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.
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
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.
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.
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.
Smart Images

Figure CN121905138B_ABST
Abstract
Citation Information
Patent Citations
Transient noise suppression-oriented real-time speech enhancement method
CN110739005A
Voice signal processing method and electronic device
WO2022160715A1