By Jennifer Kite-Powell | Forbes.com | Dec 19, 2019
In a 2018 Accenture Digital Health report, 75 percent of respondents said technology played an essential role in managing their health. When it comes to artificial intelligence (AI) powered digital health and wearable devices, 72 percent said they’re willing to share their wearable data with their health insurance plan. The report also found that when AI and robotics consumer interest surpassed the choices available today for virtual care.
At the Consumer Electronics Show (CES) 2020 in Las Vegas, January 7-10, 2020, AI-powered digital health devices will be prevalent. For people with hearing loss or who are visually impaired, machine learning in digital health devices can open new possibilities to hear conversations more clearly or see the world around them.
AI and Vision
As part of the TechLeap.nl delegation of 50 Dutch startups in The Netherlands pavilion at CES, you’ll find the startup, Envision. The company is focused on giving sight back to the visually impaired using AI to make that happen.
Envision is a prototype that works with smartphones and smart glasses such as Google Glass. It is designed to turn a user’s smartphone camera into an extra set of eyes, speaking the visual information in front of the user.
The company says the prototype can also read digital and handwritten text from screens, food packaging and posters. The company was a Google Play 2019 Accessibility Award winner.
AI and Hearing
Bruce Sharpe, Founder and CEO of Singular Hearing said that more than 466 million people worldwide are affected by some degree of hearing loss.
“This staggering number is rapidly increasing. Modern hearing aids are miracles of miniaturization, customizability and flexibility. It’s not their fault that noise has continued to be a problem,” said Sharpe. “Even powerful desktop computers were not good at handling noise. That is, until the last few years when good machine learning approaches came along.”
“Now we finally have new, more effective solutions for noise, thanks to the perfect storm of new machine learning algorithms, the availability of better data sets, powerful GPUs for training, and smartphones in everyone’s pocket that are capable of running the results,” added Sharpe.
The Canadian startup’s new product, HeardThat, is an app that uses AI to tune out background noise, which enables users with hearing loss to hear speech more clearly.
The company says that this allows users to engage in conversations they otherwise have trouble hearing HeardThat uses machine learning algorithms to separate speech from noise. It listens to the noisy environment and delivers denoised speech to the user’s Bluetooth-enabled hearing aid or other listening devices via their smartphone.
Sharpe says that other hearing assistance solutions are either devices like earbuds, which are inevitably under-powered, or phone apps that are using traditional technologies that have not been up to the task.
“They are not specifically addressing the noise problem, and nothing much new has happened in that direction for a long time,” said Sharpe. “Most phone hearing apps are trying to replace hearing aids. They amplify and filter sound. They give the user a lot of knobs and dials to turn to match their hearing capabilities.”
“We define the problem differently [..] and are focused on one thing: separate the speech from the noise, and let your hearing aids do their job to help with the speech,” said Sharpe.
Sharpe says that applying machine learning to hearing problems is quite new, but the results are already better than what done before.
“It has the unique ability to keep getting better the more it gets used. Machine learning algorithms need a lot of computing resources [..] and today’s smartphones are basically little supercomputers, and they can do what is needed,” added Sharpe.
“The human hearing system is amazingly complex, and fixing problems with it is not like putting on glasses to improve vision, not yet,” said Sharpe. “But we’re on a path where we can solve specific problems today and eventually integrate those solutions into more comprehensive remedies for a broad range of hearing issues.”