Blog Post

Announcing Support for the Syntiant NDP101 Processor

Machine Learning, TinyMLDevelopers can now use Edge Impulse to collect data, build models, and then deploy to Syntiant's new TinyML board.

Aurelien Lequertier

September 29, 2021

Today we are excited to announce our official support for the Syntiant NDP101 processor! The NDP101 (Neural Decision Processor™) is an always-on sensor and speech recognition processor, with ultra-low power consumption of less than 140 uW while recognizing words. It features a Dense Neural Network Architecture of four layers with 256 inner nodes and runs real-time audio inferencing up to 100 times per second. The NDP101 is an ideal solution for wake word detection, speech classification or any audio-related application.

To make it easy to build and deploy audio classification models on ultra-low power silicon, we have partnered with Syntiant to bring support for the NDP101 processor to Edge Impulse - giving developers a quick and efficient way to collect data, build models, and then deploy to the Syntiant TinyML Development Board. Best of all, you can collect audio data directly through the Edge Impulse Studio! The Syntiant TinyML board supports the Arduino environment to make it easier for developers to get started. 

We are also releasing a new application tuning feature to help users tune the posterior parameters of their impulse such as the best windowing and threshold settings and display FAR and FRR metrics.

Read the How do I get started? sectionHow do I get started?

Get started building your industrial-grade embedded machine learning applications for the Syntiant TinyML board today with our getting started guide

Deployment to the Syntiant TinyML board from the Edge Impulse Studio.
  1. Purchase the TinyML board on Syntiant’s website.
  2. Connect the board to Edge Impulse.
  3. Follow the Responding to your voice - Syntiant guide.
  4. Go to the Deployment tab of your Edge Impulse project, then build and download a ready-to-go binary that includes your machine learning model for the Spresense; or deploy as a NDP101 library and integrate the model into your own firmware!

Congratulations! You have now successfully built and deployed a low-power, audio classification application for the Syntiant TinyML board.

We are very excited to see what you build with the Syntiant TinyML and Edge Impulse, please post any questions you have and any projects you create over on our forum or tag @EdgeImpulse and @SyntiantCorp on social media! 

Subscribe

Are you interested in bringing machine learning intelligence to your devices? We're happy to help.

Subscribe to our newsletter