CEVA Debuts Mutisensory Hub for Smart Devices
Smart sensor technology developer CEVA has launched a new high-performance sensor hub named SensPro. The new system collects and processes a range of sensor data all at once, including audio, visual, radar, and other information.
SensPro is designed to be the central point where different kinds of information from the environment can be put together into a coherent story. The technology analyzes input based on context and can learn over time what input it gathers is relevant and relate one data stream to others. That means it could, for instance, hear the sound of a plane flying overhead with a microphone, see it with a camera, and take its range by radar, then extrapolate where it came from and where it may be going. CEVA is pitching the new tech as ideal for all kinds of consumer and industrial applications, including in cars, voice assistants, and healthcare.
“With the growth in the number and variety of sensors in modern systems, and their substantially different computation needs, we set out to design a new architecture from the ground up to address this challenge,” said CEVA vice president of research and development Ran Snir. “We constructed SensPro as a highly configurable, holistic architecture that could handle these intensive workloads using a combination of scalar, vector processing and AI acceleration, while utilizing the latest micro-architecture design techniques of deep pipelining, parallelism, and multi-tasking. The result is the most powerful DSP architecture ever conceived for sensor hubs and we’re truly excited to work with our customers and partners to bring contextually-aware products to market based on it.”
Listening and Learning
SensPro incorporates many of CEVA’s technologies for different senses. On the audio side, the company’s CEVA-BX digital audio signal processing software, ClearVox noise reduction, and WhisPro speech recognition products are featured. All have become a mainstay of CEVA’s efforts to build its presence in the voice tech industry. CEVA partnered with Novatek Microelectronics to bring its audio tech to the smart TV hardware built by Novatek. The advantage for Novatek is that the televisions will be able to respond to multiple wake words, supporting more than one voice assistant. It will also enable television manufacturers to create their own wake words or let customers choose one they like.
Most recently, CEVA and audio software developer Bragi revealed that they are working on their own hearables platform, combining the CEVA-BX software with Bragi’s operating system. The idea is to make a customizable range of wireless earbuds that can last a long time and add apps from Bragi’s digital store.