CSpotter speech recognition software optimised for industry’s most widely deployed audio/voice DSP family targeting always-on mobile and IoT devices
CEVA, Inc., the leading licensor of signal processing IP for smarter, connected devices, and Cyberon Corporation, a leading embedded speech solution provider, announced today that the companies have partnered to offer an ultra-low power, always-listening voice activation solution for smartphones, consumer and IoT devices. Cyberon have developed an optimised implementation of its CSpotter voice recognition engine for the CEVA-TeakLite family of DSPs. Cyberon will demonstrate CSpotter on CEVA-TeakLite-4 silicon at the upcoming CEVA Technology Symposium in Taiwan on October 27th, 2017.
Voice activation and control is rapidly gaining popularity across the electronics industry, where hands-free and eyes-free interaction with smartphones, smart speakers, toys and more is becoming a must-have feature. Cyberon’s CSpotter listens to ambient speech to detect and respond to a set of predefined words and/or trigger commands. CSpotter supports 33 languages, based on phoneme acoustic models. CSpotter technology is specifically designed to address low power, always-on use cases and is a valuable addition to the CEVAnet partner ecosystem. The technology offers both optimised speaker independent and dependent voice activation for the CEVA-TeakLite DSPs and is already implemented and available on CEVA-powered merchant silicon.
“The CEVA-TeakLite family of DSPs already powers billions of smartphones, consumer electronics and other smart IoT devices, making CEVA an ideal partner for our CSpotter technology,” said Tai-Hsuan Ho, founder and CEO of Cyberon. “CSpotter on CEVA’s DSPs is a highly compelling offering, with unmatched accuracy and performance in the noisiest environments and at minimal power consumption.”
“Cyberon’s low footprint voice trigger/word spotter and vast multi-language support is very impressive,” said Moshe Sheier, director of strategic marketing at CEVA. “Coupled with the world’s lowest power audio/voice DSP family, the joint implementation offers a perfect combination of performance and power efficiency for adding an always-listening voice interface to a wide range of smart devices, including smartphones, toys, wearables, automotive and IoT.”