Distributed Device Meeting Initiation Through Audio Watermarking

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing conferencing tools are inadequate for recording and transcribing ad-hoc meetings, which often lack preparation and rely on unavailable recording devices, disrupting the meeting process and lacking real-time transcription capabilities.

Innovation Solution

A system utilizing distributed devices with audio watermarking, facial recognition, and voice fingerprinting to identify and authenticate participants, generating a real-time transcript through synchronized audio processing and translation, allowing for seamless ad-hoc meeting management.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If distributed devices (smartphones, tablets) are used for ad-hoc meeting recording, then device availability and ease of deployment are improved, but audio synchronization accuracy and speaker attribution reliability deteriorate due to lack of coordinated setup

Engineering Contradiction:
Improvedevice availabilityVSAvoidaudio synchronization accuracy
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent introduces an audio watermark as an intermediary signal that is embedded in the audio stream from one device and detected by other distributed devices. This watermark contains synchronization information that enables precise temporal alignment of audio recordings from multiple independent devices, resolving the synchronization accuracy problem while maintaining device availability

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system implements feedback by having each device detect watermarks from other devices and adjust its audio recording timing accordingly. The synchronization process continuously refines timestamp alignment based on detected watermark positions, enabling accurate speaker attribution despite the decentralized nature of distributed devices

Inventive Principle:
Principle #23Feedback

2Measurement precision

If existing conferencing tools with fixed recording devices are used, then transcription accuracy is improved, but meeting disruption and setup complexity increase

Engineering Contradiction:
Improvetranscription accuracyVSAvoidmeeting disruption
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent enables distributed devices to automatically perform recording and transcription functions without requiring dedicated conferencing equipment. Each device uses its own microphone and processing capabilities, with the system self-organizing through watermark detection and synchronization, eliminating the need for setup and avoiding meeting disruption

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system makes ordinary distributed devices multi-functional by enabling them to perform both audio recording and speech-to-text transcription that were previously the domain of specialized conferencing tools. This universality allows participants to use their existing devices for both meeting participation and recording functions

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

3Measurement precision

If audio watermarking is implemented for device identification, then participant authentication accuracy is improved, but processing time and computational resources increase

Engineering Contradiction:
Improveparticipant authentication accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent embeds audio watermarks containing device identification information into the audio stream in advance, during the normal meeting flow. This preliminary action allows for accurate participant authentication without requiring separate authentication steps, as the watermark is continuously present and can be detected at any point during the meeting

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3963575B1Distributed device meeting initiation
Publication Date: 2025.09.03 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP3963575B1 patent drawingFigure 1~2
  • EP3963575B1 patent drawingFigure 3~4
  • EP3963575B1 patent drawingFigure 5~6

AI summary

A computer implemented method includes receiving audio streams at a meeting server from two distributed devices that are streaming audio captured during an ad-hoc meeting between at least two users, comparing the received audio streams to determine that the received audio streams are representative of sound from the ad-hoc meeting, generating a meeting instance to process the audio streams in response to the comparing determining that the audio streams are representative of sound from the ad-hoc meeting, and processing the received audio streams to generate a transcript of the ad-hoc meeting.