignment methods are still accurate enough to be useful for studies of L2 English speech. However, no previous study has investigated whether the difficulty of the spoken content influences accuracy. In the present study, sentences designed to present different levels of difficulty to L1 Mandarin speakers were recorded. Participants included four L1 Mandarin speakers and one L1 English speaker as a control. All participants were associated with a subjective accentedness rating scale by two experienced listeners. A dataset containing recordings was created, which underwent preprocessing, including noise filtering and segmentation by silent periods. Statistical analysis revealed that alignment performance is correlated with accentedness but not with sentence difficulty. The study identified specific phonemic errors and possible differences in variance at different difficulty levels, highlighting the challenges faced by non-native speakers. Forced alignment methods appear to be well suited for phonetic analysis included with L1 Mandarin and L2 English contexts.
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 | 0.001 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.004 | 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".