Audio Confirmation System Automates Voice-Text Verification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In audio confirmation systems, the existing technologies face challenges in ensuring that voice and text correspondences in motion picture content are accurate, leading to a significant burden for human testers to verify this correspondence, particularly when errors occur.

Innovation Solution

An audio confirmation system that includes a processor-based system with motion picture acquiring, voice recognizing, caption data acquiring, correspondence determining, and result outputting sections, utilizing voice recognition and character recognition techniques to automatically determine if voice and text in a motion picture correspond, reducing the need for manual verification.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual verification by human testers is used to confirm voice-text correspondence, then accuracy of verification is improved, but the burden and time consumption increase significantly

Engineering Contradiction:
Improveverification accuracyVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the mechanical human verification process with an automated computer-based system that uses voice recognition technology to extract and compare text from audio files with caption text, eliminating manual intervention while maintaining verification accuracy

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

Solution Approach 2:

The system enables self-verification by automatically extracting voice text through recognition algorithms and comparing it with caption text without requiring human testers, allowing the verification process to serve itself through automated computational methods

Inventive Principle:
Principle #25Self-service

2Ease of operation

If automated voice recognition and comparison is implemented, then the burden on testers is reduced, but system complexity increases

Engineering Contradiction:
Improvetester burdenVSAvoidsystem complexity
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The system integrates multiple functions into a single automated verification platform that handles voice extraction, voice recognition, text comparison, and result generation, making the complex process universally accessible through one system rather than multiple separate tools

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

Solution Approach 2:

The patent introduces an automated verification system as an intermediary between the content production process and quality assurance, mediating the verification task through computational algorithms that bridge audio processing and text comparison functions

Inventive Principle:
Principle #24Intermediary (Mediator)

3Reliability

If comprehensive voice-text correspondence verification is performed, then production failures are detected accurately, but the verification process becomes more complex and time-consuming

Engineering Contradiction:
Improvedetection accuracyVSAvoidverification process complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The verification process is segmented into distinct automated stages: voice extraction from audio files, voice recognition to convert speech to text, caption text extraction, and systematic comparison of the two text elements, breaking down complex verification into manageable computational steps

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system provides automated feedback by comparing voice-derived text with caption text and identifying discrepancies, allowing production failures to be detected through systematic feedback loops that highlight mismatches without requiring manual analysis

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP3720141B1Audio confirmation system, audio confirmation method, and program
Publication Date: 2024.01.03 SONY INTERACTIVE ENTERTAINMENT LLC
  • EP3720141B1 patent drawingFigure 1
  • EP3720141B1 patent drawingFigure 2
  • EP3720141B1 patent drawingFigure 3

AI summary

An audio confirmation system includes a voice acquiring section configured to acquire a voice contained in a motion picture; a voice text producing section configured to produce a voice text based on the acquired voice; a determining section configured to determine whether or not the produced voice text and a caption text that is embedded in an image contained in the motion picture correspond to each other; and an outputting section configured to output a result of the determination of the determining section.