Page 170 - 《应用声学》2023年第4期

832 2023 年 7 月

2022, 50(2): 129–136.
Qiu Zhibin, Lu Zuwen, Wang Haiyang, et al. Recognition
参 考 文 献 of bird sounds related to power grid faults based on mel
spectrogram and convolutional neural network[J]. Journal
[1] 赵洪峰, 雷富民. 鸟类用于环境监测的意义及研究进展 [J]. 动 of South China University of Technology(Natural Science
物学杂志, 2002(6): 74–78. Edition), 2022, 50(2): 129–136.
Zhao Hongfeng, Lei Fumin. Birds as monitors of environ- [11] Liu H, Liu C, Zhao T, et al. Bird song classification based
mental change[J]. Chinese Journal of Zoology, 2002(6): on improved Bi-LSTM-DenseNet network[C]//2021 4th
74–78. International Conference on Robotics, Control and Au-
[2] 吴伟伟, 徐海根, 吴军. 气候变化对鸟类影响的研究进展 [J]. tomation Engineering (RCAE). 2021: 152–155.
生物多样性, 2012, 20(1): 108–115. [12] Zhao M, Zhong S, Fu X, et al. Deep residual shrinkage
Wu Weiwei, Xu Haigen, Wu Jun. The impact of climate networks for fault diagnosis[J]. IEEE Transactions on In-
change on birds: a review[J]. Biodiversity Science, 2012, dustrial Informatics, 2020, 16(7): 4681–4690.
20(1): 108–115. [13] Woo S, Park J, Lee J Y, et al. CBAM: convolutional block
[3] 徐淑正, 孙忆南, 皇甫丽英, 等. 基于 MFCC 和时频图等多 attention module[M]. Berlin: Springer, 2018: 3–19.
种特征的综合鸟声识别分类器设计 [J]. 实验室研究与探索, [14] Wang Q, Wu B, Zhu P, et al. ECA-Net: efficient chan-
2018, 37(9): 81–86, 91. nel attention for deep convolutional neural networks[C]//
Xu Shuzheng, Sui Yinan, Haungfu Liying, et al. Design of 2020 IEEE/CVF Conference on Computer Vision and
synthesized bird sounds classifier based on multi feature Pattern Recognition (CVPR). IEEE, 2020: 11531–11539.
extraction classifiers and time-frequency chat[J]. Research [15] Yu F, Koltun V. Multi-scale context aggregation by
and Exploration in Laboratory, 2018, 37(9): 81–86, 91. dilated convolutions[C]// International Conference on
[4] 张赛花. 面向鸟声传感网的鸟鸣自动分类方法研究 [D]. 南京: Learning Representations (ICLR), 2016.
南京理工大学, 2018. [16] He K, Zhang X, Ren S, et al. Deep residual learning for
[5] Cakir E, Adavanne S, Parascandolo G, et al. Convo- image recognition[J]. 2016 IEEE Conference on Computer
lutional recurrent neural networks for bird audio detec- Vision and Pattern Recognition (CVPR), 2016: 770–778.
tion[C]. 2017 25th European Signal Processing Conference [17] Meng H, Yan T, Yuan F, et al. Speech emotion recog-
(EUSIPCO). IEEE, 2017: 1744–1748. nition from 3D Log-Mel spectrograms with deep learning
[6] 冯郁茜. 基于深度学习的双模态特征融合鸟类物种识别算 network[J]. IEEE Access, 2019. 7: 125868–125881.
法 [D]. 北京: 北京林业大学, 2019. [18] Chen M, He X, Jing Y, et al. 3-D convolutional recur-
[7] Naranchimeg B, Zhang C, Akashi T. Cross-domain deep rent neural networks with attention model for speech emo-
feature combination for bird species classification with tion recognition[J]. IEEE Signal Processing Letters, 2018,
audio-visual data[J]. IEICE Transactions on Information 25(10): 1440–1444.
and Systems, 2019, E102. D(10): 2033–2042. [19] Hu J, Shen L, Albanie S, et al. Squeeze-and-excitation
[8] 谢将剑, 杨俊, 邢照亮, 等. 多特征融合的鸟类物种识别方 networks[J]. IEEE Transactions on Pattern Analysis and
法 [J]. 应用声学, 2020, 39(2): 199–206. Machine Intelligence, 2017, 44(8): 2011–2023.
Xie Jiangjian,Yang Jun, Xing Zhaoliang, et al. Bird [20] Hochreiter S, Schmidhuber J. Long short-term memory[J].
species recognition method based on multi-feature fu- Neural Computation, 1997, 9(8): 1735–1780.
sion[J]. Journal of Applied Acoustics, 2020, 39(2): 199– [21] Jiang P, Fu H, Tao H, et al. Parallelized convolu-
206. tional recurrent neural network with spectral features
[9] Puget J. STFT transformers for bird song recogni- for speech emotion recognition[J]. IEEE Access, 2019, 7:
tion[C]//2021 Conference and Labs of the Evaluation Fo- 90368–90377.
rum(CLEF). Bucharest, Romania, 2021: 21–29. [22] 北京智源人工智能研究院. Birdsdata 数据集 [DB/OL]. [2021-
[10] 邱志斌, 卢祖文, 王海祥, 等. 基于 Mel 频谱图和 CNN 的电 03-10]. http://open.baai.ac.cn/data-set-detail/MTI2NDg=
网涉鸟故障鸟声识别 [J]. 华南理工大学学报 (自然科学版), /NjQ=/true.