Wake Word Detection with Edge AI
Always-on keyword spotting that listens for a specific activation phrase. Ultra-low-power operation is critical since the model runs continuously waiting for the trigger word. Uses DS-CNN or depthwise separable convolutions on mel-spectrograms of 1-second audio windows. The model classifies short audio segments as either the target keyword or background noise. Common in smart speakers, voice-activated appliances, and hands-free industrial interfaces.
Hardware Requirements
| Minimum RAM | 64 KB |
| Minimum Flash | 512 KB |
| Sensor Inputs | microphone |
| Typical Model Size | 40 KB (quantized int8) |
| Minimum Clock | 48 MHz |
Hardware Guides
No hardware guides for wake word detection yet. Use the MCU Checker to find compatible hardware.
Industry Applications
Orchestrate Wake Word Detection with ForestHub
Your devices run wake word detection on-device. ForestHub on your Linux edge gateway ingests their results over MQTT/Modbus/OPC-UA, orchestrates the sense-reason-act loop as an auditable graph, and acts on the line — the LLM is one node among many.