Mutual singular spectrum analysis for bioacoustics classification

Gatto, Bernardo B.; Colonna, Juan Gabriel; Santos, Eulanda M. dos; Nakamura, Eduardo F.

doi:10.1109/mlsp.2017.8168113

Cited by 12 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As basis vectors span a subspace, the comparison among bioacoustic signals is simplified by the use of canonical angles. This method achieved encouraging results in very challenging datasets [19], [20]. Moreover, MSSA is computationally efficient.…”

Section: Introductionmentioning

confidence: 86%

“…In light of these facts and motivated by the recent results achieved by MSSA [19], [20], in this paper, we propose a discriminative method for bioacoustic recognition called Discriminative Singular Spectrum Classifier (DSSC) as an extension of MSSA. DSSC is designed by incorporating a mechanism of extracting discriminative features based on the projection onto the generalized difference subspace (GDS) [23] into the framework of MSSA.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Discriminative Singular Spectrum Analysis for Bioacoustic Classification

Gatto¹,

Santos²,

Colonna³

et al. 2020

Interspeech 2020

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 86%

Section: Introductionmentioning

confidence: 99%

Discriminative Singular Spectrum Analysis for Bioacoustic Classification

Gatto¹,

Santos²,

Colonna³

et al. 2020

Interspeech 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Many studies have targeted the problems of bioacoustics classification. In [13], a low resource (computation and memory) framework, which utilizes mutual singular spectrum analysis to obtain the bases defining the subspaces of the bioacoustics classes, has been proposed. Canonical angles are used to measure the similarity between the subspaces to classify any test audio signal.…”

Section: Related Workmentioning

confidence: 99%

“…gl/cAu4Q1. The second dataset contains audio recordings of 10 different frog species used in [13] for bioacoustic classification and is available at http://goo.gl/FFBzbb. This set of recordings are 16-bit mono and are sampled of 44.1 kHz.…”

Section: Dataset Usedmentioning

confidence: 99%

Deep Convex Representations: Feature Representations for Bioacoustics Classification

et al. 2018

View full text Add to dashboard Cite

In this paper, a deep convex matrix factorization framework is proposed for bioacoustics classification. Archetypal analysis, a form of convex non-negative matrix factorization, is used for acoustic modelling at each level of this framework. At first level, the input feature matrix is factorized into an archetypal dictionary and corresponding convex representations. The representation matrix obtained at the first level is further factorized into a dictionary and convex representations at second level. This hierarchical factorization continues until a desired depth is achieved. We observe that the dictionaries at different levels model complimentary information present in the data. The atoms of the dictionary learned at the first layer lie on convex hull of the data, thus try to model the extremal behaviour. On the contrary, atoms of the deeper dictionaries lie on the convex hull as well as inside the convex hull. Hence, these dictionaries can simultaneously model the extremal and average behaviour of the data. The convex representations obtained from these deeper dictionaries are referred as deep convex representations. Due to inherent sparsity, they result in efficient classification performance. Through experiments on two available bioacoustics datasets, we show that the proposed approach yield comparable or better results than state-of-art approaches.

show abstract

“…Hence, the signals and the noises are separated. Therefore, the singular spectral analysis-based method can achieve a good denoising performance for many practical applications [1,17] such as the seismic signal denoising application [18,19], the image processing application [5] and the acoustic signal processing application [4,20] even though there are the spectral overlapping between the signals and the noises. Also, the denoising performances do not depend on the selection of the kernel functions.…”

Section: Introductionmentioning

confidence: 99%

Singular spectral analysis‐based denoising without computing singular values via augmented Lagrange multiplier algorithm

Feng

Ling

Lei

et al. 2019

IET signal process.

View full text Add to dashboard Cite

This study proposes an augmented Lagrange multiplier-based method to perform the singular spectral analysisbased denoising without computing the singular values. In particular, the one-dimensional (1D) signal is first mapped to a trajectory matrix using the window length L. Second, the trajectory matrix is represented as the sum of the signal dominant matrix and the noise-dominant matrix. The determination of these two matrices is formulated as an optimisation problem with the objective function being the sum of the rank of the signal dominant matrix and the l 0 norm of the noise-dominant matrix. This study employs the Schatten q-norm operator with q = 1/2 and the double nuclear-norm penalty for approximating the rank operator as well as the minimum concave penalty (MCP)-norm operator for approximating the l 0-norm operator. Third, some auxiliary variables are introduced and the augmented Lagrange multiplier algorithm is applied to find the optimal solution. Finally, the 1D denoised signal is obtained by applying the diagonal averaging method to the obtained signal dominant matrix. Computer numerical simulation results show that the authors' proposed method outperforms the existing methods.

show abstract

Mutual singular spectrum analysis for bioacoustics classification

Cited by 12 publications

References 13 publications

Discriminative Singular Spectrum Analysis for Bioacoustic Classification

Discriminative Singular Spectrum Analysis for Bioacoustic Classification

Deep Convex Representations: Feature Representations for Bioacoustics Classification

Singular spectral analysis‐based denoising without computing singular values via augmented Lagrange multiplier algorithm

Contact Info

Product

Resources

About