A research team led by scientists from the University of Buffalo modified a noise-canceling headset that allowed an electronic device to “see” and translate sign language when paired with a smartphone.
The system, dubbed SonicASL, achieved 93.8% efficiency in indoor and outdoor tests involving 42 words. Examples of the vocabulary used are “love”, “space” and “camera”. Under the same conditions, using 30 simple sentences – for example, “Nice to meet you” – SonicASL performed 90.6%.
There is still a lot of work to be done before the technology can enter the market as a commercial product, the researchers said. For example, you need to significantly expand your SonicASL vocabulary. In addition, the system must be able to read facial expressions, which is an important component of sign language.
The researchers intend to continue working on the system. Their main motive is that there are more than 72 million hearing-impaired people worldwide. They all have difficulty communicating with other people. The task is very difficult because deaf people around the world deal with over 300 different sign languages.
According to the researchers, the invention uses Doppler technology to “feel” tiny vibrations or echoes in acoustic waves generated by hand movement. The research results will be presented at the ACM Conference on Ubiquitous Computing (UbiComp), which will be held from 21 to 26 September.