Real-Time AI Featured in New Hearing Aid Line

Phonak, a Sonova brand, has launched a new family of hearing aids based on the Infinio platform—including the Audéo Sphere Infinio—the world’s first hearing aid powered by a dedicated real-time artificial intelligence (AI) chip for speech-from-noise separation.

Speech understanding in background noise remains the most frustrating challenge for people with hearing loss. Phonak’s technology, however, helps clarify speech from any direction and improves Signal-to-Noise Ratio (SNR) in noise of 10dB.¹
 
The Infinio platform offers improvements in sound quality from the first moment: Infinio achieves a 93% user preference from the first fit compared to leading competitors,² a 45% reduction in listening effort,^*3 21% less fatigue,^**4 and a 61% improvement in speech understanding (when combined with Roger ON). ^***5 The platform enables uninterrupted hands-free calls and streaming across twice the distance, compatible with all Bluetooth-enabled devices and the Audéo Sphere Infinio allows users to clearly hear speech amid noise, according to the company.
 
Building on the Infinio platform, the Audéo Sphere Infinio addresses the top challenge of understanding speech amongst noise with a new paradigm-shifting approach. With 53 times more processing power versus existing industry chips, it overcomes the current constraints of processing power to unleash AI’s full potential. In addition to the ERA chip, the Audéo Sphere Infinio is powered by a dedicated, proprietary chip called DEEPSONIC; a world-first, real-time AI sound processing chip. Its key features include: 

• Spheric Speech Clarity: Clear speech from any direction instantly.
• Speech from Noise Separation: Advanced AI separates speech from unwanted noise.
• Signal-to-Noise Ratio (SNR) Improvement: Achieves an SNR improvement of 10dB for better speech understanding in noisy environments, superior to competitor devices by up to 3.7dB.¹ Users are two to three times more likely to understand speech from any direction compared to the two leading competitors.⁶

Phonak’s proprietary DEEPSONIC chip is the first of its kind, providing real-time AI processing to instantly separate speech from background noise. Unlike existing technologies, DEEPSONIC offers dynamic, real-time adjustments, allowing users to engage in conversations from any direction. The chip’s AI architecture includes a deep neural network—4.5 million neural connections trained with more than 22 million sound samples, and unprecedented processing power (so Phonak claims). With 21 times more memory and four times more power efficiency, this chip is 53 times more powerful than existing chips and is capable of performing 7,700 million 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,” said 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.”
 
Phonak also introduced a portfolio of hearing aids with some products available to order by hearing care professionals. These devices are based on the next-gen Infinio platform, featuring:

• Audéo Sphere Infinio: Receiver-In-the-Canal (RIC), unique dual chip technology inside, ERA and DEEPSONIC, the world’s first hearing aid with a dedicated AI chip for unprecedented speech clarity in noise.
• Audéo R Infinio: RIC form factor with ultra-responsive ERA chip inside, delivering exceptional sound quality and industry-leading connectivity.
• CROS R Infinio: For unaidable hearing loss in one ear, CROS R is used in combination with Phonak Audéo, offering exceptional sound quality and connectivity as well as increased battery runtime.
• Virto R Infinio: Phonak’s first rechargeable custom hearing aid (In-The-Ear/ITE) offering exceptional sound quality and industry-leading connectivity.

Since 1947, Phonak, a Sonova brand, has been dedicated to improving the quality of life for people with hearing loss by offering a broad portfolio of hearing solutions. 
 
References
¹ Raufer, S., Kohlhauer, P., Jehle, F., Kühnel, V., Preuss, M., Hobi, S. (2024). Spheric Speech Clarity proven to outperform three key competitors for clear speech in noise. Phonak Field Study News retrieved from https://www.phonak.com/evidence
² Stewart, E., Adler, M., Seitz-Paquette, K., “Adaptive Phonak Digital (APD) 3.0 is the preferred first fit compared to a leading competitor device”. Phonak Field Study News in preparation expected August 2024
³ Habicht, J. & Schuepbach-Wolf, M. (2024). Speech Enhancer reduces subjective listening effort of speech by up to 45%. Phonak Field Study News retrieved from www.phonak.com/evidence
⁴ Latzel, M, Heeren, J and Lesimple, C. (2024) “Speech Enhancer reduces listening effort and fatigue.” Phonak Field Study News retrieved from www.phonak.com/evidence
⁵ Thibodeau L. M. (2020). Benefits in Speech Recognition in Noise with Remote Wireless Microphones in Group Settings. Journal of the American Academy of Audiology, 31(6), 404–411. https://doi.org/10.3766/jaaa.19060. Appleton-Huber, J et al “Speech 6 Enhancer reduces listening effort of speech from adjacent room.” Phonak Field Study News in preparation expected July 2024
⁶ Wright, A., Kuehnel, V., Keller, M., Seitz-Paquette, K., Latzel, M. (2024). “Spheric Speech Clarity applies DNN signal processing to significantly improve speech understanding from any direction and reduce the listening effort.” Phonak Field Study News retrieved from https://www.phonak.com/evidence
 
* In quiet listening situation for adult hearing-impaired subjects with moderate to severe hearing loss.
** Speech Enhancer on versus off, moderate to severe hearing loss.
*** Adults with sensorineural hearing loss using Roger Select with a compatible hearing aid or cochlear implant compared to hearing aid or cochlear implant alone tested in a simulated noisy restaurant setting.