Wake Word Detection

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

# requirements.txt
openwakeword>=0.6.0
numpy>=1.24.0
sounddevice>=0.4.6
onnxruntime>=1.16.0

5. Implementation Workflow (TDD)

Step 1: Write Failing Test First

# tests/test_wake_word.py
import pytest
import numpy as np
from unittest.mock import Mock, patch

class TestWakeWordDetector:
    """TDD tests for wake word detection."""

    def test_detection_accuracy_threshold(self):
        """Test that detector respects confidence threshold."""
        from wake_word import SecureWakeWordDetector

        detector = SecureWakeWordDetector(threshold=0.7)
        callback = Mock()
        test_audio = np.random.randn(16000).astype(np.float32)

        with patch.object(detector.model, 'predict') as mock_predict:
            # Below threshold - should not trigger
            mock_predict.return_value = {"hey_jarvis": np.array([0.5])}
            detector._test_process(test_audio, callback)
            callback.assert_not_called()

            # Above threshold - should trigger
            mock_predict.return_value = {"hey_jarvis": np.array([0.8])}
            detector._test_process(test_audio, callback)
            callback.assert_called_once()

    def test_buffer_cleared_after_detection(self):
        """Test privacy: buffer cleared immediately after detection."""
        from wake_word import SecureWakeWordDetector

        detector = SecureWakeWordDetector()
        detector.audio_buffer.extend(np.zeros(16000))

        with patch.object(detector.model, 'predict') as mock_predict:
            mock_predict.return_value = {"hey_jarvis": np.array([0.9])}
            detector._process_audio()

        assert len(detector.audio_buffer) == 0, "Buffer must be cleared"

    def test_cpu_usage_under_threshold(self):
        """Test CPU usage stays under 5%."""
        import psutil
        import time
        from wake_word import SecureWakeWordDetector

        detector = SecureWakeWordDetector()
        process = psutil.Process()
        start_time = time.time()

        while time.time() - start_time < 10:
            audio = np.random.randn(1600).astype(np.float32)
            detector.audio_buffer.extend(audio)
            if len(detector.audio_buffer) >= 16000:
                detector._process_audio()

        avg_cpu = process.cpu_percent() / psutil.cpu_count()
        assert avg_cpu < 5, f"CPU usage too high: {avg_cpu}%"

    def test_memory_footprint(self):
        """Test memory usage stays under 100MB."""
        import tracemalloc
        from wake_word import SecureWakeWordDetector

        tracemalloc.start()
        detector = SecureWakeWordDetector()

        for _ in range(600):
            audio = np.random.randn(1600).astype(np.float32)
            detector.audio_buffer.extend(audio)

        current, peak = tracemalloc.get_traced_memory()
        tracemalloc.stop()

        peak_mb = peak / 1024 / 1024
        assert peak_mb < 100, f"Memory too high: {peak_mb}MB"

Step 2: Implement Minimum to Pass

class SecureWakeWordDetector:
    def __init__(self, threshold=0.5):
        self.threshold = threshold
        self.model = Model(wakeword_models=["hey_jarvis"])
        self.audio_buffer = deque(maxlen=24000)

    def _test_process(self, audio, callback):
        predictions = self.model.predict(audio)
        for model_name, scores in predictions.items():
            if np.max(scores) > self.threshold:
                self.audio_buffer.clear()
                callback(model_name, np.max(scores))
                break

Step 3: Run Full Verification

pytest tests/test_wake_word.py -v
pytest --cov=wake_word --cov-report=term-missing

6. Implementation Patterns

Pattern 1: Secure Wake Word Detector

from openwakeword.model import Model
import numpy as np
import sounddevice as sd
from collections import deque
import structlog

logger = structlog.get_logger()

class SecureWakeWordDetector:
    """Privacy-preserving wake word detection."""

    def __init__(self, model_path: str = None, threshold: float = 0.5, sample_rate: int = 16000):
        if model_path:
            self.model = Model(wakeword_models=[model_path])
        else:
            self.model = Model(wakeword_models=["hey_jarvis"])

        self.threshold = threshold
        self.sample_rate = sample_rate
        self.buffer_size = int(sample_rate * 1.5)
        self.audio_buffer = deque(maxlen=self.buffer_size)
        self.is_listening = False
        self.on_wake = None

    def start(self, callback):
        """Start listening for wake word."""
        self.on_wake = callback
        self.is_listening = True

        def audio_callback(indata, frames, time, status):
            if not self.is_listening:
                return
            audio = indata[:, 0] if len(indata.shape) > 1 else indata
            self.audio_buffer.extend(audio)
            if len(self.audio_buffer) >= self.sample_rate:
                self._process_audio()

        self.stream = sd.InputStream(
            samplerate=self.sample_rate, channels=1, dtype=np.float32,
            callback=audio_callback, blocksize=int(self.sample_rate * 0.1)
        )
        self.stream.start()

    def _process_audio(self):
        """Process audio buffer for wake word."""
        audio = np.array(list(self.audio_buffer))
        predictions = self.model.predict(audio)

        for model_name, scores in predictions.items():
            if np.max(scores) > self.threshold:
                self.audio_buffer.clear()  # Privacy: clear immediately
                if self.on_wake:
                    self.on_wake(model_name, np.max(scores))
                break

    def stop(self):
        """Stop listening."""
        self.is_listening = False
        if hasattr(self, 'stream'):
            self.stream.stop()
            self.stream.close()
        self.audio_buffer.clear()

Pattern 2: False Positive Reduction

class RobustDetector:
    """Reduce false positives with confirmation."""

    def __init__(self, detector: SecureWakeWordDetector):
        self.detector = detector
        self.detection_history = []
        self.confirmation_window = 2.0
        self.min_confirmations = 2

    def on_potential_wake(self, model: str, confidence: float):
        now = time.time()
        self.detection_history.append({"time": now, "confidence": confidence})
        self.detection_history = [d for d in self.detection_history if now - d["time"] < self.confirmation_window]

        if len(self.detection_history) >= self.min_confirmations:
            avg_confidence = np.mean([d["confidence"] for d in self.detection_history])
            if avg_confidence > 0.6: