Mobile Voice Training Noise Interruption Mechanism

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Speech recognition in mobile devices is hindered by background noise during voice training, leading to increased errors in voice recognition, as existing systems fail to effectively assess and mitigate noise levels and types.

Innovation Solution

A mobile device system that determines background noise levels and types during voice training, interrupting the process if noise exceeds a threshold and displaying a noise indicator interface to prompt the user to move to a quieter location, enabling continuation only when noise levels meet a predetermined threshold.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If voice training is performed in environments with background noise, then voice recognition training can be completed, but the accuracy of voice recognition deteriorates due to excessive background noise

Engineering Contradiction:
Improvevoice training completionVSAvoidvoice recognition accuracy
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system performs preliminary noise assessment before allowing voice training to proceed. The noise detection unit evaluates the acoustic environment in advance, and only when noise levels are below the threshold does the system permit training recording, thereby preventing noise-contaminated training data from being collected

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors background noise levels during the training process and provides feedback to control whether training should proceed or be interrupted. When noise exceeds the threshold, the system interrupts training and notifies the user, creating a closed-loop control mechanism that maintains training quality

Inventive Principle:
Principle #23Feedback

2Reliability

If the system interrupts voice training when noise exceeds threshold, then voice recognition accuracy is improved, but the training time increases due to repeated interruptions

Engineering Contradiction:
Improvevoice recognition accuracyVSAvoidtraining time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs noise assessment before training begins and during pauses in training. By detecting noise levels in advance and interrupting only when necessary, the system avoids wasting time on training sessions that would be contaminated by excessive noise, thereby reducing the need for retraining

Inventive Principle:
Principle #10Preliminary action

3Manufacturing precision

If the system continuously monitors background noise levels, then the quality of voice training samples is improved, but the device complexity increases due to additional monitoring components

Engineering Contradiction:
Improvevoice training sample qualityVSAvoidnoise monitoring system complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The voice recognition system's audio processing components serve dual purposes: they process both the user's voice for training and simultaneously analyze the background noise environment. This multi-functionality allows noise monitoring without requiring entirely separate dedicated hardware, thereby limiting the increase in device complexity

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

Data Source

PatentUS10510337B2Method and device for voice recognition training
Publication Date: 2019.12.17 GOOGLE TECHNOLOGY HOLDINGS LLC
  • US10510337B2 patent drawing
  • US10510337B2 patent drawing
  • US10510337B2 patent drawing

AI summary

A method on a mobile device for voice recognition training is described. A voice training mode is entered. A voice training sample for a user of the mobile device is recorded. The voice training mode is interrupted to enter a noise indicator mode based on a sample background noise level for the voice training sample and a sample background noise type for the voice training sample. The voice training mode is returned to from the noise indicator mode when the user provides a continuation input that indicates a current background noise level meets an indicator threshold value.