.png){kind=icon}
.png){kind=icon}
Return
Spatial-Frequency Cued Generative Fixed-Filter Active Noise Control Based on Deep Learning in Reverberant Environments
.png){kind=icon}
PRE
AI
B
H
D
J
Z
Z
W
DOI：10.1016/j.sigpro.2026.110682.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A spatial–frequency cued GFANC method is proposed to address the lack of spatial awareness in the vanilla GFANC method. • Theoretical analysis establishes the role of 3D spatial conditioning in optimal control filter design under reverberation. • A multi-task CRNN jointly learns 3D spatial and frequency cues, enabling accurate control filter generation in reverberant environments. • Results on simulated and measured acoustic paths confirm superior robustness and performance across diverse noise locations and spectra.
Keywords:
Spatial-Frequency Cues
Generative Fixed-Filter
Active Noise Control
Reverberant Environments
Deep Learning
Journal
IF:
3.6
Papers:
9.8K
Citations:
1.7W
Organization
Cited Papers