Subtitle Appending Based on Media Context

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Traditional video subtitles only display dialog text and time/place information, failing to include background music or voice, which can enhance understanding, especially for viewers with hearing impairments or in noisy environments.

Innovation Solution

A system that automatically generates and appends additional subtitles based on scene recognition, transforming background information into descriptive text, which conveys tone and atmosphere through font changes, emoticons, and other visual cues.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If traditional subtitles only display dialog text and time/place information, then the subtitle format remains simple and easy to process, but background information such as background music or background voice is lost

Engineering Contradiction:
Improvebackground informationVSAvoidsubtitle format
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The patent embeds additional background information transcripts within the existing subtitle structure, nesting supplementary audio cues inside the standard subtitle format. This allows background music and voice information to be included without fundamentally changing how subtitles are displayed or processed, thus resolving the contradiction between information completeness and format simplicity.

Inventive Principle:
Principle #7Nested doll (Nesting)

Solution Approach 2:

The patent segments the subtitle into multiple components: primary dialog text and secondary background information. By separating these elements while maintaining a unified subtitle structure, the system can provide comprehensive information without overwhelming complexity in the overall format.

Inventive Principle:
Principle #1Segmentation

2Loss of information

If additional transcripts are appended to provide comprehensive scene information, then viewer understanding is enhanced, but the subtitle processing complexity increases

Engineering Contradiction:
Improvescene informationVSAvoidprocessing complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The system automatically generates and appends background information transcripts without requiring manual intervention or complex processing workflows. The automated transcription and appending processes handle the complexity internally, presenting simple output to viewers while managing processing requirements through self-service automation.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS12010393B2Automatic appending of subtitles based on media context
Publication Date: 2024.06.11 INTERNATIONAL BUSINESS MACHINE CORPORATION
  • US12010393B2 patent drawing
  • US12010393B2 patent drawing
  • US12010393B2 patent drawing

AI summary

A processor may automatically generate one or more transcripts based on a media context. The processor may append at least one of the one or more transcripts to the media. The processor may modify the at least one of the one or more transcripts based on an adjustment to a weight factor.