A robust tongue shape model from ultrasound recordings of normal and impaired speech
Bibliographic record
Abstract
Ultrasound imaging is a helpful tool to observe tongue movements without interfering with natural speech. There exist a variety of models to quantify tongue shape based on contours extracted from ultrasound images. However, these can be affected by poor image quality, e.g., when parts of the tongue are missing from the images due to imaging artifacts. In this study, we investigate the effects of various contour extraction errors on the accuracy and consistency of different shape measures. We developed exponential and polynomial contour perturbation models, then simulated missing tongue tip and root, and investigated the impact of these perturbations on shape measures based on the discrete Fourier transform (DFT), modified curvature index (MCI), and triangular fitting. This was applied to a set of CV utterances collected from healthy and impaired speakers. Results demonstrate the effectiveness of DFT and triangular fitting in clustering different phonemes despite the added noise. A high degree of correlation was found between the DFT coefficients of the perturbed and original tongue contours. There is also a trade-off between the robustness of the model and sensitivity to minor actual differences in tongue shape. Sometimes, these slight differences help group tongue shapes that differ, e.g., due to coarticulation effects. Therefore, we have attempted to improve the precision of the DFT model by adding palatal contact information.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".