On-Demand Captioning via Intermediary Server

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional captioning systems are unable to provide on-demand captioning services for audiovisual content, especially during live events or when caption data is not embedded or transmitted with the audiovisual content, resulting in the inability to offer captioning for such content.

Innovation Solution

A system comprising a source captioning device and a caption management server that connects to a captioning service provider to generate and transmit caption data in real-time or on-demand, using automated or live captioning services, allowing for the provision of captioning for audio content without pre-existing caption data.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional captioning systems rely on pre-transmitted caption data, then captioning can be provided for standard broadcast content, but captioning cannot be provided for live events or content without embedded caption data

Engineering Contradiction:
Improvecaptioning service coverageVSAvoidcaptioning availability
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent introduces an intermediary captioning service provider system that acts as a mediator between audio content sources and receivers. This intermediary system receives audio content, processes it through speech-to-text conversion services, and generates caption data dynamically, enabling captioning for content that originally had no caption data.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary actions by pre-establishing connections with multiple captioning service providers and pre-processing audio content through automated speech recognition services. This allows the system to have caption data ready before it is actually needed by receivers, enabling real-time captioning delivery.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If real-time captioning is implemented for live events, then captioning availability is improved, but system complexity increases due to need for automated speech recognition services

Engineering Contradiction:
Improvecaptioning availabilityVSAvoidsystem architecture
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the captioning system into distinct functional modules: audio content reception units, automated speech recognition processing units, caption data generation units, and transmission units. This segmentation allows each component to be independently optimized and managed, reducing overall system complexity despite the advanced capabilities.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system implements self-service capabilities through automated speech recognition services that automatically process audio content without human intervention. The system autonomously generates caption data from raw audio, manages service provider selections, and handles transmission to receivers, reducing the need for manual operations.

Inventive Principle:
Principle #25Self-service

3Adaptability or versatility

If automated speech recognition services are used, then on-demand captioning capability is improved, but processing time and resource consumption increase

Engineering Contradiction:
Improveon-demand captioning capabilityVSAvoidcaptioning processing time
Core Design Contradiction:
Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary speech-to-text conversion processing in advance before the actual captioning service is requested. By pre-processing audio content and generating caption data ahead of time, the system reduces the processing time required when real-time captioning is actually needed, effectively caching processed data for rapid delivery.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS10582271B2On-demand captioning and translation
Publication Date: 2020.03.03 VZP DIGITAL
  • US10582271B2 patent drawing
  • US10582271B2 patent drawing
  • US10582271B2 patent drawing

AI summary

Novel tools and techniques are provided for a live and/or on-demand captioning service. A system may include a caption management server, and a source captioning device. The source captioning device may generate a request to initiate captioning service, transmit the request to the caption management server, transmit the audio content to a captioning service provider as determined by the caption management server, and receive, via the caption management server, caption data from the captioning service provider. The caption management server may determine a type of captioning service requested, and determine the captioning service provider for the source captioning device to transmit the audio content based, at least in part, on the type of captioning service requested.