Retroactive Sound Identification via Continuous Audio Capture

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users often struggle to identify the source of unfamiliar or transient sounds due to difficulty articulating search parameters, especially when sounds are unusual or ephemeral, limiting their ability to access internet information about the sound's source.

Innovation Solution

A sound identification system that uses a microphone, audio store, and object identification subsystem to retroactively identify sound-producing objects by analyzing recorded audio data, even if the object is no longer present, and provides information on the object's direction and the event causing the sound, utilizing machine learning and neural networks for accurate identification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If a user attempts to identify an unfamiliar or transient sound by performing an Internet search, then the user can access information about the sound source, but the user must be able to accurately describe the sound and formulate relevant search parameters

Engineering Contradiction:
Improveinformation about sound sourceVSAvoidability to describe and search for sound
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The system performs preliminary action by automatically recording ambient sounds in the user's vicinity before a search is initiated. The audio store continuously captures and stores sound data, so when the user later encounters an unfamiliar sound, the relevant audio data is already recorded and available for analysis, eliminating the need for the user to manually describe or capture the sound at the moment of inquiry.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system introduces an intermediary - the sound identification system itself - that bridges the gap between the user's inability to describe sounds and the need for information retrieval. The system includes an object identification subsystem that automatically analyzes recorded audio data, extracts sound features, and performs searches using those features as parameters, acting as an intermediary that translates acoustic signals into actionable search queries without requiring user interpretation.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of information

If a user tries to identify a transient sound event, then the user can understand what occurred, but the sound event cannot be retrieved once it has occurred

Engineering Contradiction:
Improvesound event dataVSAvoidduration of sound event
Core Design Contradiction:
Loss of informationVSDuration of action of moving object

Solution Approach 1:

The system performs preliminary action by continuously recording and storing ambient audio data in the audio store before the user needs to identify any sound. This pre-recording approach ensures that transient sound events are captured and preserved in storage, making them available for later analysis even though the original sound event has already occurred and ceased to exist in the physical environment.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates a copy of the transient sound event by storing it as digital audio data in the audio store. Instead of relying on the physical sound wave that has already passed, the system preserves an exact digital replica of the sound event, which can be retrieved, analyzed, and examined at any later time, effectively overcoming the transient nature of the original sound.

Inventive Principle:
Principle #26Copying

3Measurement precision

If the system records and analyzes audio data to identify sound-producing objects, then accurate identification can be achieved, but additional components (microphone, audio store, object identification subsystem) are required

Engineering Contradiction:
Improvesound identification accuracyVSAvoidsystem components
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system applies universality by designing components that serve multiple functions. The audio store not only stores audio data for identification purposes but also serves as a historical record for analysis. The object identification subsystem performs multiple tasks including feature extraction, pattern recognition, and search query formulation. This multi-functionality reduces the need for separate specialized components, thereby managing complexity while maintaining high identification accuracy.

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

Solution Approach 2:

The system merges multiple functions into integrated components. The microphone, audio store, and object identification subsystem work as a unified system rather than separate independent components. The audio store is seamlessly integrated with the identification subsystem, allowing direct access to recorded data for analysis. This merging approach streamlines the system architecture, reducing the apparent complexity while enabling accurate sound identification through coordinated operation of combined components.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP3591540B1Retroactive sound identification system
Publication Date: 2022.03.23 HARMAN INT IND INC
  • EP3591540B1 patent drawingFigure 1
  • EP3591540B1 patent drawingFigure 2
  • EP3591540B1 patent drawingFigure 3

AI summary

A method for identifying at least one characteristic of a sound-producing object includes storing, in a memory, audio data acquired from an auditory environment via at least one microphone; receiving an input indicating a user request to identify a characteristic of a sound-producing object included in the auditory environment; determining, via a processor and based on a portion of the audio data acquired from the auditory environment prior to the user request, the characteristic of the sound-producing object; and causing information corresponding to the characteristic of the sound-producing object to be output via at least one output device.