CicadaNet: Deep learning based automatic cicada chorus filtering for improved long-term bird monitoring
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 spe...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-01-01
|
| Series: | Ecological Indicators |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1470160X23015650 |
| _version_ | 1797378787264954368 |
|---|---|
| author | Chengyun Zhang Nengting Jin Jie Xie Zezhou Hao |
| author_facet | Chengyun Zhang Nengting Jin Jie Xie Zezhou Hao |
| author_sort | Chengyun Zhang |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-08T20:12:40Z |
| format | Article |
| id | doaj.art-fec54f9a9a244d2a8b58e7f3f425ac37 |
| institution | Directory Open Access Journal |
| issn | 1470-160X |
| language | English |
| last_indexed | 2024-03-08T20:12:40Z |
| publishDate | 2024-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Ecological Indicators |
| spelling | doaj.art-fec54f9a9a244d2a8b58e7f3f425ac372023-12-23T05:20:16ZengElsevierEcological Indicators1470-160X2024-01-01158111423CicadaNet: Deep learning based automatic cicada chorus filtering for improved long-term bird monitoringChengyun Zhang0Nengting Jin1Jie Xie2Zezhou Hao3School of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Electronics and Communication Engineering, Guangzhou University, Guangzhou 510006, ChinaSchool of Computer and Electronic Information and School of Artificial Intelligence, Nanjing Normal University, Nanjing 210046, China; Key Laboratory of Modern Acoustics, MOE, Nanjing University, Nanjing 210032, China; Corresponding author at: School of Computer and Electronic Information and School of Artificial Intelligence, Nanjing Normal University, Nanjing 210046, China.Research Institute of Tropical Forestry, Chinese Academy of Forestry, Guangzhou 510520, ChinaPassive 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.http://www.sciencedirect.com/science/article/pii/S1470160X23015650Passive acoustic monitoringNoise filteringDeep learningAcoustic indexBiodiversity |
| spellingShingle | Chengyun Zhang Nengting Jin Jie Xie Zezhou Hao CicadaNet: Deep learning based automatic cicada chorus filtering for improved long-term bird monitoring Ecological Indicators Passive acoustic monitoring Noise filtering Deep learning Acoustic index Biodiversity |
| title | CicadaNet: Deep learning based automatic cicada chorus filtering for improved long-term bird monitoring |
| title_full | CicadaNet: Deep learning based automatic cicada chorus filtering for improved long-term bird monitoring |
| title_fullStr | CicadaNet: Deep learning based automatic cicada chorus filtering for improved long-term bird monitoring |
| title_full_unstemmed | CicadaNet: Deep learning based automatic cicada chorus filtering for improved long-term bird monitoring |
| title_short | CicadaNet: Deep learning based automatic cicada chorus filtering for improved long-term bird monitoring |
| title_sort | cicadanet deep learning based automatic cicada chorus filtering for improved long term bird monitoring |
| topic | Passive acoustic monitoring Noise filtering Deep learning Acoustic index Biodiversity |
| url | http://www.sciencedirect.com/science/article/pii/S1470160X23015650 |
| work_keys_str_mv | AT chengyunzhang cicadanetdeeplearningbasedautomaticcicadachorusfilteringforimprovedlongtermbirdmonitoring AT nengtingjin cicadanetdeeplearningbasedautomaticcicadachorusfilteringforimprovedlongtermbirdmonitoring AT jiexie cicadanetdeeplearningbasedautomaticcicadachorusfilteringforimprovedlongtermbirdmonitoring AT zezhouhao cicadanetdeeplearningbasedautomaticcicadachorusfilteringforimprovedlongtermbirdmonitoring |