The cell phone as the computer

If you had been told ten years ago that by the end of 2007 there would be an international network of wirelessly-connected computers throughout the developing world, you might well have said it wasn’t possible. But it’s possible, and it is created, and it continues to expand.

We are talking, of course, about the mobile phone network.

Along with the internet, with which it is rapidly merging, this is the most astonishing technology story of our time, and one that has the power to revolutionise access to information across the developing world.

Imagine a system that lets managers at a national level, who probably do have access to the internet on a desktop computer, coordinate and transmit SMS-based continuing education messages to the computers — sorry, to the cell phones — of those health professionals. What a difference would that make to the level of up-to-date knowledge available to a clinic worker? And how would that impact the quality of care?

And what other groups might benefit from that kind of educational program? What about teachers? What about students?

So, it’s time that we recognised that for the majority of the world’s population, and for the foreseeable future, the cell phone is the computer, and the portal to the Internet, and the communications tool, and the schoolbook, and the vaccination record, and the family album, and many other things, just as soon as someone, somewhere, sits down and writes the software that allows these functions to be performed.

Using your voice to pilot your computer

An interdisciplinary team of scientists of the University of Washington (UW) has developed Vocal Joystick, a software which enables people with disabilities to control their computers using the sound of their voice and without the need to use a mouse. Their virtual computer mouse driven by sound has already been tested at the UW Medical Center with spinal-cord-injury patients and other participants with varying levels of disabilities. The researchers, who developed their own voice-recognition technology, hope to have a prototype available online this fall. But read more…

So how does this software work? Here are some short excerpts from the Seattle Times mentioned in the introduction. “There are several options for people who needed accommodations in using computers, but the UW software is distinguished on several levels. For one, it doesn’t use standard voice-recognition technology. Instead, it detects basic sounds at about 100 times a second and harnesses them to generate fluid, adaptive cursor movement. Vocal-joystick researchers maintain the system is easier to use because it allows users to exploit a large set of sounds for both continuous and discrete movement and to make visual adjustments on the fly. Kurt L. Johnson, a professor in the Department of Rehabilitation Medicine at the UW, says he believes the software has great potential because it is easy to both learn and use.

Here are some more details about the Vocal Joystick voice-recognition technology engine. “The VJ system consists of three main components: acoustic signal processing, pattern recognition and motion control. First, the signal processing module extracts short-term acoustic features, such as energy, autocorrelation coefficients, linear prediction coeffients and mel frequency cepstral coefficients (MFCC). Signal conditioning and analysis techniques are needed for accurate estimation of these features. Next, these features are piped into the pattern recognition module, where energy smoothing, pitch and formant tracking, vowel classification and discrete sound recognition take place. This stage involves statistical learning techniques such as neural networks and dynamic Bayesian networks. Finally, energy, pitch, vowel quality and discrete sound become acoustic parameters to be transformed into direction, speed and other motion related parameters. The application driver takes the motion control parameters and launches corresponding actions.”

Notes

Vocal Joystick -^- голосовой координатный манипулятор; spinal-cord-injury patients - пациенты с повреждением спинного мозга; voice recognition technology - технология распознания голоса; harnesses – аккумулирует; autocorrelation coefficients - коэффициент взаимозависимости.