Distributed Sound Detection for Disturbance Source Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems are inadequate for effectively detecting and mitigating disturbing sounds in multi-unit buildings, such as office and apartment buildings, where sound travels through various structures and affects occupants.
Innovation Solution
A communications device with network interface and processing circuitry acquires sound representations from itself and spatially separated devices, filters based on sound level and similarity thresholds, and initiates volume adjustments or notifications to alleviate disturbances.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sound monitoring is performed using multiple spatially separated communications devices, then the ability to identify the source of disturbing sound is improved, but the complexity of the system increases
Solution Approach 1:
The system divides the monitoring task across multiple spatially separated communications devices, each independently acquiring sound representations in their respective surroundings. This segmentation enables triangulation of sound sources and improves identification accuracy without requiring a single complex centralized system
Solution Approach 2:
Standard communications devices with microphones are utilized for their dual purpose: their primary communication function and their secondary function as sound monitoring sensors. This multi-functionality reduces the need for dedicated monitoring equipment, thereby limiting the increase in system complexity
2Measurement precision
If a lower sound level threshold is used to detect disturbing sounds, then the sensitivity of detection is improved, but false positives from distant sound sources increase
Solution Approach 1:
The system introduces an intermediary analysis step that compares sound representations from multiple spatially separated devices. By analyzing similarities across these representations and considering spatial relationships, the system can distinguish between distant sounds (detected by multiple devices with low similarity) and nearby disturbing sounds (detected with high similarity), thereby reducing false positives while maintaining sensitivity
Solution Approach 2:
The system uses feedback from multiple sound representations to validate detections. A sound is more likely to be a true positive if it is consistently detected across multiple spatially separated devices with similar characteristics, allowing the system to maintain a low threshold while filtering out false positives through cross-validation
3Measurement precision
If sound representations are compared across multiple devices to identify the same sound source, then the accuracy of disturbance detection is improved, but the processing time and computational resources increase
Solution Approach 1:
The system extracts only the essential features from sound representations for comparison, such as acoustic fingerprints or key spectral characteristics, rather than processing entire audio files. This extraction approach maintains high detection accuracy while significantly reducing computational burden and processing time
Solution Approach 2:
The system performs partial comparison of sound representations by focusing on critical similarity metrics rather than exhaustive analysis of all sound parameters. This selective approach achieves sufficient detection accuracy with reduced computational resources and faster processing
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A first communications device (121) for detecting disturbing sound (101) is provided, operative to acquire a first representation of sound audible in a surrounding (120) of the first communications device, acquire, from second communications devices (111–114) which are spatially separated from the first communications device, second representations of sounds audible in the surroundings (110) of the second communications devices, and determine at least one second representation of sound which represents the same sound originating from the same source of sound. The first communications device is further operative to perform one or both of: i) if a sound level of a second representation of sound representing the same sound from the same source as the first representation of sound exceeds a first sound level threshold, and if the first communications device is proximate to the source of the sound, one or more of: trigger a notification to a user of the first communications device, reduce a volume of media played- out by the first communications device, and stop play-out of media by the first communications device, and ii) if a sound level of the first representation of sound exceeds a first sound level threshold, send a disturbance notification to the second communications device which is proximate to the source of the sound.