Classification of whale vocalizations using the Weyl transform

In this paper, we apply the Weyl transform to represent the vocalization of marine mammals. In contrast to other popular representation methods, such as the MFCC and the Chirplet transform, the Weyl transform captures the global information of signals. This is especially useful when the signal has low order polynomial phase. We can reconstruct the signal from the coefficients obtained from the Weyl transform, and perform classification based on these coefficients. Experimental results show that classification using features extracted from the Weyl transform outperforms the MFCC and the Chirplet transform on our collected whales data.

[1]  Anna Scaglione,et al.  Product high-order ambiguity function for multicomponent polynomial-phase signal modeling , 1998, IEEE Trans. Signal Process..

[2]  Kaare Brandt Petersen,et al.  Mel Frequency Cepstral Coefficients: An Evaluation of Robustness of MP3 Encoded Music , 2006, ISMIR.

[3]  M Esfahanian,et al.  Sparse representation for classification of dolphin whistles by type. , 2014, The Journal of the Acoustical Society of America.

[4]  P. Mermelstein,et al.  Distance measures for speech recognition, psychological and instrumental , 1976 .

[5]  Hervé Glotin,et al.  Subunit definition and analysis for humpback whale call classification , 2010 .

[6]  Beth Logan,et al.  Mel Frequency Cepstral Coefficients for Music Modeling , 2000, ISMIR.

[7]  Boaz Porat,et al.  Estimation and classification of polynomial-phase signals , 1991, IEEE Trans. Inf. Theory.

[8]  E. Chassande-Mottin,et al.  Discrete time and frequency Wigner-Ville distribution: Moyal's formula and aliasing , 2005, IEEE Signal Processing Letters.

[9]  Patrick Flandrin,et al.  Sparse Representations with Chirplets viaMaximum Likelihood , 2007 .

[10]  A. Robert Calderbank,et al.  The Finite Heisenberg-Weyl Groups in Radar and Communications , 2006, EURASIP J. Adv. Signal Process..

[11]  Olivier Adam,et al.  Advantages of the Hilbert Huang transform for marine mammals signals analysis. , 2006, The Journal of the Acoustical Society of America.

[12]  Benjamin Friedlander,et al.  The discrete polynomial-phase transform , 1995, IEEE Trans. Signal Process..

[13]  B.A. Weisburn,et al.  Design of time frequency strip filters , 1995, Conference Record of The Twenty-Ninth Asilomar Conference on Signals, Systems and Computers.

[14]  P. Flandrin,et al.  Chirp hunting , 1998, Proceedings of the IEEE-SP International Symposium on Time-Frequency and Time-Scale Analysis (Cat. No.98TH8380).

[15]  Ildar R Urazghildiiev,et al.  Acoustic detection of North Atlantic right whale contact calls using the generalized likelihood ratio test. , 2006, The Journal of the Acoustical Society of America.

[16]  Emmanuel J. Candès,et al.  Multiscale Chirplets and Near-Optimal Recovery of Chirps , 2002 .

[17]  Leon Cohen,et al.  Time Frequency Analysis: Theory and Applications , 1994 .

[18]  Mohammed Bahoura,et al.  Chirplet Transform Applied to Simulated and Real Blue Whale (Balaenoptera musculus) Calls , 2008, ICISP.

[19]  R. Calderbank,et al.  Chirp sensing codes: Deterministic compressed sensing measurements for fast recovery , 2009 .

[20]  Bruno Torrésani,et al.  Time-Frequency and Time-Scale Analysis , 1999 .

[21]  W. Moran,et al.  Finite Heisenberg-Weyl groups and golay complementary sequences , 2006, 2006 International Waveform Diversity & Design Conference.

[22]  Emmanuel J. Candes,et al.  Detecting highly oscillatory signals by chirplet path pursuit , 2006, gr-qc/0604017.

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

[24]  B. Borden,et al.  Fundamentals of Radar Imaging , 2009 .

[25]  Simon Haykin,et al.  The chirplet transform: physical considerations , 1995, IEEE Trans. Signal Process..