LiveDescribe: Can Amateur Describers Create High-Quality Audio Description?
Bibliographic record
Abstract
Introduction The study presented here evaluated the usability of the audio description software LiveDescribe and explored the acceptance rates of audio description created by amateur describers who used LiveDescribe to facilitate the creation of their descriptions. Methods Twelve amateur describers with little or no previous experience with audio description used the software LiveDescribe to describe a single episode of a 20-minute comedy show. Seventy-five reviewers who were blind, had low vision, or were sighted then rated the descriptions using a number of criteria, including overall quality and entertainment value. Results LiveDescribe was found to be easy to use and useful. Three of the 12 describers produced descriptions that were rated as of good overall quality, 6 produced descriptions that were rated as of medium quality, and 3 produced descriptions that were rated as of poor quality. Discussion These findings indicate that amateur description is feasible even with minimal training in either description itself or LiveDescribe. Audiences’ preferences for description seem to be based on various characteristics of describers, such as the describers’ vernacular and tone of voice and the length and timing of the descriptions. Implications for practitioners If amateur description is indeed feasible, the quantity of audio descriptions that are available to the general public could be increased significantly. A great deal of informal description is already created by families and friends of individuals who are visually impaired through the “whisper method.” If this description process could be captured and formalized through a tool such as LiveDescribe and shared through the Internet, many more descriptions could be made available.
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 | 0.011 | 0.047 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.016 | 0.004 |
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".