IRVINE, Calif., June 07, 2023 (GLOBE NEWSWIRE) -- AONDevices, a provider of super low-power, high-performance on-device AI processors and full stack solutions, today announced the launch of its groundbreaking AONDenoise™ – a compact, efficient edge AI denoising technology. Designed for applications that require minimal power and latency, AONDenoise is one of the smallest denoising algorithms available, making it an ideal AI speech enhancement for use in hearing aids, wireless earbuds, smartphones, and wearables.
Traditionally, AI speech enhancement is performed using arrays of multiple microphones, beamforming and large Digital Signal Processing (DSP) algorithms. This method, currently implemented in today’s smartphones and other devices, requires huge amounts of memory and power, which is costly. Through its state-of-the-art, AI-based denoiser, AONDevices is addressing these concerns – and leading the way forward into a new era of edge AI.
Known for its innovation in super low-power edge AI human-machine interfaces, AONDevices is expanding its focus to include innovations in human-human interfaces. With just 50K parameters, the AONDenoise solution is one of the most compact denoising algorithms on the market. It is multiple orders of magnitude smaller than traditional DSP noise reduction methods and at least an order of magnitude smaller than current AI-based denoisers. The AONDenoise solution addresses the need for customizable noise cancellation in ultra-low power, real-time processing devices, such as chips used for hearing aids. The algorithm can target a wide range of noises, such as chatter in a crowded restaurant, wind noise, dogs barking, babies crying, or keyboards clicking.
The AONDenoise solution has the potential to revolutionize various applications, including:
- Hearing Aids: Customizable noise cancellation for improved performance in different environments.
- Wireless Earbuds: Optimal audio quality in transparency mode, conversation mode, and voice calls.
- Smartphones: Clearer voice quality during calls, especially in outdoor settings.
- Podcasting: Crystal-clear audio streaming even in noisy surroundings.
Leveraging AI and deep learning neural networks, the AONDenoise solution can distinguish human speech from background noise. To maximize the efficiency of this neural network, AONDevices has developed a dedicated software tool suite. This allows both in-house and customer development to customize and train the system to handle specific noise environments or a broader range of noises.
AONDevices’ new Technical Director, Dr. Youhong Lu, commented that AONDenoise is poised to significantly enhance the next generation of wearable and mobile devices. “AONDenoise is a truly remarkable accomplishment in AI speech enhancement,” said Dr. Lu. “A small yet incredibly effective algorithm that works with just a single microphone will positively impact many lives. I have been incredibly impressed by AONDevices’ achievements and am excited for the upcoming technology revolution in which AI delivers better user experiences.” Dr. Lu recently joined the company after having previously served in high-level audio engineering roles for industry leaders including Conexant, Goodix, Plantronics, Verizon, and Microsoft.
The AONDenoise solution is now available for integration into third-party processors. For customers seeking dedicated hardware solutions, AONDevices is preparing to launch the denoiser hardware IP and the associated next-generation chip – the AON2100™ – in the coming months. For more information, contact info@aondevices.com.
About AONDevices
AONDevices is a fabless semiconductor company specializing in application-specific edge AI processors with high accuracy at ultra-low power. The company is headquartered in Irvine, California. For more information, visit www.aondevices.com or connect with the company on LinkedIn.
Media Contact:
Stephanie Olsen
Lages & Associates
(949) 453-8080
stephanie@lages.com
A photo accompanying this announcement is available at https://www.globenewswire.com/NewsRoom/AttachmentNg/2cd880e2-fe00-490e-8700-8dbfeff84907
