Speech Sensitivity Adjustment for Diverse User Accessibility

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current speech recognition technologies face challenges in accurately understanding users with speech impairments or disorders, and those with strong accents or foreign language speakers, often resulting in difficulties interacting with speech-enabled applications.

Innovation Solution

An automatic speech sensitivity adjustment feature that dynamically adjusts the sensitivity level based on the number and type of speech errors, allowing for more lenient or stringent error detection, thereby improving interaction accessibility for diverse users.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a high sensitivity level is used for speech error detection, then speech accuracy is improved, but users with speech impairments or strong accents experience difficulty interacting with the system

Engineering Contradiction:
Improvespeech error detection accuracyVSAvoidinteraction accessibility
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system dynamically adjusts the sensitivity level based on the user's speech characteristics. Initially, the sensitivity is set high to ensure accurate error detection for standard speech patterns. When speech errors are detected, the system automatically lowers the sensitivity threshold, making the system more tolerant of variations in pronunciation, accents, and speech impairments, thereby improving accessibility without sacrificing detection accuracy for clear speech

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The invention changes the sensitivity parameter of the speech error detection system based on detected speech patterns. By modifying this parameter in response to speech errors, the system adapts its detection strictness to accommodate diverse speech characteristics, resolving the contradiction between maintaining high detection accuracy and ensuring ease of operation for all users

Inventive Principle:
Principle #35Parameter changes

2Ease of operation

If a low sensitivity level is used for speech error detection, then interaction accessibility is improved, but speech error detection accuracy deteriorates

Engineering Contradiction:
Improveinteraction accessibilityVSAvoidspeech error detection accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The system employs dynamic sensitivity adjustment where the sensitivity level is not fixed but changes based on real-time speech analysis. When users with speech impairments or strong accents are detected, the system lowers sensitivity to improve accessibility. When clear, standard speech is detected, sensitivity increases to maintain high detection accuracy, thus resolving the contradiction between accessibility and precision

Inventive Principle:
Principle #15Dynamics

3Adaptability or versatility

If automatic sensitivity adjustment is implemented, then adaptability to different users is improved, but system complexity increases

Engineering Contradiction:
Improveuser accommodation capabilityVSAvoidsystem architecture complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system implements a feedback mechanism where speech errors are detected and fed back to the sensitivity adjustment module. This feedback loop automatically triggers sensitivity level changes without requiring complex user profiling or manual configuration. The feedback-based approach enables adaptability to different users while keeping the system architecture relatively simple, as the adjustment is driven by automatic detection rather than complex algorithms

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The speech recognition system performs self-adjustment of sensitivity levels based on its own detection of speech errors. Rather than requiring external configuration or complex user input analysis, the system serves itself by automatically adapting its parameters in response to detected speech patterns, thereby achieving high adaptability with minimal additional system complexity

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4022605B1Automatic speech sensitivity adjustment feature
Publication Date: 2025.01.01 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP4022605B1 patent drawingFigure 1
  • EP4022605B1 patent drawingFigure 2A
  • EP4022605B1 patent drawingFigure 2B

AI summary

An automatic speech sensitivity adjustment feature is provided. The described sensitivity feature can enable an automatic system adjustment of a sensitivity level based on the number and type of determined speech errors. The sensitivity level determines how sensitive the sensitivity feature will be when indicating speech errors. The sensitivity feature can receive audio input comprising one or more spoken words and determine speech errors for the audio input using at least a sensitivity level. The sensitivity feature can determine whether an amount and type of the speech errors requires an adjustment to the sensitivity level. The sensitivity feature can adjust the sensitivity level to a second sensitivity level based on the amount and type of the speech errors, where the second sensitivity level is a different level than the sensitivity level. The sensitivity feature can re-determine the speech errors for the audio input using at least the second sensitivity level.