首页 > 论文 > 激光与光电子学进展 > 57卷 > 8期(pp:81021--1)

基于卷积神经网络的室内麦克风阵列声源定位算法

Convolutional Neural Network Based Indoor Microphone Array Sound Source Localization

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

在室内麦克风阵列声源定位算法的研究中,混响和噪声对定位精度影响很大,传统的声源定位算法无法在高混响和低信噪比的环境中保持较高的定位精度。为了解决这一问题,提出一种基于卷积神经网络的室内声源定位算法,该算法提取麦克风阵列接收信号的相位加权广义互相关函数作为训练特征,获取目标声源三维位置信息。基于NOIZEUS数据库的实验结果表明,该方法能够通过训练适应不同的声学环境,与其他基于学习的室内声源定位算法相比,其在高混响与低信噪比环境下仍具有较好的定位性能与鲁棒性,具有较大的研究和应用价值。

Abstract

For indoor sound source localization algorithm based on microphone arrays, its accuracy is greatly influenced by the reverberation and noise. Traditional sound source localization approaches cannot keep high localization accuracy in strong reverberation and low signal-to-noise ratio environments. To tackle this problem, a novel indoor sound source localization algorithm based on convolutional neural network is proposed. By extracting the phase weighted generalized cross correlation function of the received signals from microphone arrays as training feature, the three-dimensional localization information of target sound source can be obtained. Experiments based on NOIZEUS database demonstrate that the proposed algorithm can be adapted to different acoustic conditions via training. Compared with other learning based indoor sound source localization algorithms, the proposed algorithm has good localization performance and robustness in strong reverberation and low signal-to-noise ratio environment, suggesting high research and application value.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TB52+9; TN98

DOI:10.3788/LOP57.081021

所属栏目:图像处理

基金项目:国家自然科学基金;

收稿日期:2019-08-29

修改稿日期:2019-09-19

网络出版日期:2020-04-01

作者单位    点击查看

焦琛:天津大学电气自动化与信息工程学院, 天津 300072
张涛:天津大学电气自动化与信息工程学院, 天津 300072
孙建红:天津大学电气自动化与信息工程学院, 天津 300072

联系人作者:焦琛(jiaochen@tju.edu.cn)

备注:国家自然科学基金;

【1】Zhao Z, Chen W H, Semprun K A, et al. Design and evaluation of a prototype system for real-time monitoring of vehicle honking [J]. IEEE Transactions on Vehicular Technology. 2019, 68(4): 3257-3267.

【2】Shivappa S, Trivedi M, Rao B. Audiovisual information fusion in human-computer interfaces and intelligent environments: a survey [J]. Proceedings of the IEEE. 2010, 98(10): 1692-1715.

【3】Popper A N, Fay R R. Sound source localization [M]. New York: Springer-Verlag. 2005.

【4】Li X, Deng Z D, Rauchenstein L T, et al. Contributed review: source-localization algorithms and applications using time of arrival and time difference of arrival measurements [J]. Review of Scientific Instruments. 2016, 87(4): 041502.

【5】Alameda-Pineda X, Horaud R. A geometric approach to sound source localization from time-delay estimates [J]. ACM Transactions on Audio, Speech, and Language Processing. 2014, 22(6): 1082-1095.

【6】Yook D, Lee T, Cho Y. Fast sound source localization using two-level search space clustering [J]. IEEE Transactions on Cybernetics. 2016, 46(1): 20-26.

【7】Chen H W, Ser W. Acoustic source localization using LS-SVMs without calibration of microphone arrays . [C]∥2009 IEEE International Symposium on Circuits and Systems, May 24-27, 2009, Taipei, Taiwan, China. New York: IEEE. 2009, 1863-1866.

【8】Xiao X, Zhao S, Zhong X, et al. A learning-based approach to direction of arrival estimation in noisy and reverberant environments . [C]∥2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), April 19-24, 2015, Brisbane, QLD, Australia. New York: IEEE. 2015, 2814-2818.

【9】Sun Y X, Chen J J, Yuen C, et al. Indoor sound source localization with probabilistic neural network [J]. IEEE Transactions on Industrial Electronics. 2018, 65(8): 6403-6413.

【10】Hurst P J, Norrell A. DAC quantization-noise cancellation in an echo-canceling transceiver [J]. IEEE Transactions on Circuits and Systems II: Express Briefs. 2008, 55(2): 111-115.

【11】Prodeus A M. Performance measures of noise reduction algorithms in voice control channels of UAVs . [C]∥2015 IEEE International Conference Actual Problems of Unmanned Aerial Vehicles Developments (APUAVD), October 13-15, 2015, Kiev, Ukraine. New York: IEEE. 2015, 189-192.

【12】Zhang Y S, Yang G W, Wang Q Q, et al. Weld feature extraction based on fully convolutional networks [J]. Chinese Journal of Lasers. 2019, 46(3): 0302002.
张永帅, 杨国威, 王琦琦, 等. 基于全卷积神经网络的焊缝特征提取 [J]. 中国激光. 2019, 46(3): 0302002.

【13】Wang W X, Fu Y T, Dong F, et al. Infrared ship target detection method based on deep convolution neural network [J]. Acta Optica Sinica. 2018, 38(7): 0712006.
王文秀, 傅雨田, 董峰, 等. 基于深度卷积神经网络的红外船只目标检测方法 [J]. 光学学报. 2018, 38(7): 0712006.

【14】Wang S Y, Tao S X, Yang F, et al. Laser range-gated imaging target recognition based on convolutional neural network [J]. Laser & Optoelectronics Progress. 2019, 56(2): 021001.
王书宇, 陶声祥, 杨钒, 等. 基于卷积神经网络的激光距离选通式成像目标识别 [J]. 激光与光电子学进展. 2019, 56(2): 021001.

【15】Patil U G, Shirbahadurkar S D. Performance analysis of SS based speech enhancement algorithms for ASR with non-stationary noisy database-NOIZEUS . I-SMAC) I-SMAC (IoT in Social, Mobile, Analytics and Cloud. 2018, 636-641.

【16】Alien J B, Berkley D A. Image method for efficiently simulating small‐room acoustics [J]. The Journal of the Acoustical Society of America. 1976, 60(S1): S9.

【17】Yang X, Xing H Y, Zhang J, et al. Performance analysis of sound source localization algorithm based on seven-element microphone array [J]. Chinese Journal of Sensors and Actuators. 2019, 32(7): 1034-1039.
杨旭, 行鸿彦, 张军, 等. 基于七元传声器阵列的声源定位算法及性能分析 [J]. 传感技术学报. 2019, 32(7): 1034-1039.

【18】Knapp C, Carter G. The generalized correlation method for estimation of time delay [J]. IEEE transactions on acoustics, speech, and signal processing. 1976, 24(4): 320-327.

引用该论文

Jiao Chen,Zhang Tao,Sun Jianhong. Convolutional Neural Network Based Indoor Microphone Array Sound Source Localization[J]. Laser & Optoelectronics Progress, 2020, 57(8): 081021

焦琛,张涛,孙建红. 基于卷积神经网络的室内麦克风阵列声源定位算法[J]. 激光与光电子学进展, 2020, 57(8): 081021

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF