Ultrasound overlay videos and their application in Indigenous language learning and revitalization
Bibliographic record
Abstract
Pronunciation is one of the major challenges in second language (L2) learning, and in the context of First Nations languages, the challenge can be compounded by both a scarcity of resources (including, in some cases, small numbers of speakers) and the pressures faced by heritage learners to preserve their ancestral language in an authentic way (1). In this paper, we discuss a pronunciation training tool we developed that uses ultrasound visualization technology and its potential application in Indigenous language revitalization. L2 learners rely on auditory and visual information to acquire speech sounds and patterns, and tools like ultrasound that facilitate visualization of the articulatory processes involved in speech production can aid in L2 pronunciation training (2). To make ultrasound visualization accessible and interpretable to a broader audience, we developed a series of ultrasound overlay videos which combine ultrasound images of tongue movement in speech with external profile views of a speaker’s head. There are 91 videos, corresponding to each sound in the International Phonetic Alphabet (see enunciate.arts.ubc.ca for videos and research supporting their effectiveness). While this video library is useful as a general resource, there has also been interest from First Nations groups in customized videos, either to target specific phonological contrasts in a given language or to present a familiar face in a particular linguistic community. Through community partnerships we are developing customized ultrasound overlay videos for four Indigenous languages: Upriver Halq’emeylem, SENCOTEN, Secwepemc, and Blackfoot. We report on these projects, highlighting the potential for ultrasound overlay technology to contribute to revitalization efforts in these and other First Nations languages. (1) Hinton & Ahlers (1999). The issue of “authenticity” in California language restoration. Anthropology & Education Quarterly, 30 (1), 56-67. (2) Gick, Bernhardt, Bacsfalvi, Wilson (2008). Ultrasound imaging applications in second language acquisition. Phonology and second language acquisition, Benjamins: 309-22.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.013 | 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".