Speech understanding in background noise remains the biggest challenge for people with hearing loss. According to Sonova, this Phonak technology provides unprecedented speech clarity from any direction, with an unparalleled improvement in SNR in noise of 10dB.
Building on the Infinio platform of conventional looking hearing-aids, Phonak is now promoting its Audéo Sphere Infinio model which addresses speech understanding in noise. This is essentially the same approach that all consumer technology companies are exploring and implementing in adaptive hearables - using AI for speech separation and enhancement. Sonova says that its new Infinio platform offers the new Phonak ERA chip, with more processing than existing chips in the hearing-aid industry, and overcomes the industry's current constraints of processing power required for real-time adaptive algorithms.
In the new Audéo Sphere Infinio model, the ERA processor is complemented by a dedicated, proprietary NPU chip named Deepsonic, that handles AI-based real-time processing to filter noise and provide speech from noise separation, before speech enhancement for the specific needs of the user. Sonova says that, with this implementation, users are two to three times more likely to understand speech from any direction compared to hearing-aids currently in the market, including those from Phonak.
Phonak also says that the Deepsonic chip not only provides real-time AI processing to instantly separate speech from background noise, but, unlike existing technologies, also offers dynamic, real-time adjustments, allowing users to engage in conversations from any direction. The chip's Deep Neural Network (DNN) architecture is able to handle 4.5 million neural connections, trained with over 22 million sound samples. With 21 times more memory and 4 times more power efficiency, this chip is 53 times more powerful than existing chips used in hearing-aids and is capable of performing 7,700 million operations per second.
As a reference, current platforms available for consumer hearables include the Greenwaves GAP9 ultra-low power processor that offers up to 50,000 million operations per second (or 50 giga-operations). For perspective, Qualcomm's Snapdragon X Elite Compute Platform (laptop class) includes a neural processing unit that’s capable of 45 trillion operations per second.
"We are incredibly excited to bring the Audéo Sphere Infinio to our users. This is more than just a hearing aid; it's a game-changer for anyone struggling with hearing in noisy environments," says Robert Woolley, Group Vice President Hearing Instruments at Sonova. "With our proprietary ERA and Deepsonic AI chips, we've achieved a new level of speech clarity that we're proud to share. This innovation highlights our dedication to providing the best possible sound quality and user experience."
This technology is exclusively available in the new Phonak Audéo Sphere Infinio model. With this announcement, Phonak also introduced a handful of other receiver-in-the-canal hearing aids without this technology and that benefit only from the new ERA chip upgrade. There's also the Virto R Infinio, Phonak's first rechargeable custom in-ear hearing aid (pictured above), which doesn't benefit from the company's latest AI-powered technology but could be an interesting alternative in terms of form-factor.
For some reason, these products targeted for prescription by medical professionals continue to be a complicated maze of too many options and multiple layers of different technologies that, in the end, do not benefit the people who need hearing-aids.
www.phonak.com
