Page 40 - 《应用声学》2021年第4期

524 2021 年 7 月

Cheng Yusheng, Zhang Baohua, Gao Xin, et al. Phase- 1603.08029, 2016.
coupling characteristics of ship radiated-noise demodula- [10] Iandola F, Moskewicz M, Karayev S, et al. Densenet: im-
tion spectrum and application[J]. Acta Acustica, 2013, plementing efficient convnet descriptor pyramids[J]. arXiv
32(1): 36–36. preprint, arXiv: 1404.1869, 2014.
[3] Leal N, Leal E, Sanchez G. Marine vessel recognition by [11] Simonyan K, Zisserman A. Very deep convolutional net-
acoustic signature[J]. ARPN Journal of Engineering and works for large-scale image recognition[J]. arXiv preprint,
Applied Sciences, 2015, 10(20): 9633–9639. arXiv: 1409.1556, 2014.
[4] Wang W, Li S, Yang J, et al. Feature extraction [12] Krizhevsky A, Sutskever I, Hinton G E. Imagenet
of underwater target in auditory sensation area based classification with deep convolutional neural net-
on MFCC[C]//2016 IEEE/OES China Ocean Acoustics works[C]//Advances in Neural Information Processing
(COA). IEEE, 2016: 1–6. Systems, 2012: 1097–1105.
[5] 张少康, 田德艳. 水下声目标的梅尔倒谱系数智能分类方 [13] McDonnell M D, Gao W. Acoustic scene classification us-
法 [J]. 应用声学, 2019, 38(2): 267–272. ing deep residual networks with late fusion of separated
Zhang Shaokang, Tian Deyan. Intelligent classification high and low frequency paths[C]//ICASSP 2020–2020
method of Mel frequency cepstrum coefficient for under- IEEE International Conference on Acoustics, Speech and
water acoustic targets[J]. Journal of Applied Acoustics, Signal Processing (ICASSP). IEEE, 2020: 141–145.
2019, 38(2): 267–272. [14] Koutini K, Eghbal-Zadeh H, Dorfer M, et al. The recep-
[6] Zhao Z Q, Zheng P, Xu S, et al. Object detection tive field as a regularizer in deep convolutional neural net-
with deep learning: a review[J]. IEEE Transactions on works for acoustic scene classification[C]//2019 27th Eu-
Neural Networks and Learning Systems, 2019, 30(11): ropean signal processing conference (EUSIPCO). IEEE,
3212–3232. 2019: 1–5.
[7] Kamal S, Mujeeb A, Supriya M H. Novel class detec- [15] Park D S, Chan W, Zhang Y, et al. Specaugment: a
tion of underwater targets using self-organizing neural simple data augmentation method for automatic speech
networks[C]//2015 IEEE Underwater Technology (UT). recognition[J]. arXiv preprint, arXiv: 1904.08779, 2019.
IEEE, 2015: 1–5. [16] McFee B, Raffel C, Liang D, et al. Librosa: audio and mu-
[8] 王强, 曾向阳. 深度学习方法及其在水下目标识别中的应 sic signal analysis in python[C]//Proceedings of the 14th
用 [C]// 中国声学学会水声学分会 2015 年学术会议论文集, Python in Science Conference, 2015, 8: 18–25.
2015. [17] Santos-Domínguez D, Torres-Guijarro S, Cardenal-López
[9] Targ S, Almeida D, Lyman K. Resnet in resnet: gen- A, et al. ShipsEar: an underwater vessel noise
eralizing residual architectures[J]. arXiv preprint, arXiv: database[J]. Applied Acoustics, 2016, 113: 64–69.