双解码卷积循环网络风噪声有源控制
作者:
作者单位:

南京信息工程大学

基金项目:

国家自然科学基金项目


Active control of wind noise with dual-decoder convolutional recurrent network
Author:
Affiliation:

1.Nanjing University of Information Science &2.Technology;3.amp

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • | |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    本文提出了一种利用双解码卷积循环网络(Dual-decoder Convolutional Recurrent Network, DCRN)代替FxLMS(Filtered-x Least Mean Square)算法的有源噪声控制方法,考虑到相位信息在有源噪声控制中的重要性,DCRN网络的输入特征为噪声信号的复数频谱(包括实部谱和虚部谱)。网络结构中采用编码模块从噪声复频谱中提取特征,利用双解码模块分别估计网络输出的实部谱和虚部谱,采用了参数共享机制和组策略以降低训练参数的数量并提高网络的学习能力和泛化能力。特别是针对风噪声,选用了新的损失函数和对训练数据进行正则化处理以提升DCRN的性能。实验表明,DCRN方法在仿真环境与有源降噪耳机环境下对一般噪声和风噪声都表现出良好的降噪性能和鲁棒性。

    Abstract:

    An active noise control (ANC) method is introduced which replaces filtered-x least mean square (FxLMS) algorithm with Dual-Decoder Convolutional Recurrent Network (DCRN). Due to the importance of phase information in ANC, the input feature of the DCRN is the complex spectrogram of the noise signal (including the real and imaginary spectrograms). In the network structure, a coding module is used to extract features from the noise complex spectrograms, and a dual-decoder module is used to estimate the real and imaginary spectrograms of the network output respectively. Parameter sharing mechanism and group strategy are adopted to reduce the number of training parameters and improve the learning ability and generalization ability. Especially for wind noise, a new loss function is selected and the training data is regularized to improve the performance of DCRN. The experiments in both simulation and ANC headphone environments show that the DCRN method exhibits good noise reduction performance and robustness for general noise and wind noise.

    参考文献
    [1] 张晓宇, 仪垂杰. 主、被动噪声控制的实验研究[J]. 噪声与振动控制,2011,31(03):145-148.hang Xiaoyu, Yi Chujie. Experimental study on active and passive noise control[J].Noise and Vibration Control,2011,31(03):145-148.
    [2] 吴礼福, 陈晶晶, 郭业才. 调节水床效应的双梯度有源噪声控制自适应算法[J]. 应用声学,2020,39(4):632-637.u Lifu, Chen Jingjing, Guo Yecai.Adaptive double-gradient active noise control algorithms for tuning waterbed effect[J].Journal of Applied Acoustics, 2020, 39(4): 632-637.
    [3] Schumacher T, Krüger H, Jeub M, et al. Active noise control in headsets: A new approach for broadband feedback ANC[C]//2011 IEEE International conference on acoustics, speech and signal processing (ICASSP). IEEE, 2011: 417-420.
    [4] Chang C Y, Li S T. Active noise control in headsets by using a low-cost microcontroller[J]. IEEE Transactions on industrial electronics, 2010, 58(5): 1936-1942.
    [5] Bradley S, Wu T, Hunerbein S V. The Mechanisms Creating Wind Noise in Microphones[J]. Audio Engineering Society, 2010.
    [6] Mirabilii D, Lodermeyer A, Czwielong F, et al. Simulating Wind Noise with Airflow Speed-Dependent Characteristics[C]//2022 International Workshop on Acoustic Signal Enhancement (IWAENC). IEEE, 2022: 1-5.
    [7] 赖小强, 李双田. 双传声器系统中的风噪抑制方法研究[J]. 信号处理,2013,29(4):7.ai Xiaoqiang, Li Shuangtian. Research on wind noise suppression method in dual microphone system[J].Signal Processing,2013,29(4):7.
    [8] Fisol U, Ripin Z M, Ismail N A, et al. Wind noise analysis of a two-way radio[C]// IEEE International Conference on Smart Instrumentation. IEEE, 2014.
    [9] King B, Atlas L. COHERENT MODULATION COMB FILTERING FOR ENHANCING SPEECH IN WIND NOISE. 2008.
    [10] 张程, 潘翔. 基于风噪声抑制的语音信号增强研究[J]. 信号处理在地球物理——浙江省信号处理学会2018年学术年会论文集,2018.hang Cheng, Pan Xiang. Research on speech signal enhancement based on wind noise suppression[J]. Signal Processing in Geophysics——Proceedings of the 2018 Annual Conference of Zhejiang Signal Processing Society, 2018.
    [11] Boll, S. Suppression of acoustic noise in speech using spectral subtraction. IEEE Trans. ASSP, ASSP-27(2): 113-120[J]. IEEE Transactions on Acoustics Speech Signal Processing, 1979, 27(2):113-120.
    [12] Chu Y, Zhao S, He L, et al. Wind noise suppression in filtered-x least mean squares-based active noise control systems[J]. The Journal of the Acoustical Society of America, 2022, 152(6): 3340-3345.
    [13] 吴睿, 金向锋. 抑制风噪装置的实验[J]. 应用声学,2022,41(06):1010-1015.u Rui, Jin Xiangfeng. Experiment on wind noise suppression device[J]. Journal of Applied Acoustics,2022,41(06):1010-1015.
    [14] 潘作峰, 邓玉伟, 郝耀东, 等. 动态密封状态下汽车风噪性能不确定性研究[J]. 汽车工程, 2021, 43(11): 1645-1652.an Zuofeng, Deng Yuwei, Hao Yaodong, et al. Study on uncertainty of automobile wind noise performance under dynamic sealing state[J]. Automotive Engineering, 2021, 43(11): 1645-1652.
    [15] Jiang Y, Liu H, Zhou Y, et al. An Integration Development of Traditional Algorithm and Neural Network for Active Noise Cancellation[C]//2022 IEEE 32nd International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 2022: 1-6.
    [16] Mostafavi A, Cha Y J. Deep learning-based active noise control on construction sites[J]. Automation in Construction, 2023, 151: 104885.
    [17] Im, Seonghun, et al. "Deep learning-assisted active noise control in a time-varying environment."Journal of Mechanical Science and Technology37.3 (2023): 1189-1196.
    [18] Cha, Young-Jin, Alireza Mostafavi, and Sukhpreet S. Benipal. "DNoiseNet: Deep learning-based feedback active noise control in various noisy environments."Engineering Applications of Artificial Intelligence121 (2023): 105971.
    [19] Zhang H, Wang D L. Deep ANC: A deep learning approach to active noise control[J]. Neural Networks, 2021, 141: 1-10.
    [20] Kwon S, Kim B S, Park J. Active Noise Reduction with Filtered Least-Mean-Square Algorithm Improved by Long Short-Term Memory Models for Radiation Noise of Diesel Engine[J]. Applied Sciences, 2022, 12(20): 10248.
    [21] Tan K, Wang D L. Complex spectral mapping with a convolutional recurrent network for monaural speech enhancement[C]//ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2019: 6865-6869.
    [22] 郭佳丽,邢双云,栾昊等.基于改进的LSTM算法的时间序列流量预测[J].南京信息工程大学学报(自然科学版),2021,13(05):571-575.DOI:10.13878/j.cnki.jnuist.2021.05.009.br />Guo Jiali, Xing Shuangyun, Luan Hao, etc. Time Series Traffic Forecasting Based on Improved LSTM Algorithm [J]. Journal of Nanjing University of Information Technology (Natural Science Edition), 2021,13(05):571-575.DOI:10.13878/j .cnki.jnuist.2021.05.009.
    [23] 韩莹,管健,曹允重等.LSTM-WBLS模型在日降水量预测中的应用[J].南京信息工程大学学报(自然科学版),2023,15(02):180-186.DOI:10.13878/j.cnki.jnuist.2023.02.006.br />Han Ying, Guan Jian, Cao Yunzhong, etc. Application of LSTM-WBLS Model in Daily Precipitation Prediction[J]. Journal of Nanjing University of Information Technology (Natural Science Edition), 2023,15(02):180-186.DOI:10.13878 /j.cnki.jnuist.2023.02.006.
    [24] Park, Se Rim, and Jinwon Lee. "A fully convolutional neural network for speech enhancement."arXiv preprint arXiv:1609.07132(2016).
    [25] Ideas S. Series 6000 general sound effects library[J]. Sound Effect Library.
    [26] Varga A, Steeneken H J M. Assessment for automatic speech recognition: II. NOISEX-92: A database and an experiment to study the effect of additive noise on speech recognition systems[J]. Speech communication, 1993, 12(3): 247-251.
    [27] Nelke C M, Vary P. Measurement, analysis and simulation of wind noise signals for mobile communication devices[C]// International Workshop on Acoustic Signal Enhancement. IEEE, 2014.
    [28] RWTH Aachen University, Institute of Communication Systems and Data Processing (IND).Christoph Nelke. (2014). "Wind Noise Database". [EB/OL]. Available: nelke@ind.rwth-aachen.de. (Accessed: 2023-06-18).
    [29] Allen J B, Berkley D A. Image method for efficiently simulating small‐room acoustics[J]. The Journal of the Acoustical Society of America, 1979, 65(4): 943-950.
    [30] Breining C, Dreiscitel P, Hansler E, et al. Acoustic echo control. An application of very-high-order adaptive filters[J]. IEEE signal processing Magazine, 1999, 16(4): 42-69.
    [31] Reddi S J, Kale S, Kumar S. On the convergence of adam and beyond[J]. arXiv preprint arXiv:1904.09237, 2019.
    [32] thop PyPI. https://pypi.org/project/thop/. (Accessed: 2023-07-20).2
    相似文献
    引证文献
    引证文献 [0]
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

吴礼福,葛文昌,陈 晨,王绍博.双解码卷积循环网络风噪声有源控制[J].南京信息工程大学学报,,():

复制
分享
文章指标
  • 点击次数:182
  • 下载次数: 0
  • HTML阅读次数: 0
  • 引用次数: 0
历史
  • 收稿日期:2023-08-18
  • 最后修改日期:2023-11-13
  • 录用日期:2023-11-14

地址:江苏省南京市宁六路219号    邮编:210044

联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2025 版权所有  技术支持:北京勤云科技发展有限公司