How index selection, compression, and recording schedule impact the description of ecological soundscapes.
How index selection, compression, and recording schedule impact the description of ecological soundscapes.
复制标题
DOI：
10.1002/ece3.8042
复制
发表时间：
2021-10
影响因子：
2.6
通讯作者：
Picinali L
中科院分区：
文献类型：
--
作者：
Heath BE;Sethi SS;Orme CDL;Ewers RM;Picinali L
来自环境声景记录的声学指数正被用于监测生态系统健康和发声动物的生物多样性。声景数据可能很快变得非常昂贵且难以管理，因此有时采用数据压缩或时间下采样来降低数据存储和传输成本。这些参数在不同的实验之间变化很大，这种变化的后果大多是未知的。我们分析了婆罗洲东北部历史土地利用梯度的现场记录。我们量化了实验参数（MP3压缩、录音长度和时间子集）对音景描述符（分析指数和卷积神经网络派生的AudioSet指纹）的影响。测试了两种描述符类型对参数变化的鲁棒性及其在音景分类任务中的可用性。我们发现压缩和记录长度都会导致计算的指标值发生相当大的变化。然而，我们发现这种变化和时间子集对分类模型性能的影响很小：声学指标选择对性能的影响更大，Audioset指纹识别提供了更高（12%-16%）的分类器准确度、精度和召回率。我们建议在音景分析中使用AudioSet指纹，即使在小数据池中也能找到卓越而一致的性能。如果数据存储是研究的瓶颈，我们建议使用可变比特率编码压缩（质量= 0）将文件大小减少到23%，而不会影响大多数Analytical Index值。AudioSet指纹可以进一步压缩到64 kb/s（8%文件大小）的恒定比特率编码，而不会产生任何可检测的效果。这些建议允许有效地利用有限的数据存储，同时允许不同研究之间的结果可比性。从马来西亚婆罗洲不同的森林结构中记录了声景。模拟数据收集变化，并通过常用声学指标和CNN衍生的AudioSet指纹分析所有数据组。比较了两种类型的音景描述符在数据收集中的变化效果，发现AudioSet指纹是一种更强、更健壮的音景描述符。
Acoustic indices derived from environmental soundscape recordings are being used to monitor ecosystem health and vocal animal biodiversity. Soundscape data can quickly become very expensive and difficult to manage, so data compression or temporal down‐sampling are sometimes employed to reduce data storage and transmission costs. These parameters vary widely between experiments, with the consequences of this variation remaining mostly unknown. We analyse field recordings from North‐Eastern Borneo across a gradient of historical land use. We quantify the impact of experimental parameters (MP3 compression, recording length and temporal subsetting) on soundscape descriptors (Analytical Indices and a convolutional neural net derived AudioSet Fingerprint). Both descriptor types were tested for their robustness to parameter alteration and their usability in a soundscape classification task. We find that compression and recording length both drive considerable variation in calculated index values. However, we find that the effects of this variation and temporal subsetting on the performance of classification models is minor: performance is much more strongly determined by acoustic index choice, with Audioset fingerprinting offering substantially greater (12%–16%) levels of classifier accuracy, precision and recall. We advise using the AudioSet Fingerprint in soundscape analysis, finding superior and consistent performance even on small pools of data. If data storage is a bottleneck to a study, we recommend Variable Bit Rate encoded compression (quality = 0) to reduce file size to 23% file size without affecting most Analytical Index values. The AudioSet Fingerprint can be compressed further to a Constant Bit Rate encoding of 64 kb/s (8% file size) without any detectable effect. These recommendations allow the efficient use of restricted data storage whilst permitting comparability of results between different studies. Soundscapes were recorded from different forest structures in Malaysian Borneo. Data collection variation was simulated, and all data groups were analyzed via usual acoustic indices and a CNN‐derived AudioSet Fingerprint. The effect of variation in data collection was compared between the two types of soundscape descriptor, finding the AudioSet Fingerprint to be a stronger and more robust descriptor of soundscapes.
登录
查看更多内容
DOI：
10.1080/09524622.2017.1396498
发表时间：
2019-01-02
影响因子：
1.8
作者：
Araya-Salas, Marcelo;Smith-Vidaurre, Grace;Webster, Michael
通讯作者：
Webster, Michael
影响因子：
3.3
作者：
Giavarina D
通讯作者：
Giavarina D
影响因子：
6.6
作者：
Hill, Andrew P.;Prince, Peter;Rogers, Alex
通讯作者：
Rogers, Alex
DOI：
10.1098/rstb.2011.0049
发表时间：
2011-11-27
影响因子：
6.3
作者：
Ewers, Robert M.;Didham, Raphael K.;Turner, Edgar C.
通讯作者：
Turner, Edgar C.
影响因子：
6.3
作者：
Buxton, Rachel T.;McKenna, Megan F.;Wittemyer, George
通讯作者：
Wittemyer, George