This is the code of my ICASSP2023 paper "Generative Fixed filter Active Noise Control based on Deep Learning". You can find the paper at https://arxiv.org/pdf/2208.08082.pdf or at IEEE Xplore.
To obtain more appropriate control filters for differen primary noises, a generative fixed-filter active noise control (GFANC) approach is proposed in this paper. Specifically, various control filters can be generated by using different hard weights to combine sub control filters. The hard weights are automatically obtained via a one-dimensional convolutional neural network given the incoming noise.
How to use the code:
we have provided the trained 1D CNN model, you can easily run the "Noise_Cancellation_GFANC.ipynb" file to get the noise reduction results. The real noises in our experiemnts are provided in "Real Noise Examples". The 1D CNN is trained using a synthetic noise dataset, its label file is 'Hard_Index.csv'. The entire dataset is available at https://drive.google.com/file/d/1hs7_eHITxL16HeugjQoqYFTs-Cm7J-Tq/view?usp=sharing
Especially, the pre-trained sub control filters are obtained on synthetic acoustic paths, where the primary and secondary paths are bandpass filters. If you want to use the GFANC method on new acoustic paths only requires obtaining the corresponding broadband control filter and decomposing it into sub control filters. Noticeably, the trained 1D CNN in the GFANC method can remain unchanged.
Platform: NVIDIA-SMI 466.47, Driver Version: 466.47, CUDA Version: 11.3 Environment: Jupyter Notebook 6.4.5, Python 3.9.7, Pytorch 1.10.1
RELATED PAPERS:
- Deep Generative Fixed-Filter Active Noise Control
- Delayless Generative Fixed-filter Active Noise Control based on Deep Learning and Bayesian Filter
- GFANC-Kalman: Generative Fixed-Filter Active Noise Control with CNN-Kalman Filtering
- A hybrid sfanc-fxnlms algorithm for active noise control based on deep learning
- Performance Evaluation of Selective Fixed-filter Active Noise Control based on Different Convolutional Neural Networks
- If you are interested in this work, you can read and cite our papers. Thanks!