Abstract
Biodiversity monitoring has taken a relevant role in conservation management plans, where several methodologies have been proposed to assess biological information of landscapes. Recently, soundscape studies have allowed biodiversity monitoring by compiling all the acoustic activity present in landscapes in audio recordings. Automatic species detection methods have shown to be a practical tool for biodiversity monitoring, providing insight into the acoustic behavior of species. Generally, the proposed methodologies for species identification have four main stages: signal pre-processing, segmentation, feature extraction, and classification. Most proposals use supervised methods for species identification and only perform for a single taxon. In species identification applications, performance depends on extracting representative species features. We present a feature extraction analysis for multi-species identification in soundscapes using unsupervised learning methods. Linear frequency cepstral coefficients (LFCC), variational autoencoders (VAE), and the KiwiNet architecture, which is a convolutional neural network (CNN) based on VGG19, were evaluated as feature extractors. LFCC is a frequency-based method, while VAE and KiwiNet belong to the deep learning area. In ecoacoustic applications, frequency-based methods are the most widely used. Finally, features were tested by a clustering algorithm that allows species recognition from different taxa. The unsupervised approaches performed multi-species identification between 78%–95%.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Pimm, S.L., et al.: Emerging technologies to conserve biodiversity. Trends Ecol. Evol. 30, 685–696 (2015). https://doi.org/10.1016/j.tree.2015.08.008
Dumyahn, S.L., Pijanowski, B.C.: Soundscape conservation. Landsc. Ecol. 26, 1327–1344 (2011). https://doi.org/10.1007/s10980-011-9635-x
Sueur, J., Farina, A.: Ecoacoustics: the ecological investigation and interpretation of environmental sound. Biosemiotics 8(3), 493–502 (2015). https://doi.org/10.1007/s12304-015-9248-x
Aide, T.M., Hern, A., Campos-cerqueira, M.: Species richness (of insects) drives the use of acoustic space in the tropics. Remote Sens. Ecol. Conserv., 1–12 (2017). https://doi.org/10.3390/rs9111096
Ross, S.-J., Friedman, N.R., Dudley, K.L., Yoshimura, M., Yoshida, T., Economo, E.P.: Listening to ecosystems: data-rich acoustic monitoring through landscape-scale sensor networks. Ecol. Res. 33(1), 135–147 (2017). https://doi.org/10.1007/s11284-017-1509-5
Ruff, Z.J., Lesmeister, D.B., Duchac, L.S., Padmaraju, B.K., Sullivan, C.M.: Automated identification of avian vocalizations with deep convolutional neural networks. Remote Sens. Ecol. Conserv. 6, 79–92 (2020). https://doi.org/10.1002/rse2.125
Bedoya, C., Isaza, C., Daza, J.M., López, J.D.: Automatic recognition of anuran species based on syllable identification. Ecol. Inform. 24, 200–209 (2014). https://doi.org/10.1016/j.ecoinf.2014.08.009
LeBien, J., et al.: A pipeline for identification of bird and frog species in tropical soundscape recordings using a convolutional neural network. Ecol. Inform. 59, 101113 (2020). https://doi.org/10.1016/j.ecoinf.2020.101113
Ruff, Z.J., Lesmeister, D.B., Appel, C.L., Sullivan, C.M.: Workflow and convolutional neural network for automated identification of animal sounds. Ecol. Indic. 124, 107419 (2021). https://doi.org/10.1016/j.ecolind.2021.107419
Stowell, D.: Computational bioacoustic scene analysis. In: Computational Analysis of Sound Scenes and Events, pp. 303–333. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-63450-0
Xie, J., Colonna, J.G., Zhang, J.: Bioacoustic signal denoising: a review. Artif. Intell. Rev. 54(5), 3575–3597 (2020). https://doi.org/10.1007/s10462-020-09932-4
Noda, J.J., David Sánchez-Rodríguez, C.M.T.-G.: We are IntechOpen, the world’s leading publisher of Open Access books Built by scientists, for scientists TOP 1%. Intech 32, 137–144 (2018)
Nirosha Priyadarshani, S.M., Castro, I.: Automated birdsong recognition in complex acoustic environments: a review. Avian Biol. (2018). https://doi.org/10.1111/jav.01447
Rowe, B., Eichinski, P., Zhang, J., Roe, P.: Acoustic auto-encoders for biodiversity assessment. Ecol. Inform. 62, 101237 (2021). https://doi.org/10.1016/j.ecoinf.2021.101237
Ntalampiras, S., Potamitis, I.: Acoustic detection of unknown bird species and individuals. CAAI Trans. Intell. Technol. 6, 291–300 (2021). https://doi.org/10.1049/cit2.12007
Xie, J., Hu, K., Guo, Y., Zhu, Q., Yu, J.: On loss functions and CNNs for improved bioacoustic signal classification. Ecol. Inform. 64, 101331 (2021). https://doi.org/10.1016/j.ecoinf.2021.101331
Bedoya, C.L., Molles, L.E.: Acoustic censusing and individual identification of birds in the wild (2021)
Stowell, D.: Computational bioacoustics with deep learning: a review and roadmap. PeerJ 10, e13152 (2022). https://doi.org/10.7717/peerj.13152
Xie, J., Towsey, M., Zhu, M., Zhang, J., Roe, P.: An intelligent system for estimating frog community calling activity and species richness. Ecol. Indic. 82, 13–22 (2017). https://doi.org/10.1016/j.ecolind.2017.06.015
Mermelstein, P.: Distance measures for speech recognition, psychological and instrumental. Pattern Recognit. Artif. Intell. 116, 374–388 (1976)
Zhou, X., Garcia-Romero, D., Duraiswami, R., Carol Espy-Wilson, S.S.: 2011 IEEE Workshop on Automatic Speech Recognition & Understanding: ASRU 2011: Proceedings, Waikoloa, Hawaii, U.S.A., 11–15 December 2011, p. 564 (2011)
Dong, C., Xue, T., Wang, C.: The feature representation ability of variational autoencoder. Proceedings - 2018 IEEE Third International Conference on Data Science in Cyberspace, DSC 2018, pp. 680–684 (2018). https://doi.org/10.1109/DSC.2018.00108
Fukumoto, T.: Anomaly detection using Variational Autoencoder (VAE) (2020). https://github.com/mathworks/Anomaly-detection-using-Variational-Autoencoder-VAE-/releases/tag/1.0.1, GitHub. Accessed 23 Apr 2022
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: 3rd International Conference on Learning Representations ICLR 2015 - Conference Track Proceedings, pp. 1–14 (2015)
Lamrini, B., Le Lann, M.V., Benhammou, A., Lakhal, E.K.: Detection of functional states by the “LAMDA” classification technique: application to a coagulation process in drinking water treatment. Comptes Rendus Phys. 6, 1161–1168 (2005). https://doi.org/10.1016/j.crhy.2005.11.017
Bedoya, C., Waissman Villanova, J., Isaza Narvaez, C.V.: Yager–Rybalov triple Π operator as a means of reducing the number of generated clusters in unsupervised anuran vocalization recognition. In: Gelbukh, A., Espinoza, F.C., Galicia-Haro, S.N. (eds.) MICAI 2014. LNCS (LNAI), vol. 8857, pp. 382–391. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-13650-9_34
Acknowledgments
This work was supported by Universidad de Antioquia, Instituto Tecnológico Metropolitano de Medellín, Alexander von Humboldt Institute for Research on Biological Resources and Colombian National Fund for Science, Technology and Innovation, Francisco Jose de Caldas - MINCIENCIAS (Colombia) [Program No. 111585269779].
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Guerrero, M.J., Restrepo, J., Nieto-Mora, D.A., Daza, J.M., Isaza, C. (2022). Insights from Deep Learning in Feature Extraction for Non-supervised Multi-species Identification in Soundscapes. In: Bicharra Garcia, A.C., Ferro, M., Rodríguez Ribón, J.C. (eds) Advances in Artificial Intelligence – IBERAMIA 2022. IBERAMIA 2022. Lecture Notes in Computer Science(), vol 13788. Springer, Cham. https://doi.org/10.1007/978-3-031-22419-5_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-22419-5_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-22418-8
Online ISBN: 978-3-031-22419-5
eBook Packages: Computer ScienceComputer Science (R0)