AI-powered technology could help people with speech disabilities work remotely

() – You’ve probably experienced the frustration of a smart speaker or AI assistant not listening to you or understanding you properly. For people with non-traditional speech, this can happen in almost every interaction with this type of technology. Israeli startup Voiceitt aims to change that.

By using personalized voice models, their AI-powered speech recognition system helps people with speech impairments, caused by conditions such as cerebral palsy, Parkinson’s, Down syndrome or stroke, communicate more effectively with people and digital devices.

For Sara Smolley, co-founder of Voiceitt, facilitating speech recognition for non-standard speech patterns is a personal mission.

“My grandmother was diagnosed with early-onset Parkinson’s disease,” she said. “By the time I was born, she had already lost most of her motor skills and her speech was affected.”

Voiceitt was launched as an app in 2021 and functioned as a simple voice translator that converted non-standard speech into audio. The AI ​​is trained by recording the user saying around 200 common phrases.

Smolley said the original idea was to facilitate in-person communication, but technology has now adapted to remote workers as well.

Voiceitt has developed integrations with WebEx and ChatGPT, along with a Google Chrome extension, that convert non-standard speech into captions displayed on the screen. The company is also partnering with Zoom and Microsoft Teams.

“One of the things that really stood out to me was the importance of accessibility technology in the workplace,” Smolley said. “What a (wheelchair) ramp was to yesterday’s office building, Voiceitt is to today’s remote workplace,” he said.

The software is sold as a per-minute or per-user license, with prices ranging from $20 to $50. Licenses can be purchased in bulk for workplaces and health or educational institutions.

“People are using Voiceitt not only for video conferencing, but also for writing documents, emails, posting on LinkedIn, and accessing web browsers using voice,” Smolley explained. “This has opened up the digital world to people who previously wouldn’t have been considered for certain jobs or been able to communicate with colleagues or clients.”

Among Voiceitt’s users is Colin Hughes, a former BBC producer who became accessibility advocate Hughes, who suffers from muscular dystrophy, relies on dictation for his digital interactions, making him acutely aware of both the potential and limitations of current technologies. Hughes has used Voiceitt to compose emails and dictate longer texts.

“I found the Voiceitt app to be impressively accurate with my atypical speech, and its training and setup process was straightforward,” Hughes said, though he highlighted critical shortcomings for professional users. “Many people with speech issues and upper limb disabilities need more than just speech-to-text conversion,” he noted.

He advocates features like voice-controlled cursor control and improved dictation recognition for composing long content, and says Voiceitt works best for single-sentence messages.

Hughes emphasizes the need for more comprehensive voice recognition technology that would allow users to do things like manage emails and format documents using their voice.

He sees a future where technology will play a bigger role in accessibility, adding: “This whole sector needs a shake-up. Voiceitt, with better access to the major platforms, could be the one to lead this change.”

According to Smolley, there have been significant advances in voice recognition technology in recent years.

One example is the Speech Accessibility Project, a research project led by the Beckman Institute for Advanced Science and Technology at the University of Illinois, which collects speech data from people with different conditions to build algorithms to help people with non-standard speech.

Earlier this year, Apple (AAPL) launched its AI-powered “Listen for Atypical Speech” feature, which uses machine learning to recognize a wider range of speech patterns.

With technology capturing and storing personal data, such as voice recordings, privacy can be a concern for users. Smolley says her company complies with European Union regulations, which she calls “the highest standards in the world in terms of data privacy.”

“If user data is retained in our database with their consent, it is anonymized and de-identified and used to augment our data stack and improve our algorithm,” he added.

Smolley believes Voiceitt’s technology can change people’s lives. “We want people to not only be more independent in their lives and work,” Smolley says, “but also to be able to enjoy technology and have fun.”