The University of Illinois together with great technology companies What Manzana, Google, amazon, Goal Y microsofthave come together to develop a project that allows voice recognition functions to include users of devices that they experience difficulties and that technology is also within their reach.
The Speech Accessibility Project (Speech Accessibility Project) aims to make it easier for people with a wide spectrum of speech problems to have access to technology of voice recognition and for this, it is registering the voices of people with these inconveniences.
According to Mark Hasegawa-Johnson, a professor of computer and electrical engineering at the University of Illinois, who is leading the project, “the option to communicate and operate devices with voice is very important for anyone who interacts with technology or digital economy today”.
The role that the Business of technology will be to provide the Technological infrastructure necessary to continue working towards this goal, which focuses on making technology more accessible to people with disabilities.
“Interfaces of voice they must be available to everyone and that includes people with disabilities. This is difficult because it requires infrastructure that can be provided by leading companies in technologyHasegawa said. In addition, he stated that an interdisciplinary team specialized in areas such as: linguistics, speech, Artificial Intelligence, security and privacy has been formed.
A statement issued by the educational institutionindicates that you are working with people with different disabilities such as amyotrophic lateral sclerosis, also known as Lou Gehrig’s disease, as well as Parkinson’s, cerebral palsy and Down syndrome.
That is why the institution affirms that the team made up of the technology companies It can be of great help to achieve an adequate development of speech recognition. “Instead of being separate and having their own initiatives from different companies, the groups will collaborate to help accelerate technologies that help these communities.”
How the project is carried out
According to Web page of the Beckman Institute for Advanced Science and Technology, who are part of the university and manage the project, indicates that the work that will be carried out jointly with technology companies will consist of using Artificial Intelligence (AI) Along with the capabilities of machine learning.
In this way, thanks to the recording of various voices of people with speech difficulties, it will be possible to ‘teach’ the information systems how it is that people with disabilities communicate and, in this way, improve your response when interacting with them.
From what is known about the project, at the moment the investigations and the technological development it is only being produced in English. This indicates that the results of this work could benefit more than 17.5 million people in the United States alone, who suffer from these problems, as indicated by the National Institute on Deafness and Other Communication Disorders (NIDCD)