HomeAI & Machine LearningWake-Word Detector 2D: Score Ribbon & Power Dial Simulator

Wake-Word Detector 2D: Score Ribbon & Power Dial Simulator

Interactive 2D simulator of an always-on mobile wake-word detector: scrub a live matched-filter score ribbon crossing a detection threshold, tune noise, keyword rate and microphone duty cycle, and watch false-accept rate, false-reject rate and average power update on a real-time dial.

AI & Machine Learning2DModerate60 FPS📱 Mobile-adapted⇄ 3D version
2d-mobile-voice-speech-recognition ↗ Open standalone

Every "Hey Siri" or "OK Google" moment starts with a tiny, always-on detector running a matched-filter correlation against a stored keyword template on a handful of milliwatts, long before any cloud or on-device speech recognizer wakes up. This 2D simulator streams a live strip-chart of analysis frames, scores each one with normalized cross-correlation, and lets you tune the detection threshold, background noise floor, how often the keyword is actually spoken, and the microphone's power-saving duty cycle. Drag the ribbon to scrub back through history, watch the chip-state indicator and power dial react in real time, and see true accepts, phantom false-accept wake-ups and missed false rejects accumulate — a faithful two-state power model of a real mobile voice-assistant chip.

⚙ Under the hood

Interactive 2D simulator of an always-on mobile wake-word detector: scrub a live matched-filter score ribbon crossing a detection threshold, tune noise, keyword rate and microphone duty cycle, and watch false-accept rate, false-reject rate and average power update on a real-time dial.

speech recognitionsignal processingmobile AIvoice assistantdetection theorypower efficiency

2D · HTML5 Canvas 2D · 60 FPS target · runs fully client-side, no install

What did you find?

Add reproduction steps (optional)