Pavol Harar

• Doctor of Philosophy
• Computational Scientist for BioAI & CryoET at Institute of Science and Technology Austria

In situ cryo-electron tomography (cryo-ET) has emerged as the method of choice to investigate structures of biomolecules in their native context. However, challenges remain in the efficient production of large-scale cryo-ET datasets, as well as the community sharing of this information-rich data. Here, we applied a cryogenic plasma-based focused io...

We present an algorithm and package, Redistributor, which forces a collection of scalar samples to follow a desired distribution. When given independent and identically distributed samples of some random variable S and the continuous cumulative distribution function of some desired target T, it provably produces a consistent estimator of the transf...

In cryo-electron microscopy, accurate particle localization and classification are imperative. Recent deep learning solutions, though successful, require extensive training data sets. The protracted generation time of physics-based models, often employed to produce these data sets, limits their broad applicability. We introduce FakET, a method base...

Motor speech disorders in patients with Parkinson’s disease (PD), collectively referred to as hypokinetic dysarthria, are the early markers of the disease. Acoustic speech features are, therefore, suitable digital biomarkers for the diagnosis and monitoring of this pathological phenomenon. At the same time, it is clear that language plays an essent...

Background: Due to the ongoing COVID-19 pandemic, demand for diagnostic testing has increased drastically, resulting in shortages of necessary materials to conduct the tests and overwhelming the capacity of testing laboratories. The supply scarcity and capacity limits affect test administration: priority must be given to hospitalized patients and s...

Automatic objective non-invasive detection of pathological voice based on computerized analysis of acoustic signals can play an important role in early diagnosis, progression tracking, and even effective treatment of pathological voices. In search towards such a robust voice pathology detection system, we investigated three distinct classifiers wit...

The Table 3 was published incorrectly in the original publication of the article.

We provide a comparison of general strategies for group testing in view of their application to medical diagnosis in the current COVID-19 pandemic. We find significant efficiency gaps between different group testing strategies in realistic scenarios for SARS-CoV-2 testing, highlighting the need for an informed decision of the pooling protocol depen...

The use of orthogonal projections on high-dimensional input and target data in learning frameworks is studied. First, we investigate the relations between two standard objectives in dimension reduction, preservation of variance and of pairwise relative distances. Investigations of their asymptotic correlation as well as numerical experiments show t...

The article was originally published by the journal with an incorrect title.

This paper introduces Gabor scattering, a feature extractor based on Gabor frames and Mallat’s scattering transform. By using a simple signal model for audio signals, specific properties of Gabor scattering are studied. It is shown that, for each layer, specific invariances to certain signal characteristics occur. Furthermore, deformation stability...

Automatic objective non-invasive detection of pathological voice based on computerized analysis of acoustic signals can play an important role in early diagnosis, progression tracking and even effective treatment of pathological voices. In search towards such a robust voice pathology detection system we investigated 3 distinct classifiers within su...

This paper describes a preliminary investigation of Voice Pathology Detection using Deep Neural Networks (DNN). We used voice recordings of sustained vowel /a/ produced at normal pitch from German corpus Saarbruecken Voice Database (SVD). This corpus contains voice recordings and electroglottograph signals of more than 2 000 speakers. The idea behi...

Recent, extremely successful methods in deep learning, such as convolutional neural networks (CNNs) have originated in machine learning for images. When applied to music signals and related music information retrieval (MIR) problems, researchers often apply standard FFT-based signal processing methods in order to create an image from the raw audio...

The use of orthogonal projections on high-dimensional input and target data in learning frameworks is studied. First, we investigate the relations between two standard objectives in dimension reduction, maximizing variance and preservation of pairwise relative distances. The derivation of their asymptotic correlation and numerical experiments tell...

In search towards a robust voice pathology detection system (VPD), we investigated three distinct classifiers within supervised learning and anomaly detection paradigms on data from four different databases with the aim to: 1) Investigate whether it is possible to build a robust VPD system using currently available resources and mentioned classifie...

BUT-CZAS (Brno University of Technology, Czech Anechoic Speech) is a novel database of human voice recordings, acquired in the anechoic chamber. The database consists of 405 mono recordings of the reading task in the Czech language acquired using bit depth of 24 bit and sampling rate of 48 kHz. In total, 18 speakers (9 women, 9 men) aged between 16...

Lots of voice pathologies are not being diagnosed and treated due to a lack of training, time or appropriate equipment of general practitioners. We are aiming for early diagnosis using quick preventive tests, without extensive training and without the need for expensive equipment. Which would point the patient to a specialized voice therapist if ne...

This paper describes a preliminary investigation of Voice Pathology Detection using Deep Neural Networks (DNN). We used voice recordings of sustained vowel /a/ produced at normal pitch from German corpus Saarbruecken Voice Database (SVD). This corpus contains voice recordings and electroglottograph signals of more than 2 000 speakers. The idea behi...

This paper introduces Gabor scattering, a feature extractor based on Gabor frames and Mallat's scattering transform. By using a simple signal model for audio signals specific properties of Gabor scattering are studied. It is shown that for each layer, specific invariances to certain signal characteristics occur. Furthermore, deformation stability o...