How Speech Technologies Can Level the Playing Field
Improved Sound Recognition
While technology to recognize speech and turn it into text has been around for several years, and the technology’s capabilities continually improve, the technology isn’t designed to recognize non-speech sounds, such as a baby crying or someone falling, says John Amien, vice president of sales for ID R&D, a company that provides AI and machine learning acoustic detection that augments the sound recognition technology for provider Wavio.
Wavio was founded by Greyson Watkins after an incident where his friend’s daughter fell down the stairs. Being very hard of hearing, Watkins did not hear her cries for help.
With sound awareness, Wavio’s technology can detect and intelligently respond to specific sounds in emergencies, natural disasters, and other life-threatening scenarios, alerting users to “emergency” sounds via an app or through the company’s See Sound smart home device.
When a sound occurs inside or close to a household, the nearest See Sound or other smart device registers the increase in volume and lights up and interprets the sound for the user. See Sound then interprets the sound it hears and relays the interpretation—such as “someone is crying”—to the customer.
While assistive technologies for those who are hearing or visually impaired get support from various groups—like the Industries for the Blind and Visually Impaired, the Chicago Lighthouse for the Blind and Visually Impaired, the National Association of the Deaf, and others—there is not as much knowledge of, and therefore not as much assistive technology for, those who are speech impaired, according to Tara Rudnicki, president of Tobii Dynavox, which makes online devices, about the size of an Amazon Show, that use eye-tracking technology for access.
Eye tracking has gotten more attention as a result of the heightened awareness of ALS, primarily from the ice bucket challenge in 2014, but this and other assistive technologies for the speech impaired are still largely untapped, according to Rudnicki. She says, “There’s only 10 to 15 percent penetration in the market.”
Eye tracking is a technology particularly important for those with ALS, also known as Lou Gehrig’s disease, because the muscles controlling the eyes tend to be the last ones to fail as the disease progresses. Many on the autism spectrum can also benefit from the technology, according to Rudnicki.
The eye tracker sends out near-infrared light, which is reflected in the user’s eyes. The eye tracker’s cameras pick up those reflections and use algorithms to determine where the user is looking. It is essentially designed to replace the mouse for a computer but has other applications as well.
So where does speech technology come in?
Individuals who are unable to speak or use their fingers, hands, or any other body part in a controlled manner to operate a keyboard, mouse, or touchscreen can use eye tracking to write messages using only their eyes and then have the computer speak those messages out loud.
Messages can also be sent via email, chat, SMS, or by any other means of long-distance communication. According to Rudnicki, an eye-tracking user can access all of the functions of a standard Microsoft tablet or desktop computer through the use of gaze interaction. This makes it possible for many to attend school or stay employed, maintain a hobby, pass time, and sharpen skills.
Speech pathologists and other professionals who work with the speech impaired are the key constituents to get the speech-related assistive technologies out to this market, Rudnicki adds.
Beyond the moral and legal reasons for adding assistive technology, there are business reasons to help those who are physically impaired as well, says Tim Quinlan, senior user experience architect at R2integrated (R2i), a digital marketing agency.
“The [Americans with Disabilities Act] doesn’t specifically mention websites, though there are a number of lawsuits in the courts right now,” Quinlan says.
OrCam Read is a digital assistive reading device that converts text to speech.
Thanks to voice banking, digitized speech retains the essence of the original speaker
The market for assistive tech is growing, but pain points still exist
New startup utilizes 21st century AI technology to help speech-language pathologists and the language impaired.