Distortion Product Otoacoustic Emissions (DPOAE) Skill

Zero-dependency sovereign personal agent skill for non-invasive evaluation of Distortion Product Otoacoustic Emissions (DPOAE), cochlear outer hair cell biomechanics, and headphone noise damage.

flowchart TD
    DualTones["Primary Pure Tones (F1: 65 dB, F2: 55 dB)"] --> EarCanalProbe["Low-Noise Sensitive Miniature Microphone"]
    EarCanalProbe --> SpectralAnalysis["FFT Extraction of 2F1 - F2 Distortion Peak"]
    SpectralAnalysis --> SNR_Engine["Signal-to-Noise Ratio & Clinical Pass Logic"]
    SNR_Engine --> CochlearScore["Cochlear Outer Hair Cell Resilience Engine"]
    CochlearScore --> Agent["OpenClaw / Hermes Personal Agent Actions"]

Features

• Deterministic Math: Pure Python standard library implementation with zero external dependencies.
• Clinical Audiological Standards: Implements clinical pass criteria ($SNR \ge 6 \text{ dB}$, $Amp \ge -5 \text{ dB SPL}$).
• Early Noise Overexposure Detection: Identifies outer hair cell fatigue before pure-tone hearing threshold loss occurs.
• Model Context Protocol (MCP): Native JSON-RPC tool integration for LLMs and autonomous agents.

Quickstart

from client import AcousticOtoacousticEmissionsClient

client = AcousticOtoacousticEmissionsClient()
result = client.evaluate_dpoae(
    f2_frequency_hz=2000.0,
    dpoae_amplitude_db_spl=8.5,
    noise_floor_db_spl=-12.5
)
print("DPOAE SNR:", result["signal_to_noise_ratio_snr_db"], "dB")
print("Classification:", result["classification"])

License

Apache-2.0