From Earbuds to Industrial IoT
Syntiant is making edge AI a reality.
Syntiant’s end-to-end deep learning solutions bring a highly accurate, ultra-low-power AI interface to always-on image, voice, audio and sensor applications across a wide range of consumer and industrial use cases.
Using at-memory compute and built-in standard CMOS processes, Syntiant devices directly process neural network layers from platforms such as TensorFlow or PyTorch without the need for any secondary compilers.
Designed by applying a clean-sheet, hardware/software co-design methodology that optimizes silicon and deep learning models together, Syntiant’s Core neural network architecture enables devices to be approximately 100x more efficient by providing 10x the throughput over current low-power MCU solutions, and subsequently, enabling larger networks at significantly lower power.
By combining the industry’s most efficient silicon with a data platform and training pipeline, Syntiant provides customers with low-cost, turn-key solutions that quickly deliver production grade deep learning models in a variety of domains to enable a robust interface between the physical world and digital world, free from cloud connectivity, ensuring privacy and security.
Speech and beyond ...
Syntiant devices are used in applications from event detection such as glass breaking or fall detection, wake words such as Alexa or OK/Hey Google, command words such as “volume up” or “call 911”, or speaker ID.
Soon the company will bring conversation speech at negligible power consumption to make speech a first-class interface to almost any device.
Beyond speech, our devices are being used for person detection, health monitoring and other condition-based monitoring or anomaly detection.
The integration of artificial intelligence with Industrial IoT has had a profound impact on many diverse industries ranging from aviation to manufacturing to transportation.
Adding sensors to critical equipment will elevate any workspace or facility. Syntiant technology can continuously monitor sounds, vibrations and temperature to detect and act on any issues before a costly downtime failure occurs.
From condition-based monitoring to predictive quality control, Syntiant’s deep learning sensor technology provides customers with a higher degree of automation that improves performance, productivity and efficiency across a wide range of industrial and manufacturing applications.
IIoT // Condition Based Monitoring
Consumers today want hands-free functionality.
Speech recognition and the elimination of typing improves productivity, allowing people to multitask myriad functions during their everyday lives, from making calls to managing a business to ordering a pizza.
Syntiant technology also can enable devices to run multiple neural networks in parallel, allowing developers to mix and match applications at under 1mW power consumption.
No matter where a person is located, what device he or she is using, or even what language they speak, Syntiant’s Neural Decision Processors™ bring low-latency, intelligent voice processing to almost any device, free from cloud connectivity, ensuring privacy and security.
Mobile // Handsets // Tablets
Today’s connected consumer wants one thing above all else – ease of use! Hand-free functionality lets people access and control useful information they need without pushing buttons or touching screens.
With package sizes down to 1.4mm X 1.8mm, Syntiant’s NDPs can meet the requirements of the tiniest and most demanding low-power audio, speech and sensor applications.
From smartwatches to fitness trackers and healthcare wristbands, Syntiant’s end-to-end solutions bring a level of machine learning previously only available in the cloud to wearables that previously required 10x the power and twice the die size.
Everyone wants a “smarter” and more secure home. No more fumbling with keys, remotes and touch screens improve convenience, while adding video surveillance and motion sensing can increase protection.
Syntiant’s advanced edge technology allow critical and time-sensitive decisions to be made faster, more reliably and with greater security. Multiple voice, sound and sensor applications also can be run simultaneously at significantly low power.
From convenience to security, Syntinat’s Core architecture can make any dwelling a smart home or office, enabling developers to bring a powerful AI interface to a wide range of smart home applications.