Context-Aware Noise Muting for Listening Devices

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Individuals often face the challenge of overhearing unnecessary conversations while engaged in tasks, leading to a helplessness in choosing between hearing all conversations or nothing, as existing noise cancellation methods lack the ability to selectively mute irrelevant noise based on context.

Innovation Solution

A computer-implemented method that identifies noise sources and determines their relevance to the user's context, using a conversation manager to calculate relevance scores and dynamically mute irrelevant noise, allowing only relevant conversations to be heard.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Object-affected harmful factors

If traditional noise cancellation methods are used, then all noise is reduced, but relevant conversations are also muted along with irrelevant noise

Engineering Contradiction:
Improveirrelevant noiseVSAvoidrelevant conversation
Core Design Contradiction:
Object-affected harmful factorsVSLoss of information

Solution Approach 1:

The patent segments the audio environment into multiple distinct sound sources and individually evaluates each source's relevance to the user's current task. Instead of treating all noise uniformly, the system identifies and processes each sound source separately, allowing selective muting of only those sources deemed irrelevant while preserving relevant conversations.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system dynamically changes the relevance parameter for each noise source based on contextual analysis. By calculating relevance scores that reflect the relationship between each sound source and the user's current activity, the system adjusts which sounds are muted and which are preserved, transforming the static noise cancellation approach into a dynamic, context-aware system.

Inventive Principle:
Principle #35Parameter changes

2Loss of information

If all conversations are heard, then no relevant information is lost, but distracting noise reduces productivity

Engineering Contradiction:
Improveconversation informationVSAvoiduser focus
Core Design Contradiction:
Loss of informationVSProductivity

Solution Approach 1:

The system continuously monitors both the audio environment and the user's current task context, using this feedback to dynamically adjust which sound sources are muted. By comparing the characteristics of each noise source against the user's current activity, the system provides adaptive noise filtering that maintains productivity while preserving important information.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The noise cancellation system transitions from a static approach to a dynamic one, where the muting decisions for each noise source can change in real-time based on the user's current task. This dynamic adaptation allows the system to optimize for productivity during focused work while preserving relevant conversations when appropriate.

Inventive Principle:
Principle #15Dynamics

3Loss of information

If context-aware noise filtering is implemented, then relevant conversations are preserved, but system complexity increases

Engineering Contradiction:
Improverelevant conversationVSAvoidnoise cancellation system
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The system performs preliminary analysis of each noise source to determine its relevance characteristics before making muting decisions. By pre-processing and categorizing sound sources based on their potential relevance to common tasks, the system reduces the computational complexity of real-time decisions while maintaining accurate relevant noise filtering.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20240304170A1Dynamically muting conversations based on context
Publication Date: 2024.09.12 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US20240304170A1 patent drawing
  • US20240304170A1 patent drawing
  • US20240304170A1 patent drawing

AI summary

A computer-implemented method dynamically mutes irrelevant sources of noise. The method includes identifying one or more sources of a noise in a vicinity of a listening device, where the listening device is associated with a user and the listening device includes a noise canceling function. The method also includes determining, for the user, a context, where the context represents a subject of a conversation related to the user. The method further includes calculating, for each of the one or more sources of noise, a relevance score. The method includes muting, by the listening device, each of the sources of noise where the associated relevance score is below a relevance threshold.