文献类型：期刊文献

英文题名：CicadaNet: Deep learning based automatic cicada chorus filtering for improved long-term bird monitoring

作者：Zhang, Chengyun[1] Jin, Nengting[1] Xie, Jie[2,3,4] Hao, Zezhou[5]

第一作者：Zhang, Chengyun

通信作者：Xie, J[1];Xie, J[2]

机构：[1]Guangzhou Univ, Sch Elect & Commun Engn, Guangzhou 510006, Peoples R China;[2]Nanjing Normal Univ, Sch Comp & Elect Informat, Nanjing 210046, Peoples R China;[3]Nanjing Normal Univ, Sch Artificial Intelligence, Nanjing 210046, Peoples R China;[4]Nanjing Univ, Key Lab Modern Acoust, MOE, Nanjing 210032, Peoples R China;[5]Chinese Acad Forestry, Res Inst Trop Forestry, Guangzhou 510520, Peoples R China

年份：2024

卷号：158

外文期刊名：ECOLOGICAL INDICATORS

收录：;Scopus(收录号：2-s2.0-85180549518);WOS:【SCI-EXPANDED(收录号:WOS:001143972800001)】；

基金：This work is funded by the National Natural Science Foundation of China (No.32171520 and No.32371556) and the Research Project of the Education Bureau of Guangzhou (No.202032882) . This work is also supported by the Fundamental Research Funds for the Central Univer- sities (grants No.020414380195) . We thank Guangzhou Naturesense Ecological Technology Corporation for providing the data of Chenhe- dong Nature Reserve, and thank Keyi Wu for his kind help in providing the acoustic event detection procedure.

语种：英文

外文关键词：Passive acoustic monitoring; Noise filtering; Deep learning; Acoustic index; Biodiversity

摘要：Passive acoustic monitoring has been an effective tool for bird sound analysis. However, bird sounds often include cicada noise, which is an obstacle for investigating bird sounds. For example, cicada noise can result in large deviations of acoustic index, which will lead to the mismonitoring of species richness trends. Therefore, there is a critical need to filter cicada noise for helping bird sound analysis. We develop a novel end-to-end deep learning model, named CicadaNet for filtering cicada chorus from recordings containing bird sound. CicadaNet utilizes a convolutional encoder-decoder network to encode and decode acoustic features and a conformer module for global and local sequence modeling. We build a clean bird sound dataset and collect a large amount of real cicada noise data for model evaluation. We compare CicadaNet with current state-of-the-art deep denoising models and traditional denoising algorithms. Experimental results show that CicadaNet achieves the best denoising performance (SegSNR is improved by 9.59 dB and SI-SNR is improved by 20.08 dB when the noisy SNR = 0 dB). Meanwhile, CicadaNet achieves good performance for the real-time denoising of cicada noise. Furthermore, CicadaNet achieves bird species-independent noise reduction. We evaluate the effectiveness of CicadaNet for bird diversity survey. CicadaNet achieves the best performance, which can effectively eliminate the deviation caused by cicada noise to the acoustic index. CicadaNet can be easily extended to the cancellation of other environmental noise, and we propose it for the acoustic denoising of other vocalizing animals.