Speech-to-Text Conversion for Interactive Whiteboards

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Electronic meetings often suffer from inefficiencies due to lack of proper organization, leading to wasted time and ineffective follow-up actions, such as transcription, scheduling additional meetings, and analyzing participation, which can be tedious and costly.

Innovation Solution

An apparatus comprising processors and memories that utilize artificial intelligence to manage electronic meetings by receiving audio data, translating and transcribing it, detecting person presence, tracking attendance, and analyzing meeting content to generate agendas, identify participants, and provide real-time and post-meeting processing, including sentiment analysis and report generation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If manual transcription and follow-up actions are performed, then meeting records and analysis are obtained, but time and cost are significantly consumed

Engineering Contradiction:
Improvemeeting transcription accuracyVSAvoidtranscription and follow-up time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system enables automatic self-service transcription and follow-up action generation through AI services. The whiteboard appliance automatically transcribes meeting audio, generates action items, and creates follow-up tasks without requiring manual human intervention, thus eliminating the time-consuming manual transcription process while maintaining high accuracy through multiple AI service providers

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical transcription processes with automated AI-based speech-to-text conversion services. Multiple translation/transcription services are used to convert audio data to text automatically, substituting the mechanical manual typing process with intelligent automated systems that provide both transcription and subsequent action item generation

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

2Measurement precision

If multiple translation/transcription services are used to improve accuracy, then transcription quality increases, but system complexity increases

Engineering Contradiction:
Improvetranscription accuracyVSAvoidsystem architecture complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system introduces an intermediary layer that manages multiple translation/transcription services. This intermediary layer receives audio data, distributes it to multiple AI services, aggregates the results, and presents a unified transcription output. This mediator approach maintains high transcription accuracy through multiple services while hiding the underlying complexity from the end user

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The whiteboard appliance is designed with multi-functionality to handle multiple translation/transcription services simultaneously. The system can select from and manage multiple AI service providers, aggregate their outputs, and provide comprehensive meeting processing capabilities including transcription, action item generation, and follow-up task creation within a single unified platform

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

Data Source

PatentUS10553208B2Speech-to-text conversion for interactive whiteboard appliances using multiple services
Publication Date: 2020.02.04 RICOH CO LTD
  • US10553208B2 patent drawing
  • US10553208B2 patent drawing
  • US10553208B2 patent drawing

AI summary

Artificial intelligence is introduced into an electronic meeting context to perform various tasks before, during, and/or after electronic meetings. The artificial intelligence may analyze a wide variety of data such as data pertaining to other electronic meetings, data pertaining to organizations and users, and other general information pertaining to any topic. Capability is also provided to create, manage, and enforce meeting rules templates that specify requirements and constraints for various aspects of electronic meetings. Embodiments include improved approaches for translation and transcription using multiple translation/transcription services. Embodiments also include using sensors in conjunction with interactive whiteboard appliances to perform person detection, person identification, attendance tracking, and improved meeting start. Embodiments further include improvements to the presentation of content on interactive whiteboard appliances, providing meeting services for meeting attendees, agenda extraction, and learning to aid in creating new electronic meetings.