Rubidium to supply speech recognition for CEVA microchips

October 24, 2012 - 

CEVA, Inc., a leading licensor of silicon intellectual property platform solutions and digital signal processing (DSP) cores, and Rubidium Ltd., a global supplier of embedded speech processing technologies, announced that they have partnered to deliver enhanced speech processing solutions for smart devices, integrating Rubidium’s suite of speech recognition, text-to-speech and biometric speaker identification and verification software with CEVA DSP cores.

DSPs are specialized high-speed microprocessors that are optimized for performance in applications requiring repetitive arithmetic calculations to be performed on arrays of data. DSPs provide the silicon foundation supporting the vast majority of today’s electronic products. Without DSPs there would be no smartphones, tablet computers, or high-definition televisions.

CEVA’s family of TeakLite DSP cores are designed for audio, voice, and baseband applications. Rubidium’s speech recognition software will be integrated into TeakLite DSP cores.

“Voice is the user interface-of-choice for many future products and applications,” said Moshe Sheier, director of product marketing at CEVA. “Rubidium is a recognized leader in embedded speech processing technologies and its highly-accurate and production-proven software offers a compelling hands-free user experience. Having already shipped in high volume with other members of the CEVA-TeakLite DSP family, Rubidium’s software has been further optimized to leverage the power and flexibility of our latest CEVA-TeakLite-4 DSP, delivering outstanding performance for any advanced, voice-enabled application.”

“The CEVA-TeakLite DSP family has long been the voice and audio leader in the industry, powering a wide range of pre- and post-processing applications in billions of handsets and consumer devices,” said Shlomo Peller, CEO and Founder of Rubidium. “Our speech processing technology adds to their robust audio/voice ecosystem and results in an extremely attractive solution for any company developing voice-enabled products. Features such as voice-trigger, barge-in support and our wide variety of languages increases the user’s productivity by enabling voice control and totally hands-free manipulation of a device. These and other unique features provide CEVA’s cores with a competitive advantage over alternative architectures.”

Leave a Comment


About Stephen Mayhew

Stephen Mayhew is the publisher and co-founder of Biometrics Research Group, Inc.. His experience includes a mix of entrepreneurship, brand development and publishing. Stephen attended Carleton University and lives in Toronto, Canada. Connect with Stephen on LinkindIn.