Non-sequential automatic classification of anuran sounds for the estimation of climate-change indicators

Abstract Several biological research studies have shown that the number of individuals of certain species of anurans in a specific geographical region, and the evolution of this number over time, can be used as an indicator of climate change. To detect the presence of anurans, Wireless Sensor Networks (WSNs) are usually deployed with the aim of obtaining bio-acoustic information in a set covering numerous locations. However, the identification of the anuran species from a huge number of recordings usually involves an overwhelming task that has to be undertaken by expert and intelligent systems. Previous studies into this issue have proposed several classification techniques with a common approach: they all take into account the sequential characteristic of sounds by considering syllables or other kinds of vocal segments. In noisy sounds, as it is usually the case in recordings made in natural habitats, segmentation of the signal is no straightforward task and may cause low classification accuracy. To override this problem, a new non-sequential approach is proposed in this paper. It is based on considering very small pieces of sounds (frames) each of which is then classified without considering preceding or subsequent information. Up to nine frame-based classifiers are explored in this paper and their performances are compared to the most commonly used sequential classifier: the Hidden Markov Model (HMM). Additionally, for featuring the frames, many choices have been described, although the application of the Mel Frequency Cepstral Coefficients (MFCCs) has probably become the most common method. In this work, an alternative methodology is suggested: the use of a set of MPEG-7 parameters, which offers a normalized solution with a much greater semantic content. The experimental results have shown that the proposed method clearly outperforms the HMM, thereby showing the non-sequential classification of anuran sounds to be feasible. From among the algorithms tested, the decision-tree classifier has shown the best performance with an overall classification success rate of 87.30%, which is an especially striking result considering that the analyzed sounds were affected by a decidedly noisy background.

[1]  Thomas Sikora,et al.  How Efficient is MPEG-7 for General Sound Recognition? , 2004 .

[2]  M. Casey,et al.  MPEG-7 sound-recognition tools , 2001, IEEE Trans. Circuits Syst. Video Technol..

[3]  Jesús B. Alonso,et al.  Automatic anuran identification using noise removal and audio activity detection , 2017, Expert Syst. Appl..

[4]  Roger Revelle,et al.  Carbon Dioxide Exchange Between Atmosphere and Ocean and the Question of an Increase of Atmospheric CO2 during the Past Decades , 1957 .

[5]  Douglas C. Gayou.  Effects of Temperature on the Mating Call of Hyla versicolor , 1984 .

[6]  Ronald R. Hoy,et al.  Temperature coupling in cricket acoustic communication , 1992, Journal of Comparative Physiology A.

[7]  Guy Lapalme,et al.  A systematic analysis of performance measures for classification tasks , 2009, Inf. Process. Manag..

[8]  Juan J. Noda Arencibia,et al.  Methodology for automatic bioacoustic classification of anurans based on feature fusion , 2016, Expert Syst. Appl..

[9]  Rolf Bardeli,et al.  Similarity Search in Animal Sound Databases , 2009, IEEE Transactions on Multimedia.

[10]  David M. W. Powers,et al.  Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation , 2011, ArXiv.

[11]  H. Carl Gerhardt,et al.  Temperature effects on frequency preferences and mating call frequencies in the green treefrog,Hyla cinerea (Anura: Hylidae) , 1980, Journal of comparative physiology.

[12]  Alejandro Gonzalez-Voyer,et al.  Can amphibians take the heat? Vulnerability to climate warming in subtropical and temperate larval amphibian communities , 2012 .

[13]  Jack W. Bradbury,et al.  Principles of Animal Communication , 1998 .

[14]  R R Hoy,et al.  Temperature coupling in cricket acoustic communication , 1992, Journal of Comparative Physiology A.

[15]  Chih-Hsun Chou,et al.  Bird Species Recognition by Wavelet Transformation of a Section of Birdsong , 2009, 2009 Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing.

[16]  Paul R. Martin,et al.  Impacts of climate warming on terrestrial ectotherms across latitude , 2008, Proceedings of the National Academy of Sciences.

[17]  David A. Landgrebe,et al.  The minimum distance approach to classification , 1971 .

[18]  Peter A. Flach,et al.  Machine Learning - The Art and Science of Algorithms that Make Sense of Data , 2012 .

[19]  D. Meadows,et al.  The Limits to Growth , 1972 .

[20]  Jhing-Fa Wang,et al.  Home environmental sound recognition based on MPEG-7 features , 2003, 2003 46th Midwest Symposium on Circuits and Systems.

[21]  W. Härdle,et al.  Applied Multivariate Statistical Analysis , 2003 .

[22]  Claudia Isaza,et al.  Automatic recognition of anuran species based on syllable identification , 2014, Ecol. Informatics.

[23]  Zheng Fang,et al.  Comparison of different implementations of MFCC , 2001 .

[24]  Lior Rokach,et al.  Data Mining with Decision Trees - Theory and Applications , 2007, Series in Machine Perception and Artificial Intelligence.

[25]  Nikos Fakotakis,et al.  Automatic Recognition of Urban Soundscenes , 2008, New Directions in Intelligent Interactive Multimedia.

[26]  Todor Ganchev,et al.  Automated acoustic detection of Vanellus chilensis lampronotus , 2015, Expert Syst. Appl..

[27]  A. Dobson.  An introduction to generalized linear models , 1990 .

[28]  Björn W. Schuller,et al.  Audio recognition in the wild: Static and dynamic classification on a real-world database of animal vocalizations , 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[29]  Chang-Hsing Lee,et al.  Automatic Recognition of Bird Songs Using Cepstral Coefficients , 2006 .

[30]  Panu Somervuo,et al.  Parametric Representations of Bird Sounds for Automatic Species Recognition , 2006, IEEE Transactions on Audio, Speech, and Language Processing.

[31]  Michael Kearney,et al.  The potential for behavioral thermoregulation to buffer “cold-blooded” animals against climate warming , 2009, Proceedings of the National Academy of Sciences.

[32]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[33]  Eduardo Freire Nakamura,et al.  An incremental technique for real-time bioacoustic signal segmentation , 2015, Expert Syst. Appl..

[34]  Geoffrey A. Williamson,et al.  Methods for classification of nocturnal migratory bird vocalizations using Pseudo Wigner-Ville Transform , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[35]  Sean A. Fulop.  Speech Spectrum Analysis , 2011 .

[36]  Christian Breiteneder,et al.  Discrimination and retrieval of animal sounds , 2006, 2006 12th International Multi-Media Modelling Conference.

[37]  Franz Huber,et al.  Acoustic Communication in Insects and Anurans: Common Problems and Diverse Solutions , 2002 .

[38]  Timothy F Chen,et al.  Interrater agreement and interrater reliability: key concepts, approaches, and applications. , 2013, Research in social & administrative pharmacy : RSAP.

[39]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[40]  Chong Mun Ho,et al.  Classification and identification of frog sound based on entropy approach , 2011 .

[41]  Hani Yehia,et al.  On the Use of Compressive Sensing for the Reconstruction of Anuran Sounds in a Wireless Sensor Network , 2012, 2012 IEEE International Conference on Green Computing and Communications.

[42]  Chenn-Jung Huang,et al.  Frog classification using machine learning techniques , 2009, Expert Syst. Appl..

[43]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[44]  Robert M. Gray,et al.  An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[45]  T. Mitchell Aide,et al.  Real-time bioacoustics monitoring and automated species identification , 2013, PeerJ.

[46]  Chia-Feng Juang,et al.  Birdsong recognition using prediction-based recurrent neural fuzzy networks , 2007, Neurocomputing.

[47]  L. L. Cam,et al.  Maximum likelihood : an introduction , 1990 .

[48]  Anil Prabhakar,et al.  Automatic identification of bird calls using Spectral Ensemble Average Voice Prints , 2006, 2006 14th European Signal Processing Conference.

[49]  Paul Roe,et al.  The use of acoustic indices to determine avian species richness in audio-recordings of the environment , 2014, Ecol. Informatics.

[50]  E. S. Gopi.  Digital Speech Processing Using Matlab , 2013 .

[51]  Mark E. Cambron,et al.  An Automated Digital Sound Recording System: The Amphibulator , 2006, Eighth IEEE International Symposium on Multimedia (ISM'06).

[52]  L. Baum,et al.  An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology , 1967 .

[53]  Diego Llusia,et al.  Calling behaviour under climate change: geographical and seasonal variation of calling temperatures in ectotherms , 2013, Global change biology.

[54]  Jacob Benesty,et al.  Springer handbook of speech processing , 2007, Springer Handbooks.

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

[56]  Joaquín Luque,et al.  Evaluation of MPEG-7-Based Audio Descriptors for Animal Voice Recognition over Wireless Acoustic Sensor Networks , 2016, Sensors.

[57]  Hans Schneider,et al.  Structure of the mating calls and relationships of the European tree frogs (Hylidae, anura) , 1974, Oecologia.

[58]  Thomas G. Dietterich.  Machine Learning for Sequential Data: A Review , 2002, SSPR/SPR.

[59]  T. J. Walker.  Specificity in the Response of Female Tree Crickets (Orthoptera, Gryllidae, Oecanthinae) to Calling Songs of the Males , 1957 .

[60]  T. J. Walker,et al.  FACTORS RESPONSIBLE FOR INTRASPECIFIC VARIATION IN THE CALLING SONGS OF CRICKETS , 1962 .

[61]  Theodore Garland,et al.  Why tropical forest lizards are vulnerable to climate warming , 2009, Proceedings of the Royal Society B: Biological Sciences.

[62]  Chenn-Jung Huang,et al.  Intelligent feature extraction and classification of anuran vocalizations , 2014, Appl. Soft Comput..

[63]  Rainer Knust,et al.  Climate Change Affects Marine Fishes Through the Oxygen Limitation of Thermal Tolerance , 2007, Science.

[64]  R. Márquez,et al.  Advertisement calls of the midwife toads Alytes (Amphibia, Anura, Discoglossidae) in continental Spain , 2009 .

[65]  Edward D. Bellis,et al.  The Effects of Temperature on Salientian Breeding Calls , 1957 .

[66]  R. Wielgat,et al.  On using prefiltration in HMM-based bird species recognition , 2012, 2012 International Conference on Signals and Electronic Systems (ICSES).

[67]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[68]  Ilyas Potamitis,et al.  Unsupervised dictionary extraction of bird vocalisations and new tools on assessing and visualising bird activity , 2015, Ecol. Informatics.

[69]  M.N.S. Swamy,et al.  Neural Networks and Statistical Learning , 2013 .

[70]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.