Hearing Device Speaker Recognition for Automatic Wireless Joining

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing wireless personal communication methods for hearing devices are inefficient in terms of energy consumption and signal quality, particularly in noisy environments and when users are not in close proximity, and lack effective automatic connection establishment based on speaker recognition.

Innovation Solution

A method using speaker recognition to automatically establish, join, or leave wireless personal communication connections between hearing devices by analyzing the user's acoustic environment and utilizing content-independent speaker voiceprints, combined with beam formers to improve signal-to-noise ratio, and optional user interface notifications.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If beam formers are used to improve signal-to-noise ratio, then signal quality is improved, but device complexity increases

Engineering Contradiction:
Improvesignal qualityVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The hearing device integrates multiple functions including beam forming capability, speaker recognition, and wireless communication into a single device. The beam former is part of a multi-functional system that also handles voice activity detection and automatic connection establishment, making the complexity serve multiple purposes rather than being dedicated to a single function.

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

Solution Approach 2:

The system performs preliminary voice activity detection and speaker recognition before establishing wireless connections. The beam former is activated in advance based on detected voice activity, preparing the signal processing path before actual communication begins, which improves signal quality while managing complexity through conditional activation.

Inventive Principle:
Principle #10Preliminary action

2Ease of operation

If automatic connection establishment based on speaker recognition is implemented, then ease of operation is improved, but use of energy increases

Engineering Contradiction:
Improveease of operationVSAvoiduse of energy
Core Design Contradiction:
Ease of operationVSUse of energy by moving object

Solution Approach 1:

The system uses periodic voice activity detection and speaker recognition checks rather than continuous processing. The hearing device monitors the acoustic environment at intervals, detecting voice activity and performing speaker recognition only when needed, which maintains automatic connection establishment capability while significantly reducing energy consumption compared to continuous operation.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The hearing device automatically performs speaker recognition and connection establishment without requiring user intervention. The system self-manages the detection of conversation participants, verification of speaker identity, and establishment of wireless connections, eliminating the need for manual pairing operations while optimizing energy usage through automated decision-making.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If content-independent speaker voiceprints are used for recognition, then measurement precision is improved, but loss of information increases

Engineering Contradiction:
Improvespeaker recognition accuracyVSAvoidvoice content information
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The voice signal is segmented into distinct components: voiceprint features extracted for speaker identification, and voice content preserved for communication purposes. The system separates the analysis of speaker identity (using content-independent voiceprints) from the transmission of actual speech content, allowing accurate speaker recognition without losing the informational content of the voice messages.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The content-independent voiceprint acts as an intermediary representation that enables speaker recognition without requiring transmission or processing of the actual voice content. The voiceprint serves as a compact identifier that verifies speaker identity while the original voice content remains intact for communication, resolving the conflict between recognition accuracy and information preservation.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4017021B1Wireless personal communication via a hearing device
Publication Date: 2025.11.12 SONOVA AG
  • EP4017021B1 patent drawingFigure 1~2
  • EP4017021B1 patent drawingFigure 3~4
  • EP4017021B1 patent drawingFigure 5~6

AI summary

A method for a wireless personal communication using a hearing system (10) with a hearing device (12) comprises: monitoring and analyzing the user's acoustic environment by the hearing device (12) to recognize one or more speaking persons based on content-independent speaker voiceprints saved in the hearing system (10); and presenting a user interface to the user for notifying the user about a recognized speaking person and for establishing, joining or leaving a wireless personal communication connection between the hearing device (12) and one or more communication devices used by the one or more recognized speaking persons.