Neural Decision Processors™

NDP101 - Always-On Sensor & Speech Recognition

The Syntiant® NDP architecture is built from the ground up to run deep learning algorithms. Embedded with the Syntiant Core 1™, the NDP101 is a low-power, low-latency device that achieves 100x the efficiency levels of traditional CPUs and DSPs, all without requiring a connection to the cloud.

The NDP101 runs audio and sensor applications such as keyword spotting, wake word detection, speaker identification, sensor analytics and audio event and environment classification, while consuming less than 140μW of power.

Ultra-Low-Power

Microwatt level active power consumption, while always-on and listening

Neural Processing

Neural network with half a million+ parameters providing large-scale parallelism for sensor applications

Keyword Speech

A keyword speech interface created from the simultaneous classification of dozens of keywords

System-on-chip

Programmable general purpose IO & SPI Master; booting from a serial flash with the ability to exist as the system's sole processor

Ease of Use

Multiple flexible methods to access neural processing engine with full customization of applications and post-processing

Key Features

System on chip in a 32 pin QFN package
Suitable for applications that require an MCU for control and a neural engine for decision making
Dual PDM microphone input or PCM-over-SPI input
Stereo/mono I2S interface multiplexed with PDM
Direct access to neural network over SPI for sensor applications
Frequency, time-domain & batch input models
16-bit input holding tank with faster than real-time SPI extraction
Embedded Arm Cortex-M0 processor with 112KB SRAM
Eight GPIO pins with programmable direction and drive strength
Support for external serial flash boot

Integrated clock multiplier and dividers support low-frequency clock source or external clocking
Optimized interrupt and SPI slave interface
Master SPI interface for sensor interfaces
Onboard firmware security and authentication
English speech service for keyword training
Software Development Kit (SDK) integrates in any software environment
Training Development Kit (TDK) to enable the use of standard frameworks such as TensorFlow for customer-programmed applications
Support for 64 output classifications
Active power consumption of <140µW while recognizing words