Adaptive wiener filtering denoising method and system based on three-state classification voice activity detection and storage medium

By employing a three-state classification speech activity detection and adaptive Wiener filtering method, the problem of poor adaptability to noise environments in cochlear implant systems is solved, achieving efficient noise reduction and speech clarity improvement in complex noise environments, making it suitable for cochlear implant systems.

CN121905138BActive Publication Date: 2026-06-26ZHEJIANG UNIV OF TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
ZHEJIANG UNIV OF TECH
Filing Date
2026-03-26
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing speech noise reduction technologies are difficult to adapt to complex and varied noise environments in cochlear implant systems, resulting in poor noise reduction effects, inability to accurately identify differences between speech, noise and silence, introduction of signal distortion or excessive residual noise, and impact on speech intelligibility and auditory comfort.

Method used

An adaptive Wiener filtering method based on three-state classification speech activity detection is adopted. By accurately classifying the audio signal into three states—speech, silence, and noise—and combining time-frequency domain minimum tracking and noise environment change detection, the Wiener filter parameters are dynamically adjusted to achieve accurate estimation and real-time monitoring of noise power spectral density.

Benefits of technology

It significantly improves speech signal-to-noise ratio and clarity in complex noisy environments, while maintaining speech fidelity and comfort. It is suitable for resource-constrained cochlear implant systems, enhancing speech perception and communication quality for hearing-impaired patients.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121905138B_ABST
    Figure CN121905138B_ABST
Patent Text Reader

Abstract

The application discloses a kind of based on tri-state classification voice activity detection's self-adapting wiener filtering noise reduction method and system and storage medium, for solving the technical problem that cochlear implant internal speech noise reduction algorithm is not good under non-stationary noise environment The effect of reducing noise is not good.The application first by improved voice activity detection audio frame is divided into speech frame, silence frame and noise frame three categories, and minimum value tracking in time-frequency domain is carried out to realize the power spectrum estimation of noise.The system further introduces noise environment change detection mechanism, dynamically assesses noise stability, and adjusts wiener filter parameter accordingly.Aiming at different types of frame and frequency point, the system dynamically optimizes filter parameter, including smoothing coefficient, gain lower limit and frequency band weight.Through this multi-level adaptive processing mechanism, the method can realize higher speech signal-to-noise ratio and clarity under complex noise environment, suitable for cochlear implant single microphone noise reduction.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Transient noise suppression-oriented real-time speech enhancement method

    CN110739005A

  • Voice signal processing method and electronic device

    WO2022160715A1