Switching latency in ear-worn devices implementing neural networks

Ear-worn devices switch between latency configurations using different neural networks to balance noise reduction and user experience, addressing latency challenges in noisy environments.

WO2026112188A1PCT designated stage Publication Date: 2026-05-28FORTELL RESEARCH INC
View PDF 8 Cites 0 Cited by

Patent Information

Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
FORTELL RESEARCH INC
Filing Date
2025-11-19
Publication Date
2026-05-28

AI Technical Summary

Technical Problem

Ear-worn devices face challenges in balancing data processing latency to achieve high-quality noise reduction and user experience, particularly in noisy environments, where longer latencies can improve noise separation but lead to lag in voice processing.

Method used

The device switches between configurations with different data processing latencies based on environmental conditions or user input, using distinct neural networks for each configuration to optimize performance.

Benefits of technology

This approach enhances user experience by adapting to noise levels while maintaining effective noise reduction and minimizing latency issues.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure US2025056185_28052026_PF_FP_ABST
    Figure US2025056185_28052026_PF_FP_ABST
Patent Text Reader

Abstract

Described herein is an ear-worn device that may include processing circuitry and control circuitry. The processing circuitry may include neural network circuitry configured to implement one or more first neural network layers or one or more second neural network layers. The control circuitry may be configured to control the processing circuitry to operate using a first configuration or a second configuration. The neural network circuitry may be configured to implement the one or more first neural network layers when the processing circuitry operates using the first configuration, and the first configuration may have a first data processing latency. The neural network circuitry may be configured to implement the one or more second neural network layers when the processing circuitry operates using the second configuration, and the second configuration may have a second data processing latency different from the first data processing latency.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • US11812225B2

  • US11886974B1

  • US11937047B1

  • US12231851B1

  • US12418756B2