Synaptics uses edge AI to bring better voice recognition to headsets

Synaptics Headset

Fin is a former junior editor at TechForge.

Synaptics, a human interface hardware and software developer, has unveiled a new edge AI headset platform that improves voice recognition.

The AudioSmart AS33970 SoC brings a number of major upgrades to the world of wireless headsets and audio recognition.

It is said to be 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.

What’s more, its reduced power consumption enables a 35% to 55% improvement in battery life over wireless headsets on the market currently. Thanks to its integrated architecture, this can be achieved alongside a reduction in size, design complexity, and cost.

The new AS33970 has also reduced its chip count from five to three and requires fewer microphones, leading to a lighter design that reduces user fatigue, according to Synaptics.

The lack of a boom microphone means Synaptics’ product is the first on the market to qualify for Microsoft Teams’ Open Office Premium specification without needing one.

Peter Cooney, founder of SAR Insight & Consulting, noted: “The dynamic market for high-end headsets demands a highly flexible and scalable solution to enable a wide variety of features and industrial designs.

“The AudioSmart AS33970 SoC headset platform, with its highly-customisable architecture, allows customers to deliver differentiated headsets in both form and function.”

Find out more about Digital Transformation Week North America, taking place on November 9-10 2021, a virtual event and conference exploring advanced DTX strategies for a ‘digital everything’ world.

Tags: , , , ,

View Comments
Leave a comment

Leave a Reply