Video Picture Switching via Voice Recognition in Video Conferences

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current video conference systems face discontinuity and reduced interactivity due to manual intervention required for switching video pictures, often resulting in hysteresis when participants switch venues.

Innovation Solution

A method and device that utilize voice recognition technology to automatically determine when a participant is called and switch video pictures to the corresponding venue, eliminating the need for manual intervention and enabling timely switching by establishing and updating correspondence relations between participants and venues.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Speed

If manual intervention via remote controller is used to switch video pictures, then the system operation is simple and reliable, but the switching speed is slow and continuity is broken

Engineering Contradiction:
Improvevideo picture switching speedVSAvoidmanual operation requirement
Core Design Contradiction:
SpeedVSEase of operation

Solution Approach 1:

The system automatically switches video pictures by detecting voice signals and identifying called participants without requiring manual intervention. The MCU autonomously completes the switching process based on voice recognition results, making the system self-serving and eliminating the need for user operation while achieving rapid switching.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical remote controller operation with voice recognition technology. Instead of manually pressing buttons on a remote controller, users simply speak the participant's name, and the system automatically recognizes and switches to the corresponding video picture, substituting mechanical operation with acoustic signal processing.

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

2Ease of operation

If voice activated switch is used to broadcast picture, then manual intervention is eliminated, but hysteresis occurs due to waiting for speech detection

Engineering Contradiction:
Improveautomatic switchingVSAvoidswitching delay
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system performs preliminary action by continuously monitoring and pre-processing voice signals during the conference. When a participant is called, the system has already detected and identified the voice signal, so switching can occur immediately without waiting for speech detection, eliminating hysteresis while maintaining automatic operation.

Inventive Principle:
Principle #10Preliminary action

3Productivity

If automatic voice recognition switching is implemented, then continuity and interactivity are improved, but system complexity increases

Engineering Contradiction:
Improveconference continuityVSAvoidvoice recognition system
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The MCU performs multiple functions: it manages video switching, processes voice signals, performs voice recognition, and maintains participant correspondence relations. By making the MCU multi-functional, the patent avoids adding separate dedicated hardware for each function, thereby improving productivity without proportionally increasing system complexity.

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

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Ensures continuity and enhances the 'face-to-face' experience in video conferences by allowing seamless video picture switching without manual intervention, improving the overall communication experience.

Implementation Method 1

determining, by the MCU, through voice recognition technology whether the participant is called based on the voice signal

Methodology Applied
Scientific EffectVoice recognition:

Data Source

PatentEP2528326B1Method and device for switching video pictures
Publication Date: 2016.05.04 HUAWEI DEVICE CO LTD
  • EP2528326B1 patent drawingFigure 1~2
  • EP2528326B1 patent drawingFigure 3~5
  • EP2528326B1 patent drawingFigure 6~7

AI summary

A method and device for switching video pictures are disclosed in the invention, which belong to video conference field. Said method includes: obtaining correspondence relations between participants and venues; finding, when a participant is called, a venue corresponding to the called participant according to the correspondence relations; and switching the video pictures to the venue corresponding to the called participant. The device includes a relation obtaining module, a venue finding module and a video switching module. Alternatively, the device includes a relation obtaining module, a venue finding module and a switch requesting module. According to the invention, it is possible to find the venue corresponding to the called participant according to the correspondence relations, and automatically switch the video to the venue or request to an MCU for switching the video to the venue, without a manual intervention of the participant or waiting for a response from the participant, so that continuity of the video conference is ensured, the video pictures can be switched in time, and "face to face" communion experience of the participants in the video conference is improved.