Learnability of ultrasound tongue imaging devices in speech-language pathology
Bibliographic record
Abstract
Ultrasound tongue imaging has shown potential for speech-language pathologists (SLPs) to evaluate and treat persistent articulatory disorders. However, SLPs typically begin with low to no familiarity with ultrasound. Thus, this study investigated an important aspect of ultrasound device usability: learnability for SLPs. The project was funded by an NSERC Engage grant in partnership with Clarius Mobile Health. Twelve SLPs learned to use two ultrasound devices: a wireless device, provided by our partner Clarius, and a traditional device, to record clips of their or the experimenter’s tongue. They then completed a questionnaire (French translation of the System Usability Scale (Brooke, 1996)). Two expert judges evaluated the clips recorded by the SLPs for the choice of settings and the positioning of the probe. Results of the SUS show a better usability for the wireless device than the traditional device. SLPs appreciated the user-friendly tablet interface, possibly because they are already used to interacting with tablets. Clips analyses show a better choice of settings by the SLPs with the wireless device. The positioning of the probe, however, was better with the traditional device, possibly due to its smaller probe. In conclusion, US seems to have a good potential of usability in speech-language pathology, provided that SLPs receive training for US image interpretation. A traditional US device may require a longer learning period than a wireless model with tablet interface.
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 | 0.068 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| 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".