Web Conferencing System Identifies Speaking Person
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In web conferencing scenarios where multiple participants share a microphone, existing systems struggle to accurately identify the speaking person, leading to issues like howling and voice interruptions.
Innovation Solution
A computer-readable medium and web conferencing system that identifies speaking persons by distinguishing between voice input and volume input modes, using a server to differentiate between participants based on IP addresses and microphone usage, and displaying this information on a shared screen.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If a speakerphone is used for multiple participants to share a microphone, then howling and voice interruptions are reduced, but the system cannot identify the actual speaking person
Solution Approach 1:
The system segments the audio signal processing by identifying individual participant terminals within a group sharing a speakerphone. Each terminal's audio input is separately analyzed to detect volume changes, allowing the system to identify which specific participant is speaking while maintaining the shared microphone configuration.
Solution Approach 2:
The system implements feedback by continuously monitoring volume information from each terminal and using this feedback to dynamically identify the speaking person. The server receives volume data from all terminals, compares it against reference values, and updates the speaking person identification in real-time based on the feedback loop.
2Measurement precision
If volume information is monitored from all terminals, then the speaking person can be identified, but the system complexity increases
Solution Approach 1:
The server performs multiple functions: it manages group formations, receives audio signals from terminals, processes volume information, identifies speaking persons, and displays results. This multi-functionality consolidates the system complexity into a single central component rather than distributing it across multiple devices.
Solution Approach 2:
Each terminal autonomously monitors its own volume information and transmits only relevant data to the server. The terminals self-manage their audio input characteristics without requiring complex coordination with other terminals, reducing overall system complexity.
Data Source
AI summary
A non-transitory computer readable medium is provided, the medium storing a program causing a process to be executed by a computer operating as a server of a web conferencing system, the process including: identifying a group of participants sharing a microphone to be used for voice input; and identifying, if information indicating a volume equal to or greater than a reference value from a terminal not connected to the microphone from among terminals of the participants belonging to the group is inputted while a voice from the group is being inputted, the participant whose terminal corresponds to the transmission origin of the information as a speaking person.