FPGA Implementation of Blue Whale Calls Classifier Using High-Level Programming Tool

In this paper, we propose a hardware-based architecture for automatic blue whale calls classification based on short-time Fourier transform and multilayer perceptron neural network. The proposed architecture is implemented on field programmable gate array (FPGA) using Xilinx System Generator (XSG) and the Nexys-4 Artix-7 FPGA board. This high-level programming tool allows us to design, simulate and execute the compiled design in Matlab/Simulink environment quickly and easily. Intermediate signals obtained at various steps of the proposed system are presented for typical blue whale calls. Classification performances based on the fixed-point XSG/FPGA implementation are compared to those obtained by the floating-point Matlab simulation, using a representative database of the blue whale calls.

[1]  E. D. Chesmore,et al.  Automated identification of field-recorded songs of four British grasshoppers using bioacoustic signal recognition , 2004, Bulletin of Entomological Research.

[2]  Nathan Intrator,et al.  Classification of underwater mammals using feature extraction based on time-frequency analysis and BCM theory , 1998, IEEE Trans. Signal Process..

[3]  Chen Chin-Hsing,et al.  Classification of underwater signals using wavelet transforms and neural networks , 1998 .

[4]  David Reby,et al.  Cepstral coefficients and hidden Markov models reveal idiosyncratic voice characteristics in red deer (Cervus elaphus) stags. , 2006, The Journal of the Acoustical Society of America.

[5]  B. Venkataramani,et al.  System on programmable chip implementation of neural network-based isolated digit recognition system , 2009 .

[6]  Nathalie Roy,et al.  Detection and localization of blue and fin whales from large-aperture autonomous hydrophone arrays: A case study from the St. Lawrence estuary , 2008 .

[7]  V B Deecke,et al.  Quantifying complex patterns of bioacoustic variation: use of a neural network to compare killer whale (Orcinus orca) dialects. , 1999, The Journal of the Acoustical Society of America.

[8]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[9]  Bor-Shing Lin,et al.  An FPGA-Based Rapid Wheezing Detection System , 2014, International journal of environmental research and public health.

[10]  Whitlow W. L. Au,et al.  Principles of marine bioacoustics , 2008 .

[11]  Arik Kershenbaum,et al.  An image processing based paradigm for the extraction of tonal sounds in cetacean communications. , 2013, The Journal of the Acoustical Society of America.

[12]  Klaus Zuberbühler,et al.  A method for automated individual, species and call type recognition in free-ranging animals , 2013, Animal Behaviour.

[13]  FPGA implementation of feature extraction algorithm for speaker verification , 2010, Proceedings of the 17th International Conference Mixed Design of Integrated Circuits and Systems - MIXDES 2010.

[14]  Michel André,et al.  Neural network-based sperm whale click classification , 2007, Journal of the Marine Biological Association of the United Kingdom.

[15]  B. Venkataramani,et al.  Design of a real time automatic speech recognition system using Modified One Against All SVM classifier , 2011, Microprocess. Microsystems.

[16]  Nathalie Roy,et al.  Passive acoustic detection and localization of whales: effects of shipping noise in Saguenay-St. Lawrence Marine Park. , 2008, The Journal of the Acoustical Society of America.

[17]  Mohammed Bahoura,et al.  Automatic recognition of fin and blue whale calls for real-time monitoring in the St. Lawrence. , 2009, The Journal of the Acoustical Society of America.

[18]  Shing-Tai Pan,et al.  An efficient hybrid learning algorithm for neural network–based speech recognition systems on FPGA chip , 2013, Neural Computing and Applications.

[19]  Mohammed Bahoura,et al.  Acoustic detection and localization of whales in bay of fundy and St. Lawrence estuary critical habitats , 2004 .

[20]  Mohammed Bahoura,et al.  Blue whale calls classification using short-time Fourier and wavelet packet transforms and artificial neural network , 2010, Digit. Signal Process..

[21]  Mohammed Bahoura,et al.  FPGA implementation of a feature extraction technique based on Fourier transform , 2012, 2012 24th International Conference on Microelectronics (ICM).

[22]  E. D. Chesmore,et al.  Application of time domain signal coding and artificial neural networks to passive acoustical identification of animals , 2001 .

[23]  Mohammed Bahoura,et al.  Serial combination of multiple classifiers for automatic blue whale calls recognition , 2012, Expert Syst. Appl..

[24]  Antonio Cañas,et al.  Hardware description of multi-layer perceptrons with different abstraction levels , 2006, Microprocess. Microsystems.

[25]  Jhing-Fa Wang,et al.  Chip design of MFCC extraction for speech recognition , 2002, Integr..

[26]  Enrique Cantó,et al.  Real-Time Speaker Verification System Implemented on Reconfigurable Hardware , 2013, J. Signal Process. Syst..

[27]  J. Hildebrand,et al.  Gaussian mixture model classification of odontocetes in the Southern California Bight and the Gulf of California. , 2007, The Journal of the Acoustical Society of America.

[28]  L. Fanucci,et al.  Low-error digital hardware implementation of artificial neuron activation functions and their derivative , 2011, Microprocess. Microsystems.

[29]  Xuan-Tu Tran,et al.  Design and Implementation of a SoPC System for Speech Recognition , 2013, MUE.