Fluent.ai Far-Field Voice UI

Fluent.ai Far-Field Voice UI

Capture and process voice in the noisiest environments with the cost-effective STM32H747I MCU. Powered by Alexa-qualified TalkTo, this reference design brings far-field Voice UI with intent recognition to home automation devices.

 

Benefits

Far-field (3 m) voice activation with high response accuracy rate

  • DSP Concepts' high-performance TalkTo Audio Front-end
  • Local commands with intent recognition

Automatic Intent Recognition with support for multiple languages and accents

Cost-effective BOM for small form-factor products

Runs on single low-cost STM32H747I microcontroller

No external memory required

Audio Front-end Features

DSP Concepts’ TalkTo provides reliable far-field performance in noisy environments

  • • 2-mic array
  • • Single-Channel Noise Reduction (SDNR)
  • • State-of-the-art noise cancellation with Adaptive Interference Canceller (AIC) 
    • ○ No reference signal needed
    • ○ Eliminates 30dB of directional interfering noise

 

Fluent.ai “Alexa” Wake Word model

Fluent.ai Automatic Intent Recognition (Air) model

  • • Speech-to-intent recognition model
  • • Support for approximately 50 commands
  • • Support for multiple languages and accents 
    • ○ English (North American accent)
    • ○ English (Mainland Chinese accent)
    • ○ Mandarin (Mainland Chinese accent)

 

 

Software Integrations

Software Integrations - Audio Weaver Designer
Audio Weaver Designer
Drag-and-drop graphical tool to customize and tune audio processing models in real-time with 500+ modules
Software Integrations - Audio Weaver Core
Audio Weaver Core
Embedded audio processing engine for the ARM Cortex-M7
Software Integrations - TalkTo
TalkTo Voice UI
Adaptive interference cancellation and advanced beam-forming signal processing for far-field command recognition

Hardware Specifications

Processor

  • STM32H747I XIH6 Dual-Core MCU with Arm® Cortex®-M7 @ 480 MHz and Arm® Cortex®-M4 @ 240 MHz

Memory

  • 2028kB Flash
  • 1024kB RAM

Audio I/O

  • SAI channel codec
  • 2-channel USB audio I/O
  • 4-channel microphone input

Board Connectors 

  • USB with Micro-AB

Included with the demo kit

  • Available from Fluent.ai
  • Includes STM32H747I Discovery Kit with STM32H747 MCU and pre-flashed demo firmware
  • DSP Concepts 4-mic array daughter board with 2 mics enabled
  • Voice UI Quickstart Bundle available upon request: Everything you need to know to design voice-enabled IoT products, including design guidelines, microphone placement, an Audio Weaver Designer layout (.AWD), and tools to get started.
  • USB cable
  • AC-powered stereo speakers with volume control and integrated audio cable
STM32H747I MCU Diagram

Ready to get started?