Speech Technology Magazine

 

CEVA, Rubidium Partner to Develop Speech Processing Solutions

Solutions address growing demand for voice-powered user interfaces.
Posted Oct 23, 2012
Page1 of 1
Bookmark and Share

CEVA, a licensor of silicon intellectual property platform solutions and DSP cores, and Rubidium, a global supplier of embedded speech processing technologies, have teamed up to deliver enhanced speech processing solutions for smart devices. The solutions integrate Rubidium's suite of speech recognition, text-to-speech, and biometric speaker identification and verification software with the CEVA-TeakLite family of DSPs, including the CEVA-TeakLite-4.

"Voice is the user interface of choice for many future products and applications," said Moshe Sheier, director of product marketing at CEVA, in a statement. "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."

Rubidium software includes ASR, which controls any set of functions through voice commands, These functions include call acceptance and rejection, device setup and installation procedure (pairing, calibration, interconnection, etc.), voice dialing, music streaming control, and multilevel selection menus. There is also a voice trigger function, which is a continuous ASR engine that wakes up upon the user's uttering a voice password.

Another feature is a biometric speaker identification engine that offers a small footprint and a low-cost design for affordable and effective biometric identification and verification on any consumer product or mass market device. Also offered is a TTS in a variety of languages that announces text with a natural and human-sounding voice.

The CEVA-TeakLite DSP family has shipped more than 3 billion chips and has over 100 licensees, 30 active ecosystem partners and more than 100 audio and voice codecs and enhancement applications available.

"Our speech processing technology adds to [CEVA's] robust audio/voice ecosystem and results in an extremely attractive solution for any company developing voice-enabled products," said Shlomo Peller, CEO and founder of Rubidium, in a statement. "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."


Page1 of 1