New App Uses ALS Patients with Speech Disabilities’ Own Voices to Help Them Communicate

The first app for amyotrophic lateral sclerosis (ALS) patients who have begun to lose their speaking abilities was recently launched by UK company Therapy Box. The app was designed to substitute standard text-to-speech synthesis with a synthesizer based on the patient’s own voice. The Predictable 4 app has entered the ModelTalker program, at a cost of $140 annually, as a way of helping patients with ALS and other disabling diseases maintain effective communication and a sense of independence.

The ModelTalker program was designed by a research team led by Tim Bunnell, Ph.D. at the Nemours Speech Research Laboratory in Wilmington, DE, in order to provide a new usable solution to positively affect the lives of people who struggle with communication difficulties. It is the first iOS app to enter this unexplored field and use the actual voices of patients to communicate.

“Everyone’s voice is personal; it defines who we are and is part of what makes us unique as human beings,” added the co-founder of Therapy Box, Rebecca Bright. “Previously, those who can no longer speak, for whatever reason, could use an ‘off the shelf’ communication tool featuring a generic voice, which in many cases does not reflect the age or local dialect of the person. Stephen Hawking’s synthetic voice, for example, has an American accent. The latest app means these people can use their own voice, or a close approximation of their voice, so that they continue to sound authentically like themselves when they do not have the power to communicate verbally.”

It is already in use, with ALS patient Peter Pierce being one of the first to try it out in lieu of using a robotic voice to communicate. He already used Predictable and created a ModelTalker voice while he was still able to talk, using Predictable for over 20 months. He said the use of Predictable with ModelTalker was “liberating.”

Another patient, this time in the United States, who decided to use the app is Katie Hassell, 10, of Garnet Valley, PA. She suffers from developmental disabilities that caused her speech impairment, so she decided to use her own voice at the Nemours speech lab. With the help of her brother Ryan, she recorded about 800 sentences for the program to create a synthetic voice.

“The software enables us to blend Katies’ pitch and unique speech features with Ryan’s intelligible speech, thus creating a ModelTalker voice that will allow her to converse and conveys Katie’s vocal identity,” explained Bunnell. “It is very gratifying to be able to provide ModelTalker voices on the app. As a pediatric healthcare system with a significant special needs population, Nemours is always looking for ways to reach children who may benefit from new assistive technologies. It’s exciting to see our research efforts go from the lab to the iPad.”

Apps like TherapyBox’s ModelTalker are some of the most important feats of research and programming in healthcare, as they provide patients with disabilities a positive outlook, which has been shown time and again to be crucial to more favorable disease outcomes.