Audio Signal Categorization for Unintended Noise Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional web meetings are compromised by unintended noise from participants, such as keyboard typing, background noise, and environmental sounds, which degrade the quality of the experience and can be embarrassing for the source, leading to reluctance in addressing the issue to avoid rudeness or further quality reduction.

Innovation Solution

Audio signals from participants are categorized as intended or unintended based on contextual factors like language detection, sound volume, repetitiveness, and location, allowing for adjustments in sound levels and user alerts to enhance the meeting quality by distinguishing and managing unintentional participant sounds.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If all meeting members' voice data is combined into a single audio feed, then all participants can hear everyone, but unintended noise from any participant degrades the overall audio quality

Engineering Contradiction:
Improveability to hear all participantsVSAvoidunintended noise degradation
Core Design Contradiction:
Adaptability or versatilityVSObject-affected harmful factors

Solution Approach 1:

The patent segments the combined audio feed into individual participant audio streams, allowing separate processing and analysis of each participant's audio signal. This enables the system to identify and manage unintended noise from specific participants while preserving the ability to hear all participants.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary audio processing system that acts as a mediator between the raw audio feeds from participants and the final combined audio output. This intermediary system analyzes audio characteristics, identifies unintended noise, and applies selective filtering or attenuation before combining the audio streams.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Object-affected harmful factors

If audio signals are processed to remove unintended noise, then audio quality improves, but the system complexity increases due to need for categorization and control mechanisms

Engineering Contradiction:
Improveunintended noise reductionVSAvoidaudio processing system complexity
Core Design Contradiction:
Object-affected harmful factorsVSDevice complexity

Solution Approach 1:

The patent implements self-service mechanisms where the audio processing system automatically categorizes audio signals as intended or unintended based on analysis of audio characteristics such as volume, duration, and patterns. The system self-regulates by automatically adjusting audio levels and providing alerts without requiring manual intervention or complex external control mechanisms.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent employs feedback mechanisms where the audio processing system continuously monitors audio signals, categorizes them, and provides real-time feedback through alerts to participants when unintended noise is detected. This feedback loop enables automatic adjustment of audio processing parameters based on detected noise patterns.

Inventive Principle:
Principle #23Feedback

3Object-affected harmful factors

If participants are alerted about unintended noise, then meeting quality improves, but participants may feel embarrassed or rude leading to social discomfort

Engineering Contradiction:
Improvemeeting quality enhancementVSAvoidsocial discomfort
Core Design Contradiction:
Object-affected harmful factorsVSObject-generated harmful factors

Solution Approach 1:

The patent applies partial action by selectively alerting participants only when unintended noise is detected, rather than continuously monitoring and alerting for all audio signals. The system uses thresholds and patterns to determine when alerting is appropriate, balancing quality improvement with social comfort.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The patent implements preliminary action by providing gentle alerts or notifications to participants before more severe penalties or disruptions occur. The system may first issue subtle warnings or visual indicators, allowing participants to correct their behavior before more intrusive measures are taken.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP2962423B1Controlling an electronic conference based on detection of intended versus unintended sound
Publication Date: 2020.01.15 GETGO INC
  • EP2962423B1 patent drawingFigure 1
  • EP2962423B1 patent drawingFigure 2
  • EP2962423B1 patent drawingFigure 3

AI summary

A technique manages an electronic conference. The technique involves receiving a set of audio signals from a set of participants of the electronic conference, each audio signal being received from a respective participant. The technique further involves categorizing the set of audio signals received from the set of participants, each audio signal being individually categorized as currently representing (i) intentional participant sound or (ii) unintentional participant sound. The technique further involves controlling operation of the electronic conference based on the categorized set of audio signals.