Atypical Speech Recognition Startup Voiceitt Debuts iOS App for Smart Home Control and Communication

Israeli speech recognition technology startup Voiceitt has launched a new iOS app to help people with atypical and impaired speech communicate. The Voiceitt app is designed to repeat what the user says in a way intelligible to other people and to voice assistants operating smart home devices, training and improving with use.

Voiceitt iOS

Voiceitt’s tech works with a user to train the mobile app’s automatic speech recognition program to analyze not only words, but the speech patterns, rhythms, and non-verbal sounds. The personalized dictionary gets better and faster at comprehending what the user says with practice. Five minutes with a phrase is usually enough. The user can then converse and be understood far more easily than they might without the app. Those conversations can be with humans or with voice assistants.

“I originally envisioned Voiceitt helping people communicate with other people,” Voiceitt CEO Danny Weissberg told Voicebot in an interview a few months ago. “As the world started to change and smart speakers became more and more part of our lives, we actually realized we can do much more than that. We have technology that can improve those products and make them accessible to those that need them most.”

There are a growing number of efforts examining how to make voice assistants more accessible to people with atypical speech patterns. For instance, Apple has researchers pursuing techniques that will enable Siri to spot when someone is stuttering in order to compensate and ensure it doesn’t interrupt or misunderstand the user. Google’s Project Euphonia is built with an eye on a similar goal, training voice assistants to understand people with unique speech patterns.

Alexa Access

The Voiceitt app can speak aloud and theoretically talk to any voice assistant, but Voiceitt is particularly well suited for Alexa devices as the startup worked with Amazon’s Lab126 to teach Voiceitt how to turn a user’s words into Alexa-friendly data, communicating silently with the voice assistant instead of just repeating the words aloud. Deep Alexa integration means there’s no need for a specific Alexa skill, either. Voiceitt was part of the 2018 Amazon Alexa Accelerator and eventually became an Amazon Alexa Fund portfolio company. The startup has raised more than $15 million, including a $10 million Series A funding round led by Viking Maccabee Ventures last August. The iOS app is currently free to try, but will likely switch to a subscription system in the near future.

“In collaboration with Voiceitt, we have been able to bring Alexa to even more customers,” Amazon Lab126 director of accessibility Peter Korn said 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 Debuts Direct Alexa Control for People with Speech Disabilities

Voice Tech Startup Voiceitt Raises $10M to Help People with Speech Impairments Talk to Voice Assistants and Other People

Apple is Developing Stutter Detection for Siri