Co-designing a speech interface for people with dysarthria
Bibliographic record
Abstract
Purpose – The purpose of this paper is to describe the development and evaluation of CanSpeak which is an open-source speech interface for users with dysarthria of speech. The interface can be customized by each user to map a small number of words they can speak clearly to commands in the computer system, thereby adding a new modality to their interaction. Design/methodology/approach – The interface was developed in two phases: in the first phase, the authors used participatory design to engage the users and their community in the customization of the system, and in the second phase, we used a more focussed co-design methodology during which a user of the system became a co-designer by directly making new design decisions about the system. Findings – The study showed that it is important to include assistive technology users and their community in the design and customization of technology. Participation led to increased engagement, adoption and also provided new ideas that were rooted in the experience of the user. Originality/value – The co-design phase of the project provided an opportunity for the researchers to work closely with a user of their system and include her in design decisions. The study showed that by employing co-design new insights into the design domain can be revealed and incorporated into the design that might not be revealed otherwise.
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 | 0.009 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".