Print this page|
The Design of Human-Powered Access Technology
In this paper, the authors frame recent developments in human computation in the historical context of accessibility, and outline a framework for discussing new advances in human-powered access technology. Authors: Jeffrey P. Bigham, Richard E. Ladner and Yevgen Borodin.
People with disabilities have always overcome accessibility problems by enlisting people in their community to help. The Internet has broadened the available community and made it easier to get on-demand assistance remotely. In particular, the past few years have seen the development of technology in both research and industry that uses human power to overcome technical problems too difficult to solve automatically.
Technology alone is still far from being capable of solving many real accessibility problems
The tendency in technical fields is to concentrate on fully automated solutions, but it is clear that, despite tremendous
advances over the past few decades, technology alone is still far from being capable of solving many real accessibility problems that people with disabilities face in their everyday lives. For example, OCR seems like a solved problem until it fails to decipher the text on a road sign captured by a cell phone camera, object recognition works reasonably well until the camera is held by a blind person and the laudable 99% accuracy reported by commercial automatic speech recognition
systems falls off precipitously on casual conversation or any time it has not been trained for the speaker.
Even the automatic techniques used by the screen-reading software to convey the contents of the computer screen to blind people are error-prone, unreliable, and, therefore, confusing. As a result, the many access technology is used only by people who are technically-savvy. When access technology is unreliable, it is abandoned altogether.
The paper presents a set of 13 design principles for humanpowered access technology motivated both by historical context
and current technological developments. We then demonstrate the utility of these principles by using them to compare several existing human-powered access technologies.
Read further at: http://hci.cs.rochester.edu/pubs/pdfs/design-of-hp-at.pdf