Auryx transforms existing active-noise cancelling earbuds into accurate health monitoring devices using advanced AI algorithms. The platform leverages built-in microphones and sophisticated audio-based foundation models to track vital signs during daily activities. This provides professional-grade health insights without requiring users to adopt new, dedicated hardware.
Funding
Funding not disclosed
Founders
Product
Problem
Existing methods for continuous health monitoring often require dedicated wearable devices, which can be cumbersome and lead to user non-adherence. This limits the ability to gather longitudinal physiological data during everyday activities, hindering early detection and proactive management of health conditions.
Solution
Auryx transforms commercially available active-noise cancelling earbuds into sophisticated health monitoring devices by leveraging their integrated microphones and advanced AI algorithms. Our platform analyzes subtle acoustic signals to derive key vital signs, providing continuous, professional-grade health insights without the need for additional hardware. This approach enables seamless health tracking during any daily activity, from exercise to sleep, and offers a non-intrusive method for long-term physiological data acquisition. The system is built upon a foundation of biomedical signal processing and machine learning research, validated through rigorous testing.
Target Audience
Auryx targets individuals seeking convenient, continuous health monitoring and healthcare providers or researchers interested in collecting real-world physiological data without specialized hardware.
Features
- Utilizes existing active-noise cancelling earbud microphones for physiological data acquisition.
- Employs advanced AI and audio-based foundation models for accurate vital sign extraction.
- Enables continuous health monitoring during diverse daily activities.
- Provides professional-grade health insights without requiring supplementary hardware.
- Leverages proprietary algorithms for biomedical signal processing and machine learning.
- Offers a non-intrusive approach to longitudinal physiological data collection.