Statistical Model-based Approaches Research Articles

Genetic Algorithm-Based Adaptive Wiener Gain for Speech Enhancement Using an Iterative Posterior NMF

In this paper, we propose a genetic algorithm-based adaptive Wiener gain for speech enhancement using an iterative posterior non-negative matrix factorization (NMF). In the recent past, NMF-based Wiener filtering methods were used to improve the performance of speech enhancement, which has shown that they provide better performance when compared with conventional NMF methods. But performance degrades in non-stationary noise environments. Template-based approaches are more robust and perform better in non-stationary noise environments compared to statistical model-based approaches but are dependent on a priori information. Combining the approaches avoids the drawbacks of both. To improve the performance further, speech and noise bases are adapted simultaneously in the NMF approach. The usage of Super-Gaussian constraints in iterative NMF still improves the performance in non-stationary noise. The silence frame is a challenging task in the case of NMF; still there will be some amount of noise present in those frames. For further enhancement, we have combined with a genetic algorithm (GA)-based adaptive Wiener filter which performs well in denoising and also the GA search the adaptive [Formula: see text] allows us to control the trade-off between fitting the observed spectrogram of mixed speech and noise achieving high likelihood under our prior model. The proposed method outperforms other benchmark algorithms in terms of the source to distortion ratio (SDR), short-time objective intelligibility (STOI), and perceptual evaluation of speech quality (PESQ).

Seismic hazard analysis for engineering sites based on the stochastic finite-fault method

Seismic hazard analyses are mainly performed using either deterministic or probabilistic methods. However, there are still some defects in these statistical model-based approaches for regional seismic risk assessment affected by the near-field of large earthquakes. Therefore, we established a deterministic seismic hazard analysis method that can characterize the entire process of ground motion propagation based on stochastic finite-fault simulation, and we chose the site of the Xiluodu dam to demonstrate the method. This method can characterize earthquake source properties more realistically than other methods and consider factors such as the path and site attenuation of seismic waves. It also has high computational efficiency and is convenient for engineering applications. We first analyzed the complexity of seismogenic structures in the Xiluodu dam site area, and then an evaluation system for ground motion parameters that considers various uncertainties is constructed based on a stochastic finite-fault simulation. Finally, we assessed the seismic hazard of the dam site area comprehensively. The proposed method was able to take into account the complexity of the seismogenic structures affecting the dam site and provide multi-level parameter evaluation results corresponding to different risk levels. These results can be used to construct a dam safety assessment system of an earthquake in advance that provides technical support for rapidly and accurately assessing the post-earthquake damage state of a dam, thus determining the influence of an earthquake on dam safety and mitigating the risk of potential secondary disasters.

Malaria micro-stratification using routine surveillance data in Western Kenya

BackgroundThere is an increasing need for finer spatial resolution data on malaria risk to provide micro-stratification to guide sub-national strategic plans. Here, spatial-statistical techniques are used to exploit routine data to depict sub-national heterogeneities in test positivity rate (TPR) for malaria among patients attending health facilities in Kenya.MethodsRoutine data from health facilities (n = 1804) representing all ages over 24 months (2018–2019) were assembled across 8 counties (62 sub-counties) in Western Kenya. Statistical model-based approaches were used to quantify heterogeneities in TPR and uncertainty at fine spatial resolution adjusting for missingness, population distribution, spatial data structure, month, and type of health facility.ResultsThe overall monthly reporting rate was 78.7% (IQR 75.0–100.0) and public-based health facilities were more likely than private facilities to report ≥ 12 months (OR 5.7, 95% CI 4.3–7.5). There was marked heterogeneity in population-weighted TPR with sub-counties in the north of the lake-endemic region exhibiting the highest rates (exceedance probability > 70% with 90% certainty) where approximately 2.7 million (28.5%) people reside. At micro-level the lowest rates were in 14 sub-counties (exceedance probability < 30% with 90% certainty) where approximately 2.2 million (23.1%) people lived and indoor residual spraying had been conducted since 2017.ConclusionThe value of routine health data on TPR can be enhanced when adjusting for underlying population and spatial structures of the data, highlighting small-scale heterogeneities in malaria risk often masked in broad national stratifications. Future research should aim at relating these heterogeneities in TPR with traditional community-level prevalence to improve tailoring malaria control activities at sub-national levels.

The Speech Enhancement via Attention Masking Network (SEAMNET): An End-to-end System for Joint Suppression of Noise and Reverberation

This paper proposes the Speech Enhancement via Attention Masking Network (SEAMNET), a neural network-based end-to-end single-channel speech enhancement system designed for joint suppression of noise and reverberation. It formalizes an end-to-end network architecture, referred to as b-Net , which accomplishes noise suppression through attention masking in a learned embedding space. A key contribution of SEAMNET is that the b-Net architecture contains both an enhancement and an autoencoder path. This paper proposes a novel loss function which simultaneously trains both the enhancement and the autoencoder paths, so that disabling the masking mechanism during inference causes SEAMNET to reconstruct the input speech signal. This allows dynamic control of the level of suppression applied by SEAMNET via a minimum gain level, which is not possible in other state-of-the-art approaches to end-to-end speech enhancement. This paper also proposes a perceptually-motivated waveform distance measure. In addition to the b-Net architecture, this paper proposes a novel method for designing target waveforms for network training, so that joint suppression of additive noise and reverberation can be performed by an end-to-end enhancement system, which has not been previously possible. Experimental results show the SEAMNET system to outperform a variety of state-of-the-art baselines systems, both in terms of objective speech quality measures and subjective listening tests. Finally, this paper draws parallels between SEAMNET and conventional statistical model-based enhancement approaches, offering interpretability of many network components.

Adaptive Batch Size Image Merging Steganography and Quantized Gaussian Image Steganography

In digital image steganography, the statistical model of an image is essential for hiding data in less detectable regions and achieving better security. This has been addressed in the literature where different cost-based and statistical model-based approaches were proposed. However, due to the usage of heuristically defined distortions and non-constrained message models, resulting in numerically solvable equations, there is no closed-form expression for security as a function of payload. The closed-form expression is crucial for a better insight into image steganography problem and also improving performance of batch steganography algorithms. Here, we develop a statistical framework for image steganography in which the cover and the stego messages are modeled as multivariate Gaussian random variables. We propose a novel Gaussian embedding model by maximizing the detection error of the most common optimal detectors within the adopted statistical model. Furthermore, we extend the formulation to cost-based steganography, resulting in a universal embedding scheme that improves empirical results of current cost-based and statistical model-based approaches. This methodology and its presented solution, by reason of assuming a continuous hidden message, remains the same for any embedding scenario. Afterward, the closed-form detection error is derived within the adopted model for image steganography and it is extended to batch steganography. Thus, we introduce Adaptive Batch size Image Merging steganographer, AdaBIM , and mathematically prove it outperforms the state-of-the-art batch steganography method and further verify its superiority by experiments.

Speech enhancement using posterior regularized NMF with bases update

In this paper, a combination of statistical model-based approach and Non-negative Matrix Factorization (NMF)-based approach with on-line update of speech and noise bases for speech enhancement is proposed. Template-based approaches are more robust and perform better than non-stationary noises compared to statistical model-based approaches but are dependent on a priori information. Combining the approaches avoids the drawbacks of both. To improve the performance further, speech and noise bases are adapted simultaneously in NMF approach with the help of the estimated speech presence probability (SPP). The proposed method outperforms other benchmark algorithms in terms of perceptual evaluation of speech quality (PESQ) and source-to-distortion ratio (SDR) in stationary and non-stationary noise environment conditions with matched and mismatched noise basis.

NMF-Based Speech Enhancement Using Bases Update

This letter presents a speech enhancement technique combining statistical models and non-negative matrix factorization (NMF) with on-line update of speech and noise bases. The statistical model-based enhancement methods have been known to be less effective to non-stationary noises while the template-based enhancement techniques can deal with them quite well. However, the template-based enhancement techniques usually rely on a priori information. To overcome the shortcomings of both approaches, we propose a novel speech enhancement method that combines the statistical model-based enhancement scheme with the NMF-based gain function. For a better performance in time-varying noise environments, both the speech and noise bases of NMF are adapted simultaneously with the help of the estimated speech presence probability. Experimental results showed that the proposed method outperformed not only the statistical model-based and NMF approaches, but also their combination in various noise environments.

Mammalogy. 6th ed.

Vaughan, T. A., J. N. Ryan, and N. J. Czaplewski. 2015. Mammalogy . 6th ed. Jones & Bartlett, Burlington, Massachusetts, 755 pp. ISBN 978-1-284-03209-3, price (paperback), $141.83. As undoubtedly was the case for many, Vaughan’s Mammalogy was my 1st introduction to the discipline. Indeed my Mammalogy course (at the University of Vermont) shaped my career and convinced me I wanted to become a biologist. It was, therefore, with a great deal of respect that I agreed to write this review. This is a standard classic in mammalogy and the 6th edition will remain so. Although the same overall structure of the 5th edition has been maintained, there are a few changes since the 5th edition. First, Chapters 2 and 3 have swapped places so now the mammal origins chapter precedes the chapter on mammalian characters. This change seems a little awkward to me; it’s far easier to highlight important transitions in the evolution of mammals if students already are familiar with ancestral and derived states. The rest of the chapters are arranged in the same manner (this is both a strength and a weakness, see below) and the Table of Contents is less detailed than that in the 5th edition. Chapter 1 introduces classification and phylogenetics. The example of parsimony applied to nucleotide sequence data is retained from the 5th edition. This would be fine if it were noted that use of parsimony alone is obsolete and statistical model-based approaches were mentioned explicitly (instead of implicitly through the notion of molecular clocks). However, as written, the description of phylogenetic analysis misrepresents the current state of the discipline. The references cited for more information on phylogeny estimation are obsolete or even nonexistent (the authors suggest that PAUP, a software package, explains phylogenetic methods). Chapter 2 describes the origin of mammals and is a mixed bag. There is, once again, an excellent presentation of early synapsids, therapsids, and cynodonts and the description of the evolution of mammalian ear ossicles … Department of Biological Sciences, Box 443051, University of Idaho, Moscow, ID 83844-3051, USA; e-mail: jacks{at}uidaho.edu.

Voice Activity Detection Based on Multiple Statistical Models

One of the key issues in practical speech processing is to achieve robust voice activity detection (VAD) against the background noise. Most of the statistical model-based approaches have tried to employ the Gaussian assumption in the discrete Fourier transform (DFT) domain, which, however, deviates from the real observation. For a class of VAD algorithms based on Gaussian model and Laplacian model, we incorporate complex Laplacian probability density function to our analysis of statistical properties. Since the statistical characteristics of the speech signal are differently affected by the noise types and levels, to cope with the time-varying environments, our approach is aimed at finding adaptively an appropriate statistical model in an online fashion. The performance of the proposed VAD approaches in stationary noise environment is evaluated with the aid of an objective measure.

Towards the handling of uncertainties in statistical FDI

AbstractThe paper provides fundamental steps towards addressing the theoretically and practically important issue of handling uncertainties in statistical model-based approaches to fault detection and isolation (FDI). Two main types of uncertainties are distinguished: uncertainties in parameters on the one hand; uncertainties due to under-modeling as well as those resulting from changes in functioning modes, on the other hand. It is suggested that two different theories should be used.

Methodological Issues in Spatial Microsimulation Modelling for Small Area Estimation

In this paper, some vital methodological issues of spatial microsimulation modelling for small area estimation have been addressed, with a particular emphasis given to the reweighting techniques. Most of the review articles in small area estimation have highlighted methodologies based on various statistical models and theories. However, spatial microsimulation modelling is emerging as a very useful alternative means of small area estimation. Our findings demonstrate that spatial microsimulation models are robust and have advantages over other type of models used for small area estimation. The technique uses different methodologies typically based on geographic models and various economic theories. In contrast to statistical model-based approaches, the spatial microsimulation model-based approaches can operate through reweighting techniques such as GREGWT and combinatorial optimization. A comparison between reweighting techniques reveals that they are using quite different iterative algorithms and that their properties also vary. The study also points out a new method for spatial microsimulation modelling

Voice activity detection based on multiple statistical models

One of the key issues in practical speech processing is to achieve robust voice activity detection (VAD) against the background noise. Most of the statistical model-based approaches have tried to employ the Gaussian assumption in the discrete Fourier transform (DFT) domain, which, however, deviates from the real observation. In this paper, we propose a class of VAD algorithms based on several statistical models. In addition to the Gaussian model, we also incorporate the complex Laplacian and Gamma probability density functions to our analysis of statistical properties. With a goodness-of-fit tests, we analyze the statistical properties of the DFT spectra of the noisy speech under various noise conditions. Based on the statistical analysis, the likelihood ratio test under the given statistical models is established for the purpose of VAD. Since the statistical characteristics of the speech signal are differently affected by the noise types and levels, to cope with the time-varying environments, our approach is aimed at finding adaptively an appropriate statistical model in an online fashion. The performance of the proposed VAD approaches in both the stationary and nonstationary noise environments is evaluated with the aid of an objective measure.

Statistical Model-Based Approaches to Audio Restoration and Analysis

In this paper we provide an overview of model-based approaches to audio processing, with an emphasis on restoration and interpretable analysis. Application areas include denoising/declicking and correction of nonlinear distortions such as clipping and poor quantisation. We highlight the potential benefits arising from a carefully constructed model-based approach to audio problems, in which any prior knowledge about the generative mechanism for the data can be incorporated quantitatively into the restoration framework. We propose that model-based methods are the principal means by which high level inferences about an audio signal can be achieved in future work.