2021 Speech Industry Award Winner: Voiceitt Makes Voice More Accessible
Fresh off a $15 million funding round completed a year ago, Israel-based Voiceitt, a provider of commercial speech recognition technology, is refocusing attention on applications that can translate unintelligible and atypical speech in real time, enabling people with severe speech impairments and other disabilities to communicate by voice.
“As we continue our growth, we are committed to our mission of making speech accessible to all. Our long-term vision is to integrate Voiceitt’s customizable speech recognition with mainstream voice technologies to enable environmental control through a universally accessible voice system,” said Sara Smolley, Voiceitt’s executive vice president and cofounder, in a statement. “Voiceitt’s versatile technology can be applied in a range of voice-enabled applications in diverse contexts and environments.”
A chief target of that technology enablement has been Amazon’s Alexa, where Voiceitt had huge success this year.
The company in December made it possible for people with speech impairments to use the Voiceitt mobile app to access and interact with the Alexa personal assistant.
“Integration of Voiceitt’s speech recognition with a powerful service like Alexa further demonstrates Voiceitt’s value proposition in a rapidly expanding industry and of our vision to make speech recognition accessible to everyone,” said Danny Weissberg, CEO and cofounder of Voiceitt, in a statement at the time.
“In collaboration with Voiceitt, we have been able to bring Alexa to even more customers,” said Peter Korn, director of accessibility at Amazon Lab126, in a statement. “We strive to make all Amazon products and services as delightful and easy to use as possible for everyone. Voiceitt’s integration with Alexa helps us do just that, enabling customers with speech impairments to enjoy all that Alexa has to offer and help them live more independently.”
Voiceitt’s product launch followed a successful pilot with Inglis House, a Philadelphia long-term care community for people with physical disabilities. In the pilot, Voiceitt worked closely with Inglis’s Assistive Technology Team to help participants with cerebral palsy and atypical speech use Voiceitt and Alexa to perform daily tasks independently, such as controlling channels on their TVs or playing music.
“Voiceitt takes the intuitiveness of Alexa and opens it up to an even larger population. It will prove to push beyond the boundaries of possibility for assistive technology while empowering its users,” said Dyann Roth, president and CEO of Inglis, in a statement.
“Commercially available solutions do not always work well for people with speech impairments, who may need them the most. Through Alexa and Voiceitt, Inglis residents and many others in our community will be able to access these innovative technologies for the first time,” Roth said.
Voiceitt also worked with the Department of Intellectual & Developmental Disabilities (DIDD) of Tennessee and the Arc of Tennessee to perfect its speech technology.
“Our work with Voiceitt is already yielding impactful results for people with intellectual disabilities,” said Brad Turner, DIDD’s commissioner, in a statement.
Voiceitt in June launched its app on the Apple Store. The Voiceitt app, which empowers individuals with speech impairments to navigate their environments and control smart home devices using voice commands, can be downloaded for free by individuals or in volume by institutions, nursing facilities, and organizations.
The Voiceitt experience begins with a simple training phase. After the user repeats a set of words and phrases several times, the Voiceitt app builds an artificial intelligence-powered speech model that allows the individual to communicate specific commands.
Voiceitt’s proprietary automatic speech recognition engine, which combines machine learning with speech analysis technology, can recognize not only atypical speech but also speech patterns—including utterances, cadences, breathing pauses, and nonverbal sounds—in any language. App users can build a personalized dictionary and train the app to recognize their unique pronunciations, a process that takes about five minutes per phrase. The app then recognizes users’ trained phrases in real time and translates output into typical speech, enabling users to convey complex sentences that help them better navigate their daily lives.
“The degree of independence our app helps give to members of our user community has inspired us to develop our technology even further and make it available to even more people. Our goal is to give voice to everyone,” Weissberg said further.