Ambiq Wearable

Ambiq Wearable

AVS-qualified TalkTo brings power optimized, highly accurate wake word detection to the industry's lowest power MCUs in the Ambiq wearable reference design. Significantly reduce false positives while still meeting the battery life requirements on small, wearable devices.

 

Benefits

Near-field always-on, always-listening solution

• DSP Concepts high performance TalkTo Audio Front-end

• Meets AVS 2.1 specification

Extended battery life for wearable

• Proprietary Quiescent Sound Detector together with environment-adaptive microphone processing

• Industry’s lowest power operation enabled with Ambiq SPOT™ (Subthreshold Power Optimized Technology)

Audio Front-end Features

DSP Concepts’ TalkTo for excellent far-field performance in noisy environments

  • • 2-mic adaptive beamformer with Single Channel Noise Reduction (SCNR)
  • • State-of-the-art noise cancellation with Adaptive Interference Canceller (AIC)
    • ○ No reference signal needed
    • ○ Eliminates 30dB of external noise sources such as background music or a booming movie
  • • 35 dB Acoustic Echo Cancellation (AEC) for excellent barge-in performance
  • • Quiescent Sound Detector (QSD) for wakeup on voice

 

 

High Performance TrulyHandsfree™ Alexa wake word from Sensory

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 Cortex-M4
Software Integrations - TalkTo Voice UI
TalkTo Voice UI
Noise reduction, echo cancellation and advanced beam-forming signal processing for far-field voice activation
Software Integrations - TrulyHandsfree Alexa wake word
TrulyHandsfree Alexa wake word

Hardware Specifications

Kit Hardware
  • Ambiq Apollo3 Blue Plus EVB
  • mikroBUS Audio Shield
  • Two DMIC Click boards
Processor
  • Ambiq ultra-low power Apollo3 Blue Plus MCU
  • 32-bit ARM Cortex-M4F MCU
  • 48/96 MHz TurboSPOT clock frequency
Memory
  • 2 MB flash and 768 KB SRAM
Audio I/O
  • PDM dual interface for mono and stereo audio microphones
  • Click board with Vesper VM3011 ZeroPower Listening microphone with 2 VM3000 Mics or Click board with 3 Memsensing Mics
Connectivity
  • Integrated BLE 5 wireless connectivity

Included with the demo kit

  • Ambiq Voice-on-SPOT™ SDK
  • Voice UI Quickstart Bundle: Everything you need to know to design voice-enabled wearables, including design guidelines, microphone placement, Audio Weaver Designer layout files (.AWD), and tools to get started.
Ambiq Wearable Diagram

Ready to get started?