Audio Event Detection Using Sound Source Location

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional surveillance systems fail to accurately distinguish sound events from different sources, leading to unnecessary notifications, as they detect sounds based solely on captured audio without considering the location of the sound source.

Innovation Solution

An electronic device equipped with multiple sound sensors, a feature extractor, and a location determination unit that extracts sound features and determines the location of the sound source, allowing for precise identification of audio events and selective notifications based on both sound characteristics and location information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional surveillance systems detect sound events based solely on captured audio without location information, then the system can detect all sounds including those from speakers, but the system generates false notifications and cannot distinguish security-relevant events from non-security events

Engineering Contradiction:
Improveaccuracy of sound event detectionVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent introduces location information as an additional dimension to the sound detection process. Instead of relying solely on audio characteristics, the system now considers both sound features and spatial position of the sound source. This dimensional expansion enables the system to distinguish between sounds from different locations, thereby improving detection accuracy and reducing false notifications while maintaining reasonable system complexity through the use of existing microphone arrays and processing capabilities.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Reliability

If the system provides notifications for all detected sound events, then the system ensures comprehensive monitoring, but the system generates unnecessary notifications that reduce user convenience

Engineering Contradiction:
Improvecompleteness of sound event monitoringVSAvoiduser convenience
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent applies local quality by making the notification behavior dependent on the specific location where the sound event occurs. Different locations are assigned different notification policies based on their security relevance. For example, sounds detected near security-sensitive areas trigger notifications, while sounds from known non-security areas (such as speaker locations) do not. This location-based differentiation maintains comprehensive monitoring while eliminating unnecessary notifications, thereby improving user convenience.

Inventive Principle:
Principle #3Local quality

3Measurement precision

If the system uses multiple sound sensors to determine location information, then the system can distinguish sound sources by location, but the system increases hardware complexity and cost

Engineering Contradiction:
Improveprecision of sound source locationVSAvoidnumber of sound sensors
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent makes the existing sound sensors serve multiple functions: they continue to detect sound events for security monitoring while simultaneously determining the location of sound sources through time difference of arrival or signal strength comparison. This multi-functionality allows the system to achieve precise location measurement without adding dedicated location-detection hardware, thereby improving measurement precision while controlling hardware complexity and cost.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS10134422B2Determining audio event based on location information
Publication Date: 2018.11.20 QUALCOMM INC
  • US10134422B2 patent drawing
  • US10134422B2 patent drawing
  • US10134422B2 patent drawing

AI summary

A method of determining, by an electronic device, an audio event is disclosed. The method may include receiving an input sound from a sound source by a plurality of sound sensors. The method may also extracting, by a processor, at least one sound feature from the received input sound, determining, by the processor, location information of the sound source based on the input sound received by the sound sensors, determining, by the processor, the audio event indicative of the input sound based on the at least one sound feature and the location information, and transmitting, by a communication unit, a notification of the audio event to an external electronic device.