Forced Alignment for Understudied Language Varieties: Testing Prosodylab-Aligner with Tongan Data.
Bibliographic record
Abstract
Automated alignment of transcriptions to audio files expedites the process of preparing data for acoustic analysis. Unfortunately, the benefits of auto-alignment have generally been available only to researchers studying majority languages, for which large corpora exist and for which acoustic models have been created by large-scale research projects. Prosodylab-Aligner (PL-A), from McGill University, facilitates automated alignment and segmentation for understudied languages. It allows researchers to train acoustic models using the same audio files for which alignments will be created. Those models can then be used to create time-aligned Praat TextGrids with word and phone boundaries marked. For the benefit of others who wish to use PL-A for research projects, this paper reports on our use of PL-A on Tongan field recordings, reviewing the software, outlining required steps, and providing tips. Since field recordings often contain more background noise than the laboratory recordings for which PL-A was designed, the paper also discusses the relative benefits of removing background noise for both training and alignment purposes. Finally, it compares acoustic measures based on various alignments and compares boundary placements with those of human aligners, demonstrating that automated alignment is both feasible and less time-consuming than manual alignment.
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 | 0.018 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.005 |
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".