Cough Vocalization Analysis for Authentication and Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current security technology lacks solutions for early detection of respiratory threats and alternative biometric authentication techniques using sound-based analysis.
Innovation Solution
A system and method that utilizes sound-based vocalization analysis to establish a baseline sound signal data signature, comparing it with real-time recordings for early detection of respiratory anomalies, using AI and machine learning to identify deviations from the baseline.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional security technology is used, then security measures are in place, but early detection of respiratory threats is not possible
Solution Approach 1:
The patent replaces traditional mechanical/security-based detection systems with an acoustic field-based detection system. The system uses sound wave analysis of vocalizations (coughs, sneezes, speech) to detect respiratory anomalies, substituting physical contact or visual inspection with acoustic sensing and machine learning analysis.
Solution Approach 2:
The system changes the detection parameter from visual or physical contact to acoustic frequency analysis. By analyzing specific acoustic parameters (frequency, amplitude, temporal patterns) of vocalizations, the system can detect respiratory threats without requiring traditional security measures.
2Adaptability or versatility
If sound-based vocalization analysis is implemented, then alternative biometric authentication and respiratory anomaly detection are achieved, but device complexity increases
Solution Approach 1:
The system achieves multi-functionality by using a single acoustic sensing platform for both biometric authentication and respiratory anomaly detection. The same sound recording and analysis infrastructure serves dual purposes: verifying user identity through vocalization patterns and detecting respiratory threats, thereby reducing the need for separate specialized devices.
Solution Approach 2:
The system uses the user's own vocalization as both the authentication credential and the diagnostic sample. The user's voice naturally provides both identity verification information and respiratory health information, eliminating the need for separate authentication devices or medical testing equipment.
3Measurement precision
If multiple vocalization recordings are collected for baseline creation, then authentication accuracy improves, but time consumption increases
Solution Approach 1:
The system collects a sufficient number of vocalization samples (three recordings) to establish an accurate baseline without requiring excessive recording time. This partial action approach captures enough variability in the user's voice patterns to create a robust baseline while keeping the setup process quick and user-friendly.
Data Source
AI summary
Systems and methods of the present disclosure enable authentication and/or anomaly detection using machine learning-based modelling. Audio recordings that represent audio from a forced cough vocalizations are received from a user device. One or more audio filters extract forced cough vocalization recordings from the audio recordings and signal data signatures representative of the forced cough vocalization recordings are generated. Gaussian mixture models are produced for each unique combination of the signal data signatures, where each unique combination include a group of model baselines and a test match baseline. Each Gaussian mixture model is used to produce a match value for the associated test match baseline based on the associated model baselines, and a statistical score is determined for each match value. One or more baseline Gaussian mixture models are determined based on the statistical score and stored in a user profile.