CEVA Introduces ClearVox, Partners with Silentium

CEVA, a licensor of signal processing platforms and artificial intelligence processors for connected devices, today introduced ClearVox, a suite of advanced voice input processing algorithms aimed at enhancing speech intelligibility and voice clarity for voice-enabled devices. ClearVox is licensed exclusively for the CEVA-TeakLite-4 and CEVA-X2 audio/voice DSPs.

ClearVox incorporates advanced algorithms that cope with different acoustic scenarios and microphone configurations, including optimized software for speaker direction of arrival, multimicrophone beamforming, noise suppression, and acoustic echo cancellation, as well as the related firmware and driver software. It is offered in two pre-packaged software form factors; one for near-field applications, including headsets and wearables, and the other for far-field applications targeting the emerging smart speaker, infotainment, and other advanced voice-enabled applications. The accompanying SDKit is available to help customers configure and adopt ClearVox to their unique product specifications, such as the number and geometry of microphones, echo tail length, and more.

"Voice input technologies are some of the most complicated and diverse algorithms to design, yet have become a must-have for every voice-enabled device. Our ClearVox technology takes advantage of the latest academic research in algorithms for beamforming and signal direction of arrival to achieve a truly robust and exceptionally clear voice signal, regardless of background noise, acoustics, environment. or product design," said Erez Bar-Niv, chief technology officer at CEVA, in a statement. "Our customers can now benefit from a single-source offering for the complete voice input solution, both the DSP and the software reducing design complexity and their time to market."

ClearVox is available today for select customers and for general licensing in the second quarter of this year.

And, in another move aimed at improving the voice quality of its Teak-Lite products, CEVA today also partnered with Silentium to deliver an active noise cancellation solution.

Together, the companies will deliver a low-power active noise cancellation solution for headsets and hearables. The solution is based on a CEVA-TeakLite-4 implementation of Silentium's Broadband P2P ANC technology, which enhances the personal audio experience. The P2P solution supports broadband fully adaptive ANC technology up to 1 KHz, and licensees can choose from feedforward, feedback, or hybrid systems .

"The CEVA-TeakLite family of DSPs are broadly adopted in wireless headsets and hearables, thanks to its ideal blend of power, performance and footprint for small form factor use cases", said Amit Grauer, senior director of business development at Silentium, in a statement. "Our active noise cancellation technology delivers a premium experience, and, together with CEVA, we offer a highly compelling ANC solution to its audio/voice DSP licensees."

"Silentium's Broadband P2P ANC technology offers a tremendous value-add with its demonstrable improvement in sound quality when implemented on our audio/voice DSPs," said Moshe Sheier, director of strategic marketing at CEVA, in a statement. "The flexibility to tailor the solution for a specific use case is something our customers truly value and we're delighted to extend our sound ecosystem with this exciting technology."

SpeechTek Covers
for qualified subscribers
Subscribe Now Current Issue Past Issues