湿地声景录音策略及面向声景分类的特征选择

doi:10.17520/biods.2024121

生物多样性 ›› 2024, Vol. 32 ›› Issue (10): 24121. DOI: 10.17520/biods.2024121 cstr: 32101.14.biods.2024121

• 技术与方法 • 下一篇

湿地声景录音策略及面向声景分类的特征选择

胡婉君¹, 郝泽周²(), 夏灿玮³(), 谢将剑¹^,⁴^,⁵^,^*()()

1.北京林业大学工学院, 北京 100083
2.中国林业科学研究院热带林业研究所, 广州 510520
3.生物多样性与生态工程教育部重点实验室, 北京师范大学生命科学学院, 北京 100875
4.林木资源高效生产全国重点实验室, 北京 100083
5.北京林业大学生物多样性智慧监测研究中心, 北京 100083

收稿日期:2024-03-30 接受日期:2024-05-28 出版日期:2024-10-20 发布日期:2024-07-16
通讯作者: *E-mail: shyneforce@bjfu.edu.cn
基金资助:
国家自然科学基金(62303063)

Wetland soundscape recording scheme and feature selection for soundscape classification

Wanjun Hu¹, Zezhou Hao²(), Canwei Xia³(), Jiangjian Xie¹^,⁴^,⁵^,^*()()

1. School of Technology, Beijing Forestry University, Beijing 100083, China
2. Research Institute of Tropical Forestry, Chinese Academy of Forestry, Guangzhou 510520, China
3. Ministry of Education Key Laboratory for Biodiversity Science and Ecological Engineering, College of Life Sciences, Beijing Normal University, Beijing 100875, China
4. State Key Laboratory of Efficient Production of Forest Resources, Beijing 100083, China
5. Research Center for Biodiversity Intelligent Monitoring, Beijing Forestry University, Beijing 100083, China

Received:2024-03-30 Accepted:2024-05-28 Online:2024-10-20 Published:2024-07-16
Contact: *E-mail: shyneforce@bjfu.edu.cn
Supported by:
National Natural Science Foundation of China(62303063)

摘要/Abstract

摘要：

声景描述了生物多样性、人类活动和其他声音的空间和时间模式, 反映了重要的人为和生态过程。声景分类不仅有助于提升不同声景成分计算分析的准确率, 还有助于深入了解不同声音的特点和分布, 从而为保护和改善生态环境提供依据。然而, 被动声学设备采集的大量录音数据给声景数据的分析带来困难。为平衡采样数据量与采样成本之间的矛盾, 有必要探索一种高效的录音策略, 满足声景分类研究的需要。本研究以北京野鸭湖湿地公园的录音数据为研究对象, 在不同录音策略下对比了7个声学指数(声学复杂度指数(acoustic complexity index, ACI)、声学多样性指数(acoustic diversity index, ADI)、声学均匀度指数(acoustic evenness index, AEI)、生物声学指数(bioacoustic index, BIO)、声熵指数(acoustic entropy index, H)、振幅包络线中值(median of the amplitude envelope, M)和标准化声景差异指数(normalized difference sound index, NDSI))和BYOL-A (bootstrap your own latent for audio)特征的表现, 探索适合声景分类(生物声、地理声、人工声)的录音策略及声学特征。结果表明: (1)每小时均匀采集10个1 min的子样本可以较好地平衡数据量与成本之间的矛盾(Spearman相关系数ρ > 0.9); (2)描述声景的多个声学指数中, ACI和H是最稳定的指标; (3) BYOL-A特征比声学指数能更有效地完成声景分类。合适的录音策略和高性能的深度学习特征——BYOL-A特征能够快速捕捉声景信息, 有助于提高声景分类的准确率。本研究结果可为声景数据采集和声学特征选择提供参考依据。

关键词: 湿地, 声景分类, 声学指数, 自监督学习, 声学监测

Abstract

Aims: Soundscape describes the spatial and temporal patterns of biodiversity, human activities, and other sounds, reflecting important anthropogenic and ecological processes. Soundscape classification not only helps improve the accuracy of calculating and analyzing different soundscape components, but also helps researchers gain a deeper understanding of the characteristics and distribution of different sounds, thus providing a basis for protecting and improving the ecological environment by offering a deeper understanding of species composition in an ecosystem. However, the large number of recordings collected by passive acoustic devices poses difficulties in analyzing soundscape data. This study aims to explore an efficient recording scheme that balances the amount of sampling data with the sampling cost to achieve the most productive outcome for soundscape classification research.

Methods: This study takes the recording data of Yeyahu Wetland Park of Beijing as the research object, compares the performance of seven acoustic indices (acoustic complexity index (ACI), acoustic diversity index (ADI), acoustic evenness index (AEI), bioacoustic index (BIO), acoustic entropy index (H), median of the amplitude envelope (M), normalized difference sound index (NDSI)) and BYOL-A (bootstrap your own latent for audio) features by different recording schemes, and explores appropriate recording schemes and acoustic features for soundscape classification (biophony, geophony, anthrophony).

Results: (1) Uniformly collecting 10 1-min sub-samples per hour could effectively capture soundscape information and balances data volume and cost (Spearman correlation coefficient ρ > 0.9). (2) Among the multiple acoustic indices, ACI and H were the most stable indices. (3) BYOL-A features were more effective in completing soundscape classification than acoustic indices.

Conclusion: Appropriate recording scheme and high-performance deep learning features such as BYOL-A features can quickly capture soundscape information and help improve the accuracy of soundscape classification. This study is expected to provide a guideline for soundscape data collection and acoustic feature selection in future research.

Key words: wetland, soundscape classification, acoustic indices, self-supervised learning, acoustic monitoring

胡婉君, 郝泽周, 夏灿玮, 谢将剑 (2024) 湿地声景录音策略及面向声景分类的特征选择. 生物多样性, 32, 24121. DOI: 10.17520/biods.2024121.

Wanjun Hu, Zezhou Hao, Canwei Xia, Jiangjian Xie (2024) Wetland soundscape recording scheme and feature selection for soundscape classification. Biodiversity Science, 32, 24121. DOI: 10.17520/biods.2024121.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.biodiversity-science.net/CN/10.17520/biods.2024121

https://www.biodiversity-science.net/CN/Y2024/V32/I10/24121

图/表 10

图1 北京野鸭湖湿地公园录音点布设

Fig. 1 Recording site layout of Yeyahu Wetland Park of Beijing

表1 本研究使用的7个声学指数介绍

Table 1 Seven acoustic indices used in this study

声学指数 Acoustic indices	计算公式 Computing formula	描述 Description	参考文献 Reference
声学复杂度指数 Acoustic complexity index (ACI)	$D / ∑ I k$	相邻频段窗口音量的变化; D为相邻频段音量差的累积; I_k为各频段的音量 Difference in amplitude among samples; D is summary of intensity difference among adjacent frequency bands ; I_k is intensity in a single frequency band	Pieretti et al, 2011
声学多样性指数 Acoustic diversity index (ADI)	$∑ p i × log p i$	基于Shannon指数量化音量在不同频段的分布; p_i是每个频率区间的相对强度 Spectral complexity based on Shannon index; p_i is relative intensity in each frequency band	Villanueva-Rivera et al, 2011
声学均匀度指数 Acoustic evenness index (AEI)	$Gini(I)$	基于Gini指数量化音量在不同频段的分布; I是音量 Gini coefficient with intensity at each frequency band; I is intensity	Villanueva-Rivera et al, 2011
生物声学指数 Bioacoustic index (BIO)	$∑ I k$	特定频段音量的汇总; I_k为各频段的音量 Sum of intensity in particular frequency band; I_k is intensity in a single frequency band	Boelman et al, 2007
声熵指数 Acoustic entropy index (H)	$H t × H f$	时间熵(H_t)和频谱熵(H_f)的乘积 Product of time entropy (H_t) and spectral entropy (H_f)	Sueur et al, 2008
振幅包络线中值 Median of the amplitude envelope (M)	$Median A k$	声音振幅包络值的中值; A_k是振幅包络值 Median of the amplitude envelope value; A_k is amplitude envelope value	Depraetere et al, 2012
标准化声景差异指数 Normalized difference sound index (NDSI)	$b − a b + a$	生物产生音量(b)与人类产生音量(a)的比率 Ratio of amplitude in biophony (b) and anthrophony (a)	Kasten et al, 2012

表1 本研究使用的7个声学指数介绍

Table 1 Seven acoustic indices used in this study

声学指数 Acoustic indices	计算公式 Computing formula	描述 Description	参考文献 Reference
声学复杂度指数 Acoustic complexity index (ACI)	$D / ∑ I k$	相邻频段窗口音量的变化; D为相邻频段音量差的累积; I_k为各频段的音量 Difference in amplitude among samples; D is summary of intensity difference among adjacent frequency bands ; I_k is intensity in a single frequency band	Pieretti et al, 2011
声学多样性指数 Acoustic diversity index (ADI)	$∑ p i × log p i$	基于Shannon指数量化音量在不同频段的分布; p_i是每个频率区间的相对强度 Spectral complexity based on Shannon index; p_i is relative intensity in each frequency band	Villanueva-Rivera et al, 2011
声学均匀度指数 Acoustic evenness index (AEI)	$Gini(I)$	基于Gini指数量化音量在不同频段的分布; I是音量 Gini coefficient with intensity at each frequency band; I is intensity	Villanueva-Rivera et al, 2011
生物声学指数 Bioacoustic index (BIO)	$∑ I k$	特定频段音量的汇总; I_k为各频段的音量 Sum of intensity in particular frequency band; I_k is intensity in a single frequency band	Boelman et al, 2007
声熵指数 Acoustic entropy index (H)	$H t × H f$	时间熵(H_t)和频谱熵(H_f)的乘积 Product of time entropy (H_t) and spectral entropy (H_f)	Sueur et al, 2008
振幅包络线中值 Median of the amplitude envelope (M)	$Median A k$	声音振幅包络值的中值; A_k是振幅包络值 Median of the amplitude envelope value; A_k is amplitude envelope value	Depraetere et al, 2012
标准化声景差异指数 Normalized difference sound index (NDSI)	$b − a b + a$	生物产生音量(b)与人类产生音量(a)的比率 Ratio of amplitude in biophony (b) and anthrophony (a)	Kasten et al, 2012

图2 Bootstrap your own latent for audio (BYOL-A)模型结构图

Fig. 2 Bootstrap your own latent for audio (BYOL-A) structure diagram

图3 子样本录音策略示意图。以10 min、20 min、40 min的样本时长为例, 列出3种不同的子样本录音策略。

Fig. 3 Sub-samples recording schemes. Taking samples of 10 min, 20 min, and 40 min in length as examples, three different sub-samples recording schemes are listed.

图4 子样本长度与总样本的声学指数特征和BYOL-A特征(H)的相关性。图中黑线表示相关系数的中位数, 阴影区域表示相关系数的取值范围。(A) ACI; (B) ADI; (C) AEI; (D) BIO; (E) H; (F) M; (G) NDSI。声学指数的全称见表1, BYOL-A, Bootstrap your own latent for audio。

Fig. 4 The correlation of the acoustic index features and BYOL-A feature (H) between sub-sample length and total sample. The black line in the graph represents the median of the correlation coefficients, and the shaded area represents the range of values for the correlation coefficients. (A) ACI; (B) ADI; (C) AEI; (D) BIO; (E) H; (F) M; (G) NDSI. Abbreviations of acoustic indices are the same as denoted in Table 1, BYOL-A, Bootstrap your own latent for audio.

图5 不同采样策略下子样本与总样本的声学指数特征和BYOL-A特征(H)的相关性。(A) ACI; (B) ADI; (C) AEI; (D) BIO; (E) H; (F) M; (G) NDSI。声学指数的全称见表1, BYOL-A, Bootstrap your own latent for audio。

Fig. 5 The correlation of the acoustic index features and BYOL-A (H) between sub-samples by different recording schemes and total sample.(A) ACI; (B) ADI; (C) AEI; (D) BIO; (E) H; (F) M; (G) NDSI. Abbreviations of acoustic indices are the same as denoted in Table 1, BYOL-A, Bootstrap your own latent for audio.

图6 不同采样策略下子样本与总样本的声学指数特征的误差。(A) ACI; (B) ADI; (C) AEI; (D) BIO; (E) H; (F) M; (G) NDSI。声学指数的全称见表1。

Fig. 6 The error of the acoustic index features between sub-samples by different recording schemes and total sample. (A) ACI; (B) ADI; (C) AEI; (D) BIO; (E) H; (F) M; (G) NDSI. Abbreviations of acoustic indices are the same as denoted in Table 1.

图7 声学指数ACI、ADI、AEI、BIO、H、M和NDSI之间的相关性。声学指数的全称见表1。

Fig. 7 The correlation between acoustic indices ACI, ADI, AEI, BIO, H, M, and NDSI. Abbreviations of acoustic indices are the same as denoted in Table 1.

表2 声学指数(ACI、ADI、AEI、BIO、H、M、NDSI)和BYOL-A特征在声景分类任务中的效果对比。声学指数的全称见表1, BYOL-A, Bootstrap your own latent for audio。

Table 2 Comparison of the effectiveness of soundscape classification based on acoustic indices (ACI, ADI, AEI, BIO, H, M, NDSI) and BYOL-A feature. Abbreviations of acoustic indices are the same as denoted in Table 1, BYOL-A, Bootstrap your own latent for audio.

	袋外误差 Out-of-bag error	Kappa值 Kappa value	准确率 Accuracy	精确率 Precision	召回率 Recall	F1分数 F1 score	运算时间 Calculating time
声学指数 Acoustic indices	3%	0.96	0.93	0.97	0.97	0.97	121.57 s
BYOL-A特征 Bootstrap your own latent for audio feature	0.88%	0.99	0.99	0.99	0.99	0.99	36.42 s

图8 声学指数(ACI、ADI、AEI、BIO、H、M、NDSI)和BYOL-A特征在声景分类任务的混淆矩阵。BIOP: 生物声; NOISE: 人工声; GEO: 地理声。声学指数的全称见表1, BYOL-A, Bootstrap your own latent for audio。

Fig. 8 Confusion matrix of soundscape classification based on acoustic indices (ACI, ADI, AEI, BIO, H, M, NDSI) and BYOL-A feature. BIOP, Biophony; NOISE, Anthrophony; GEO, Geophony. Abbreviations of acoustic indices are the same as in Table 1, BYOL-A, Bootstrap your own latent for audio.

参考文献 48

[1]	Aide TM, Corrada-Bravo C, Campos-Cerqueira M, Milan C, Vega G, Alvarez R (2013) Real-time bioacoustics monitoring and automated species identification. PeerJ, 1, e103.
[2]	Anunciação PR, Sugai LSM, Martello F, Ribeiro MC (2022) Estimating the diversity of tropical anurans in fragmented landscapes with acoustic monitoring: Lessons from a sampling sufficiency perspective. Biodiversity and Conservation, 31, 3055-3074.
[3]	Blumstein DT, Mennill DJ, Clemins P, Girod L, Yao K, Patricelli G, Hanser SF (2011) Acoustic monitoring in terrestrial environments using microphone arrays: Applications, technological considerations and prospectus. Journal of Applied Ecology, 48, 758-767.
[4]	Boelman N, Asner G, Hart P, Martin R (2007) Multi-trophic invasion resistance in Hawaii: Bioacoustics, field surveys, and airborne remote sensing. Ecological Applications, 17, 2137-2144. DOI PMID
[5]	Bradfer-Lawrence T, Gardner N, Bunnefeld L, Bunnefeld N, Willis SG, Dent DH (2019) Guidelines for the use of acoustic indices in environmental research. Methods in Ecology and Evolution, 10, 1796-1807. DOI
[6]	Buxton R, McKenna M, Clapp M, Meyer E, Stabenau E, Angeloni L, Crooks K, Wittemyer G (2018) Efficacy of extracting indices from large-scale acoustic recordings to monitor biodiversity. Conservation Biology, 32, 1174-1184. DOI PMID
[7]	Cifuentes E, Vélez Gómez J, Butler SJ (2021) Relación entre índices acústicos, duración de las grabaciones y tiempo de procesamiento: Una prueba metodológica. Biota Colombiana, 22, 26-35.
[8]	Cook A, Hartley S (2018) Efficient sampling of avian acoustic recordings: Intermittent subsamples improve estimates of single species prevalence and total species richness. Avian Conservation and Ecology, 13, 21.
[9]	Depraetere M, Pavoine S, Jiguet F, Gasc A, Duvail S, Sueur J (2012) Monitoring animal diversity using acoustic indices: Implementation in a temperate woodland. Ecological Indicators, 13, 46-54.
[10]	Digby A, Towsey M, Bell BD, Teal PD (2013) A practical comparison of manual and autonomous methods for acoustic monitoring. Methods in Ecology and Evolution, 4, 675-683.
[11]	Fairbrass AJ, Firman M, Williams C, Brostow GJ, Titheridge H, Jones KE (2019) CityNet—Deep learning tools for urban ecoacoustic assessment. Methods in Ecology and Evolution, 10, 186-197. DOI
[12]	Fairbrass AJ, Rennert P, Williams C, Titheridge H, Jones KE (2017) Biases of acoustic indices measuring biodiversity in urban areas. Ecological Indicators, 83, 169-177.
[13]	Farina A, Pieretti N, Piccioli L (2011) The soundscape methodology for long-term bird monitoring: A Mediterranean Europe case-study. Ecological Informatics, 6, 354-363.
[14]	Gasc A, Francomano D, Dunning JB, Pijanowski BC (2017) Future directions for soundscape ecology: The importance of ornithological contributions. The Auk, 134, 215-228.
[15]	Gasc A, Sueur J, Jiguet F, Devictor V, Grandcolas P, Burrow C, Depraetere M, Pavoine S (2013) Assessing biodiversity with sound: Do acoustic diversity indices reflect phylogenetic and functional diversities of bird communities? Ecological Indicators, 25, 279-287.
[16]	Grill JB, Strub F, Altché F, Tallec C (2020) Bootstrap your own latent: A new approach to self-supervised learning. Neural Information Processing Systems. arXiv, 2006.07733.
[17]	Heath BE, Sethi SS, Orme CDL, Ewers RM, Picinali L (2021) How index selection, compression, and recording schedule impact the description of ecological soundscapes. Ecology and Evolution, 11, 13206-13217. DOI PMID
[18]	Hutto RL, Stutzman RJ (2009) Humans versus autonomous recording units: A comparison of point-count results. Journal of Ornithology, 80, 387-398.
[19]	Jorge FC, Machado CG, da Cunha Nogueira SS, Nogueira-Filho SLG (2018) The effectiveness of acoustic indices for forest monitoring in Atlantic rainforest fragments. Ecological Indicators, 91, 71-76.
[20]	Kasten E, Gage S, Fox J, Joo W (2012) The remote environmental assessment laboratory’s acoustic library: An archive for studying soundscape ecology. Ecological Informatics, 12, 50-67.
[21]	Laiolo P (2010) The emerging significance of bioacoustics in animal species conservation. Biological Conservation, 143, 1635-1645.
[22]	Li CH, Lei T (2014) Effects of anthropogenic disturbance on plant diversity in Yeyahu Municipal Nature Reserve of Beijing. Journal of Fujian Forestry University, 34, 309-315. (in Chinese with English abstract)
	[李聪慧, 雷霆 (2014) 人为干扰对北京野鸭湖市级自然保护区植物多样性的影响. 福建林学院学报, 34, 309-315.]
[23]	Mullet TC, Gage SH, Morton JM, Huettmann F (2016) Temporal and spatial variation of a winter soundscape in south-central Alaska. Landscape Ecology, 31, 1117-1137.
[24]	Niizumi D, Takeuchi D, Ohishi Y, Harada N, Kashino K (2021) BYOL for audio: Self-supervised learning for general-purpose audio representation. 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1-8. Shenzhen, China.
[25]	Pieretti N, Duarte MHL, Sousa-Lima RS, Rodrigues M, Young RJ, Farina A (2015) Determining temporal sampling schemes for passive acoustic studies in different tropical ecosystems. Tropical Conservation Science, 8, 215-234.
[26]	Pieretti N, Farina A, Morri D (2011) A new methodology to infer the singing activity of an avian community: The acoustic complexity index (ACI). Ecological Indicators, 11, 868-873.
[27]	Pijanowski BC, Farina A, Gage SH, Dumyahn SL, Krause BL (2011a) What is soundscape ecology? An introduction and overview of an emerging new science. Landscape Ecology, 26, 1213-1232.
[28]	Pijanowski BC, Villanueva-Rivera LJ, Dumyahn SL, Farina A, Krause BL, Napoletano BM, Gage SH, Pieretti N (2011b) Soundscape ecology: The science of sound in the landscape. BioScience, 61, 203-216.
[29]	Priyadarshani N, Marsland S, Castro I (2018) Automated birdsong recognition in complex acoustic environments: A review. Journal of Avian Biology, 49, e01447.
[30]	Rempel RS, Hobson KA, Holborn G, Wilgenburg SLV, Elliott J (2005) Bioacoustic monitoring of forest songbirds: Interpreter variability and effects of configuration and digital processing methods in the laboratory. Journal of Field Ornithology, 76, 1-11.
[31]	Rodrigues M (1996) Song activity in the chiffchaff: Territorial defence or mate guarding? Animal Behaviour, 51, 709-716.
[32]	Ruff ZJ, Lesmeister DB, Appel CL, Sullivan CM (2021) Workflow and convolutional neural network for automated identification of animal sounds. Ecological Indicators, 124, 107419.
[33]	Sethi SS, Jones NS, Fulcher BD, Picinali L, Clink DJ, Klinck H, Orme CDL, Wrege PH, Ewers RM (2020) Characterizing soundscapes across diverse ecosystems using a universal acoustic feature set. Proceedings of the National Academy of Sciences, USA, 117, 17049-17055.
[34]	Stevenson BC, Borchers DL, Altwegg R, Swift RJ, Gillespie DM, Measey GJ (2015) A general framework for animal density estimation from acoustic detections across a fixed microphone array. Methods in Ecology and Evolution, 6, 38-48.
[35]	Stowell D, Wood MD, Pamuła H, Stylianou Y, Glotin H (2019) Automatic acoustic detection of birds through deep learning: The first Bird Audio Detection Challenge. Methods in Ecology and Evolution, 10, 368-380. DOI
[36]	Sueur J, Farina A (2015) Ecoacoustics: The ecological investigation and interpretation of environmental sound. Biosemiotics, 8, 493-502.
[37]	Sueur J, Farina A, Gasc A, Pieretti N, Pavoine S (2014) Acoustic indices for biodiversity assessment and landscape investigation. Acta Acustica United with Acustica, 100, 772-781.
[38]	Sueur J, Pavoine S, Hamerlynck O, Duvail S (2008) Rapid acoustic survey for biodiversity appraisal. PLoS ONE, 3, e4065.
[39]	Sugai LSM, Silva TSF, Llusia D, Siqueira T (2021) Drivers of assemblage-wide calling activity in tropical anurans and the role of temporal resolution. Journal of Animal Ecology, 90, 673-684. DOI PMID
[40]	Swiston KA, Mennill DJ (2009) Comparison of manual and automated methods for identifying target sounds in audio recordings of Pileated, Pale-Billed, and Putative Ivory- Billed Woodpeckers. Journal of Field Ornithology, 80, 42-50.
[41]	Takeuchi D, Koizumi Y, Ohishi Y, Harada N, Kashino K (2020) Effects of word-frequency based pre- and post- processings for audio captioning. In:International Workshop on Detection and Classification of Acoustic Scenes and Events. arXiv, 2009.11436.
[42]	Towsey M, Parsons S, Sueur J (2014) Ecology and acoustics at a large scale. Ecological Informatics, 21, 1-3.
[43]	Ulloa JS, Aubin T, Llusia D, Courtois ÉA, Fouquet A, Gaucher P, Pavoine S, Sueur J (2019) Explosive breeding in tropical anurans: Environmental triggers, community composition and acoustic structure. BMC Ecology, 19, 28. DOI PMID
[44]	Villanueva-Rivera L, Pijanowski B, Doucette J, Pekin B (2011) A primer of acoustic analysis forlandscape ecologists. Landscape Ecology, 26, 1233-1246.
[45]	Wang Y, Gao GC, Fu BQ, Wu Z (2009) Composition and spatial distribution pattern of ground-dwelling beetle communities in Yeyahu Wetland, Beijing. Biodiversity Science, 17, 30-42. (in Chinese with English abstract) DOI
	[王玉, 高光彩, 付必谦, 吴专 (2009) 北京野鸭湖湿地地表甲虫群落组成与空间分布格局. 生物多样性, 17, 30-42.] DOI
[46]	Wilkins MR, Seddon N, Safran RJ (2013) Evolutionary divergence in acoustic signals: Causes and consequences. Trends in Ecology & Evolution, 28, 156-166.
[47]	Wrege PH, Rowland ED, Keen S, Shiu Y (2017) Acoustic monitoring for conservation in tropical forests: Examples from forest elephants. Methods in Ecology and Evolution, 8, 1292-1301.
[48]	Zwart MC, Baker A, McGowan PJ, Whittingham MJ (2014) The use of automated bioacoustic recorders to replace human wildlife surveys: An example using nightjars. PLoS ONE, 9, e102770.

湿地声景录音策略及面向声景分类的特征选择

Wetland soundscape recording scheme and feature selection for soundscape classification

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 48

相关文章 15

编辑推荐

Metrics

本文评价

[1]	白皓天, 余上, 潘新园, 凌嘉乐, 吴娟, 谢恺琪, 刘阳, 陈学业. AI辅助识别的鸟类被动声学监测在城市湿地公园中的应用[J]. 生物多样性, 2024, 32(8): 24188-.
[2]	张乃鹏, 梁洪儒, 张焱, 孙超, 陈勇, 王路路, 夏江宝, 高芳磊. 土壤类型和地下水埋深对黄河三角洲典型盐沼植物群落空间分异的影响[J]. 生物多样性, 2024, 32(2): 23370-.
[3]	郭倩茸, 段淑斐, 谢捷, 董雪燕, 肖治术. 鸟声标注技术及其在被动声学监测中的应用[J]. 生物多样性, 2024, 32(10): 24313-.
[4]	李晓媛, 张雯丽, 田澍辽, 王振龙, 肖治术. 动物园基于生物声学监测的动物福利评价进展[J]. 生物多样性, 2024, 32(10): 24297-.
[5]	陈蕾, 许志勇, 苏菩坤, 赖小甜, 赵兆. 依频声学多样性指数用于人类活动区域的适用能力[J]. 生物多样性, 2024, 32(10): 24286-.
[6]	刘莹莹, 龚立新, 曾皓, 冯江, 董永军, 王磊, 江廷磊. 被动声学监测在蝙蝠研究中的应用[J]. 生物多样性, 2024, 32(10): 24233-.
[7]	黄万涛, 郝泽周, 张梓欣, 肖治术, 张承云. 被动声学监测设备性能比较及对鸟声识别的影响[J]. 生物多样性, 2024, 32(10): 24273-.
[8]	何凯莹, 徐心慧, 张承云, 郝泽周, 肖治术, 郭莹莹. 生物声学数据档案的管理标准及管理技术进展[J]. 生物多样性, 2024, 32(10): 24266-.
[9]	李乐, 张承云, 裴男才, 高丙涛, 王娜, 李嘉睿, 武瑞琛, 郝泽周. 基于被动声学监测技术的城市绿地景观格局与鸟类多样性关联分析[J]. 生物多样性, 2024, 32(10): 24296-.
[10]	谢将剑, 沈忱, 张飞宇, 肖治术. 融合音频及生态位信息的跨地域鸟类物种识别方法[J]. 生物多样性, 2024, 32(10): 24259-.
[11]	郝泽周, 张承云, 李乐, 高丙涛, 曾伟, 王淳, 王梓炫, 黄万涛, 张悦, 裴男才, 肖治术. 城市鸟类多样性被动声学监测与评价技术应用[J]. 生物多样性, 2024, 32(10): 24123-.
[12]	吴浩, 余玉蓉, 王佳钰, 赵媛博, 高娅菲, 李小玲, 卜贵军, 薛丹, 吴林. 低水位增加灌木多样性和生物量但降低土壤有机碳含量: 以鄂西南贫营养泥炭地为例[J]. 生物多样性, 2023, 31(3): 22600-.
[13]	黄雨菲, 路春燕, 贾明明, 王自立, 苏越, 苏艳琳. 基于无人机影像与面向对象-深度学习的滨海湿地植物物种分类[J]. 生物多样性, 2023, 31(3): 22411-.
[14]	肖治术, 崔建国, 王代平, 王志陶, 罗金红, 谢捷. 现代生物声学的学科发展趋势及中国机遇[J]. 生物多样性, 2023, 31(1): 22423-.
[15]	张屹美, 王言一, 何衍, 周冰, 田苗, 夏灿玮. Beta声学指数的特征和应用[J]. 生物多样性, 2023, 31(1): 22513-.