Switchable Microphone Array for Noise-Robust Audio Capture

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional personal listening devices lack advanced audio processing capabilities, microphone arrays that can be selectively adjusted for different situations, and the ability to store, process, analyze, and report on detected audio content.

Innovation Solution

A media capture and process system that includes a user media device with a selectively adjustable microphone array, which captures audio and visual media, and processes it in real-time using a connected computer or remote service, performing noise cancellation, natural language processing, and deep learning to generate reports and insights.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional personal listening devices are used, then device simplicity is maintained, but audio processing capability and adaptability are limited

Engineering Contradiction:
Improveaudio processing capabilityVSAvoiddevice complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system divides audio processing functions into segments: the wearable device captures audio with the microphone array, while a separate computing device (smartphone, tablet, or cloud service) performs the complex signal processing, noise cancellation, and analysis. This segmentation allows the wearable device to remain simple while achieving advanced audio processing capabilities through external computational resources.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

A computing device acts as an intermediary between the wearable listening device and the user. The intermediary receives audio data from the simple wearable device, performs complex processing including adaptive noise cancellation and voice activity detection, then delivers processed audio to the user. This intermediary approach enables advanced functionality without complicating the wearable device itself.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If a fixed microphone configuration is used, then device simplicity is maintained, but adaptability to different listening situations is reduced

Engineering Contradiction:
Improveadaptability to listening situationsVSAvoidmicrophone array complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The microphone array employs dynamic configuration where individual microphones can be selectively activated or deactivated based on the listening situation. The system adapts its microphone configuration in real-time through voice activity detection and noise analysis, switching between different microphone combinations to optimize performance for specific scenarios such as one-on-one conversations, group discussions, or noisy environments.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The microphone array is designed with universal adaptability, where the same physical array of microphones can serve multiple functions across different listening situations. By implementing software-based beamforming and noise cancellation algorithms that work across various configurations, the system achieves multi-functionality without requiring separate hardware for each listening scenario.

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

3Reliability

If audio processing is performed locally on the wearable device, then real-time processing is achieved, but processing robustness and analytical capability are limited

Engineering Contradiction:
Improveprocessing robustnessVSAvoidprocessing capability
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system replaces local mechanical processing limitations with remote computational power. Instead of relying on the limited processing capabilities of the small wearable device, the invention substitutes local processing with cloud-based or smartphone-based processing resources. This substitution enables robust audio analysis, deep learning-based noise cancellation, and comprehensive voice activity detection while maintaining real-time performance through wireless communication.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

4Loss of information

If no audio storage and analysis capability is provided, then device simplicity is maintained, but ability to generate reports and insights is lost

Engineering Contradiction:
Improveaudio content analysisVSAvoidsystem complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The system performs preliminary audio capture and transmission to a computing device for analysis. The wearable device captures audio content and promptly transmits it for offline analysis, preserving the information while deferring the complex analysis work to a more capable device. This preliminary action ensures no information is lost while managing system complexity by separating capture from analysis functions.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3340647B1Media capture and process system
Publication Date: 2021.03.31 FUJITSU LTD
  • EP3340647B1 patent drawingFigure 1
  • EP3340647B1 patent drawingFigure 2
  • EP3340647B1 patent drawingFigure 3

AI summary

A user media device may include a microphone array and a communication interface. The microphone array may include an omnidirectional microphone and a directional microphone. The microphone array may be selectively switchable. The communication interface may communicatively couple the user media device with a computer and may transmit audio captured by the microphone array to the computer for transfer to a remote service. The remote service may generate text of the processed audio via natural language processing. The remote service may further perform semantic reasoning of the processed audio via a semantic reasoning engine. The remote service may also generate content based at least in part on the semantic reasoning performed on the processed audio. The curated content may include a report having results of the semantic reasoning organized to demonstrate the results in a meaningful way with respect to the processed audio.