Deploying AI Models at the Edge

Synaptics’ new chip puts edge AI in office headsets for better voice recognition

Categories Edge Computing News  |  Hardware
Synaptics’ new chip puts edge AI in office headsets for better voice recognition

Synaptics has launched its newest AudioSmart AS33970 headset platform SoC. According to the announcement, it is the world’s first highly integrated AI-enabled ENC (Environmental Noise Cancellation) and hybrid ANC (Active Noise Cancellation) single-chip solution integrating neural and voice processing engines for optimal audio performance. In addition, its best-in-class power consumption enables a 35-55 percent improvement in battery life compared to currently shipping wireless headsets, as well as a significant reduction in size, design complexity, and cost, driven by its integrated architecture.

The AS33970 SoC reduces the chip count compared to other headset solutions from 5 to 3 while also lowering the number of microphones needed, significantly cutting system costs. Together with ultra-low power consumption, this reduction in chip count and passive components leads to a lighter and smaller design resulting in reduced user fatigue. In addition, the AS33970 AudioSmart SoC platform is the first and only open-market solution that meets the Microsoft Teams Open Office Premium specification without a boom mic enabling premium voice performance while optimizing comfort and usability in a sleeker form factor.

Further, the AS33970 headset SoC offers cutting-edge technology that leverages the flexibility of the Synaptics’ Neural Processing Unit (NPU) to utilize use-case-specific Deep Neural Network (DNN) models to provide both ENC and hybrid ANC in extremely noisy environments.

Our customers demand a high-end headset solution that can operate and support office, home, school, e-sports café, and transit environments,” says Craig Stein, SVP & GM, Mobile & IoT Division at Synaptics. “Our headset platform SoC provides a unified hardware platform with turnkey, customizable ANC, and ENC algorithms while lowering system cost, providing manufacturers a scalable platform to support a wide array of wired and wireless form factors.”

Article Topics

 |   |   | 

Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Featured Edge Computing Company

Edge Ecosystem Videos

Automating the Edge

“Automating

Deploying AI Models at the Edge

“Deploying

Latest News