Discriminative Singular Spectrum Analysis for Bioacoustic Classification

Abstract

Automatic analysis of bioacoustic signals is a fundamental tool to evaluate the vitality of our planet. Frogs and bees, for instance, may act like biological sensors providing information about environmental changes. This task is fundamental for ecological monitoring and includes many challenges such as nonuniform signal length processing, degraded target signal due to environmental noise, and the scarcity of the labeled samples for training machine learning. To tackle these challenges, we present a bioacoustic signal classifier equipped with a discriminative mechanism to extract useful features for analysis and classification efficiently. The proposed classifier does not require a large amount of training data and handles nonuniform signal length natively. Unlike current bioacoustic recognition methods, which are task-oriented, the proposed model relies on transforming the input signals into vector subspaces generated by applying Singular Spectrum Analysis (SSA). Then, a subspace is designed to expose discriminative features. The proposed model shares end-to-end capabilities, which is desirable in modern machine learning systems. This formulation provides a segmentation-free and noise-tolerant approach to represent and classify bioacoustic signals and a highly compact signal descriptor inherited from SSA. The validity of the proposed method is verified using three challenging bioacoustic datasets containing anuran, bee, and mosquito species. Experimental results on three bioacoustic datasets have shown the competitive performance of the proposed method compared to commonly employed methods for bioacoustics signal classification in terms of accuracy.

Advancing the Interpretation of Shallow Water Marine Soundscapes

“…In some cases, classification was derived from band-level indices (e.g., Širović et al, 2015;Oestreich et al, 2020). When the training data are insufficient, additional exemplars can be added by transforming the true signals (and labeling them as false) or adding different types and amounts (Barchiesi et al, 2015;Benetos et al, 2015;Shane et al, 2015;Zabalza et al, 2015;Freeman and Freeman, 2016;Lin et al, 2017a,b;Lin et al, , 2019Lin et al, , 2021Tsao, 2018, 2020;Colonna et al, 2018;Guan et al, 2018;Reis et al, 2018;Seger et al, 2018;Virtanen et al, 2018;Abeßer, 2020;Gatto et al, 2020;Mooney et al, 2020;Shajahan et al, 2020;Xie et al, 2020;Dias et al, 2021;Dimoff et al, 2021;Gabrielli et al, 2021;Ick and McFee, 2021;Ozanich et al, 2021).…”

“…The literature referenced simply serve as examples, and not an exhaustive or systematic search of the literature. References cited in the table:(Barchiesi et al, 2015;Benetos et al, 2015;Shane et al, 2015;Zabalza et al, 2015;Freeman and Freeman, 2016; Lin et al, 2017a,b;Lin et al, , 2019Lin et al, , 2021 Tsao, 2018, 2020;Colonna et al, 2018;Guan et al, 2018;Reis et al, 2018;Seger et al, 2018;Virtanen et al, 2018;Abeßer, 2020;Gatto et al, 2020;Mooney et al, 2020;Shajahan et al, 2020;Xie et al, 2020;Dias et al, 2021;Dimoff et al, 2021;Gabrielli et al, 2021;Ick and McFee, 2021;Ozanich et al, 2021).…”

Pattern-set Representations using Linear, Shallow and Tensor Subspaces

“…(3) Introduce a deterministic neural network initialization by applying the convolutional kernels produced by FKT or GDS as an alternative to the random initialization process. (4) Propose an information fusion strategy by subspaces that may handle both sound subspaces [44,45] and video subspaces in a unified framework.…”