Aerosol Reachable Area Estimation via Speech and Mouth Position
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods fail to accurately estimate the area reachable by aerosol caused by speech sounds, making it difficult to reduce the risk of infection effectively.
Innovation Solution
An aerosol reachable area estimation system that detects voice and estimates the area based on the correlation between speech sounds and the velocity vector of aerosol released, using a detector and controller to identify the position and direction of the mouth, and notify the estimated area for disinfection or ventilation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing detection methods (sound-based cough/sneeze detection) are used, then infection risk can be detected, but the area reachable by aerosol cannot be accurately estimated
Solution Approach 1:
The system changes parameters by incorporating multiple detection modalities (sound detection, image recognition for mouth position/direction, and speech sound analysis) to accurately estimate aerosol reachable area. This multi-parameter approach transforms the estimation from impossible to achievable by combining different types of data about the utterer's state and environment.
Solution Approach 2:
The estimation process is segmented into distinct functional components: voice detection for speech sound identification, image recognition for mouth position and direction, correlation data storage for velocity vectors, and integration processing for final area calculation. This segmentation allows each component to specialize in one aspect while contributing to the overall accurate estimation.
2Reliability
If accurate aerosol area estimation is achieved through multiple parameters (speech sound, mouth position, velocity vector), then infection risk reduction improves, but system complexity increases
Solution Approach 1:
The controller serves multiple functions: it detects speech sounds, recognizes mouth position and direction from images, retrieves correlation data, performs integration calculations, and outputs estimation results. This multi-functionality reduces the need for separate dedicated components for each task, thereby managing system complexity while achieving reliable aerosol area estimation for infection risk reduction.
3Device complexity
If only speech sound detection is used, then system simplicity is maintained, but aerosol velocity and direction cannot be determined
Solution Approach 1:
The system uses an intermediary approach by introducing correlation data that links speech sounds to aerosol velocity vectors. This correlation data acts as a bridge between the easily detectable speech sound and the harder-to-measure aerosol dynamics, allowing velocity and direction information to be inferred without direct measurement of aerosol itself.
Solution Approach 2:
Instead of using complex mechanical or physical measurement systems to directly track aerosol velocity and direction, the system substitutes these with acoustic detection (microphone for speech sounds) and optical detection (camera for mouth position), combined with pre-established correlation data. This substitution achieves the same information goal with simpler, more practical detection methods.
Data Source
AI summary
An aerosol reachable area estimation system includes a detector that detects a voice and a controller that estimates an area reachable by aerosol released to a space where an utterer who has emitted the voice detected by the detector exists from a speech sound included in the voice on a basis of a correlation between the speech sound and a velocity vector of aerosol released from the utterer when the utterer utters the speech sound and a position and a direction of the utterer's mouth.