A spatial active noise reduction method based on deep learning and cylindrical harmonic decomposition

By combining pillar harmonic decomposition and deep learning, a CTN neural network is trained to predict and generate antiphase cancellation signals, solving the noise cancellation problem of feedback ANC systems in complex signal environments and achieving effective noise suppression in specific spatial regions.

CN117133262BActive Publication Date: 2026-07-07PEKING UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
PEKING UNIV
Filing Date
2023-08-01
Publication Date
2026-07-07

Smart Images

  • Figure CN117133262B_ABST
    Figure CN117133262B_ABST
Patent Text Reader

Abstract

The application discloses a kind of space active noise reduction methods based on deep learning and column harmonic decomposition, the present application is through annular microphone array, acquires noise signal;After column harmonic decomposition, the column harmonic signal that can express entire sound field is obtained;CTN neural network is trained using column harmonic signal, the time sequence modeling of column harmonic signal is realized, i.e. The application can realize the elimination of noise in a certain area.
Need to check novelty before this filing date? Find Prior Art