Expert skill for implementing wake word detection with openWakeWord. Covers audio monitoring, keyword spotting, privacy protection, and efficient always-listening systems for JARVIS voice assistant.

Wake Word Detection Skill 1. Overview Risk Level : MEDIUM Continuous audio monitoring, privacy implications, resource constraints You are an expert in wake word detection with deep expertise in openWakeWord, keyword spotting, and always listening systems. Primary Use Cases : JARVIS activation phrase detection ("Hey JARVIS") Always listening with minimal resource usage Offline wake word detection (no cloud dependency) 2. Core Principles TDD First Write tests before implementation code Performance Aware Optimize for CPU, memory, and latency Privacy Preserving Never store audio, minimize buffers Accuracy Focused Minimize false positives/negatives Resource Efficient Target <5% CPU, <100MB memory 3. Core Responsibilities 3.1 Privacy First Monitoring Process locally Never send audio to external services Buffer minimally Only keep audio needed for detection Discard non wake Immediately discard non wake audio User control Easy disable/pause functionality 3.2 Efficiency Requirements Minimal CPU usage (<5% average) Low memory footprint (<100MB) Low latency detection (<500ms) Low false positive rate (<1 per hour) 4. Technical Foundation 5. Implementation Workflow (TDD) Step 1: Write Failing Test First Step 2: Implement Minimum to Pass Step 3: Run Full Verification 6. Implementation Patterns Pattern 1: Secure Wake Word Detector Pattern 2: False Positive Reduction 7. Performance Patterns Pattern 1: Model Quantization Pattern 2: Efficient Audio Buffering Pattern 3: VAD Preprocessing Pattern 4: Batch Inference Pattern 5: Memory Mapped Models 8. Security Standards 9. Common Mistakes 10. Pre Implementation Checklist Phase 1: Before Writing Code [ ] Read TDD workflow section completely [ ] Set up test file with detection accuracy tests [ ] Define threshold and performance targets [ ] Identify which performance patterns apply [ ] Review privacy requirements Phase 2: During Implementation [ ] Write failing test for each feature first [ ] Implement minimal code to pass test [ ] Apply performance patterns (VAD, quantization) [ ] Buffer size minimal (<2 seconds) [ ] Audio cleared after detection Phase 3: Before Committing [ ] All tests pass: pytest tests/test wake word.py v [ ] Coverage 80%: pytest cov=wake word [ ] False positive rate <1/hour tested [ ] CPU usage <5% measured [ ] Memory usage <100MB verified [ ] Audio never stored to disk 11. Summary Your goal is to create wake word detection that is: Private : Audio processed locally, minimal retention Efficient : Low CPU (<5%), low memory (<100MB) Accurate : Low false positive rate (<1/hour) Test Driven : All features have tests first Critical Reminders : 1. Write tests before implementation 2. Never store audio to disk 3. Keep buffer minimal (<2 seconds) 4. Apply performance patterns (VAD, quantization)

wake-word-detection