Acoustic Representation Authentication for Privacy-Preserving Dictation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Healthcare providers face authentication burdens and privacy concerns when using multiple computing devices for dictation, particularly in environments where rapid location changes are common, and existing authentication methods may expose sensitive audio data.

Innovation Solution

A device and method for privacy-preserving authentication using trained models to generate privacy-preserving acoustic representations of audio segments from different microphones, comparing these representations to determine microphone association and authenticate the user based on similarity metrics, ensuring privacy by not transmitting speech content.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional authentication methods are used at each computing device, then security is maintained, but authentication time and operational burden increase significantly

Engineering Contradiction:
Improveauthentication securityVSAvoidauthentication time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary authentication by capturing audio data from the environment before the user actively initiates authentication. The server continuously monitors acoustic representations and automatically authenticates users based on pre-established audio profiles, eliminating the need for manual authentication actions at each device.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The authentication system operates autonomously by automatically capturing environmental audio, comparing it against stored profiles, and authenticating users without requiring their active participation. The system serves itself by continuously monitoring and automatically verifying user identity based on acoustic signatures.

Inventive Principle:
Principle #25Self-service

2Measurement precision

If audio data is transmitted for authentication purposes, then authentication accuracy improves, but privacy of sensitive conversations is compromised

Engineering Contradiction:
Improveauthentication accuracyVSAvoidprivacy exposure
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The system extracts only the acoustic representation features necessary for authentication from the audio data, separating these features from the actual speech content. By extracting and transmitting only the authentication-relevant acoustic characteristics while leaving the conversational content on the local device, the system achieves accurate authentication without exposing private conversations.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system uses acoustic representations as an intermediary between the audio data and the authentication process. Instead of directly transmitting or analyzing raw audio content, the intermediary acoustic features serve as a privacy-preserving bridge that enables authentication while protecting the underlying sensitive conversation content.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Adaptability or versatility

If multiple computing devices are used for dictation, then workflow flexibility improves, but authentication complexity increases

Engineering Contradiction:
Improveworkflow flexibilityVSAvoidauthentication complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system implements a universal authentication mechanism based on environmental acoustic representations that works across all computing devices without requiring device-specific authentication configurations. The same acoustic-based authentication approach functions consistently whether the user is at a desktop, laptop, or mobile device, simplifying the overall authentication system despite multiple devices.

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

Data Source

PatentEP4704082A1Device and computer-implemented method for privacy-preserving authentication
Publication Date: 2026.03.04 SOLVENTUM INTELLECTUAL PROPERTIES CO
  • EP4704082A1 patent drawingFigure 1
  • EP4704082A1 patent drawingFigure 2
  • EP4704082A1 patent drawingFigure 3

AI summary

A computer-implemented method for privacy-preserving authentication includes: receiving a first privacy-preserving acoustic representation of a first audio segment associated with a first microphone from a first computing device, the first privacy-preserving acoustic representation being locally generated on the first computing device by a trained model based on the first audio segment; receiving a second privacy-preserving acoustic representation of a second audio segment associated with a second microphone from a second computing device, the second audio segment being generated by the second microphone contemporaneously with the first audio segment; generating a similarity metric score based on the first privacy-preserving acoustic representation and the second privacy-preserving acoustic representation; determining that the first microphone and the second microphone are associated with a substantially similar location based on the similarity metric score; and authenticating that the first microphone and the second microphone are associated with the substantially similar location.