Investigation of Unsupervised Models for Biodiversity Assessment

Significant animal species loss has been observed in recent decades due to habitat destruction, which puts at risk environmental integrity and biodiversity. Traditional ways of assessing biodiversity are limited in terms of both time and space, and have high cost. Since the presence of animals can be indicated by sound, recently acoustic recordings have been used to estimate species richness. Bioacoustic sounds are typically recorded in habitats for several weeks, so contain a large collection of different sounds. Birds are of particular interest due to their distinctive calls and because they are useful ecological indicators. To assess biodiversity, the task of manually determining how many different types of birds are present in such a lengthy audio is really cumbersome. Towards providing an automated support to this issue, in this paper we investigate and propose a clustering based approach to assist in automated assessment of biodiversity. Our approach first estimates the number of different species and their volumes which are used for deriving a biodiversity index. Experimental results with real data indicates that our proposed approach estimates the biodiversity index value close to the ground truth.

[1]  Brian Hanson,et al.  Robust speaker-independent word recognition using static, dynamic and acceleration features: experiments with Lombard and noisy speech , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[2]  Klaus Riede,et al.  Monitoring Biodiversity: Analysis of Amazonian Rainforest Sounds , 2016 .

[3]  Paul Roe,et al.  Clustering Acoustic Events in Environmental Recordings for Species Richness Surveys , 2015, ICCS.

[4]  Padmanabhan Rajan,et al.  Model-based unsupervised segmentation of birdcalls from field recordings , 2016, 2016 10th International Conference on Signal Processing and Communication Systems (ICSPCS).

[5]  Javier Seoane,et al.  Effect of Expert Opinion on the Predictive Ability of Environmental Models of Bird Distribution , 2005 .

[6]  Paul Roe,et al.  Revealing the ecological content of long-duration audio-recordings of the environment through clustering and visualisation , 2018, PloS one.

[7]  Robert K. Peet,et al.  The Measurement of Species Diversity , 1974 .

[8]  Sadaoki Furui,et al.  Speaker-independent isolated word recognition using dynamic features of speech spectrum , 1986, IEEE Trans. Acoust. Speech Signal Process..

[9]  Paul Roe,et al.  Sampling environmental acoustic recordings to determine bird species richness. , 2013, Ecological applications : a publication of the Ecological Society of America.

[10]  H. Akaike,et al.  Information Theory and an Extension of the Maximum Likelihood Principle , 1973 .

[11]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[12]  Jill L. Deppe,et al.  Using soundscape recordings to estimate bird species abundance, richness, and composition , 2009 .

[13]  Panu Somervuo,et al.  Analyzing Bird Song Syllables on the Self-Organizing Map , 2003 .

[14]  Justin Salamon,et al.  Unsupervised feature learning for urban sound classification , 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[15]  Robert K. Colwell,et al.  Estimating terrestrial biodiversity through extrapolation. , 1994, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[16]  Jinhai Cai,et al.  Sensor Network for the Monitoring of Ecosystem: Bird Species Recognition , 2007, 2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information.

[17]  Ian Agranat,et al.  Bat species identification from zero crossing and full spectrum echolocation calls using Hidden Markov Models, Fisher scores, unsupervised clustering and balanced winnow pairwise classifiers , 2013 .