Search
Filters
total: 11099
-
Catalog
- Publications 7184 available results
- Journals 204 available results
- Conferences 107 available results
- People 168 available results
- Inventions 1 available results
- Projects 8 available results
- Laboratories 1 available results
- e-Learning Courses 496 available results
- Events 29 available results
- Open Research Data 2901 available results
displaying 1000 best results Help
Search results for: NEURAL TEXT-TO-SPEECH MULTILINGUAL SYNTHESIS VOICE CONVERSION SYNTHETIC DATA NORMALISING FLOWS
-
Text & Talk
Journals -
Robustness in Compressed Neural Networks for Object Detection
PublicationModel compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a large effect on noisy cases or objects belonging to less frequent classes. It is a crucial problem from the perspective of the models' safety, especially for object detection in the autonomous driving...
-
Minimizing Distribution and Data Loading Overheads in Parallel Training of DNN Acoustic Models with Frequent Parameter Averaging
PublicationIn the paper we investigate the performance of parallel deep neural network training with parameter averaging for acoustic modeling in Kaldi, a popular automatic speech recognition toolkit. We describe experiments based on training a recurrent neural network with 4 layers of 800 LSTM hidden states on a 100-hour corpora of annotated Polish speech data. We propose a MPI-based modification of the training program which minimizes the...
-
Neural network agents trained by declarative programming tutors
PublicationThis paper presents an experimental study on the development of a neural network-based agent, trained using data generated using declarative programming. The focus of the study is the application of various agents to solve the classic logic task – The Wumpus World. The paper evaluates the effectiveness of neural-based agents across different map configurations, offering a comparative analysis to underline the strengths and limitations...
-
ATOMIC DATA AND NUCLEAR DATA TABLES
Journals -
Design and Analysis of Artificial Neural Network (ANN) Models for Achieving Self-Sustainability in Sanitation
PublicationThe present study investigates the potential of using fecal ash as an adsorbent and demonstrates a self-sustaining, optimized approach for urea recovery from wastewater streams. Fecal ash was prepared by heating synthetic feces to 500 °C and then processing it as an adsorbent for urea adsorption from synthetic urine. Since this adsorption approach based on fecal ash is a promising alternative for wastewater treatment, it increases...
-
Elimination of clicks from archive speech signals using sparse autoregressive modeling
PublicationThis paper presents a new approach to elimination of impulsivedisturbances from archive speech signals. The proposedsparse autoregressive (SAR) signal representation is given ina factorized form - the model is a cascade of the so-called formantfilter and pitch filter. Such a technique has been widelyused in code-excited linear prediction (CELP) systems, as itguarantees model stability. After detection of noise pulses usinglinear...
-
Toward Intelligent Vehicle Intrusion Detection Using the Neural Knowledge DNA
PublicationIn this paper, we propose a novel intrusion detection approach using past driving experience and the neural knowledge DNA for in-vehicle information system security. The neural knowledge DNA is a novel knowledge representation method designed to support discovering, storing, reusing, improving, and sharing knowledge among machines and computing systems. We examine our approach for classifying malicious vehicle control commands...
-
Hydraulic loss coefficients in 1D Flows
PublicationWyniki pomiarów pokazują, że współczynniki strat energii mechanicznej dla przepływów niejednostajnych i nieustalonych przyjmują wartości zdecydowanie większe, niż tradycyjnie przyjmowane dla ruchu jednostajnego. W pracy przedstawiono ananizę możliwych przypadków ruchu oraz wyniki obserwacji laboratoryjnych.Wykazano, że wzrost wartości współczynników jest uzasadniony fizykalnie.Zaproponowano robocza metodą ich korygowania.
-
Prediction of metal deformation due to line heating; an alternative method of mechanical bending, based on artificial neural network approach
PublicationLine heating is one of the alternative methods of forming metals and this kind of forming uses the heating torch as a source of heat input. During the process, many parameters are considered like the size of the substrate, thickness, cooling method, source power intensity, the travel speed of the power source, the sequence of heating, and so on. It is important to analyze the factors affecting the...
-
Adding Interpretability to Neural Knowledge DNA
PublicationThis paper proposes a novel approach that adds the interpretability to Neural Knowledge DNA (NK-DNA) via generating a decision tree. The NK-DNA is a promising knowledge representation approach for acquiring, storing, sharing, and reusing knowledge among machines and computing systems. We introduce the decision tree-based generative method for knowledge extraction and representation to make the NK-DNA more explainable. We examine...
-
Youth Voice Journal
Journals -
Carbon Resources Conversion
Journals -
Contemporary Voice of Dalit
Journals -
Endoscopic Videos Deinterlacing and On-Screen Text and Light Flashes Removal and Its Influence on Image Analysis Algorithms' Efficiency
PublicationIn this article, deinterlacing and removing on- screen text and light flashes methods on endoscopic video images are discussed. The research is intended to improve disease recognition algorithms' performance. In the article, four configurations of deinterlacing methods and another four configurations of text and flashes removal methods are described and examined. The efficiency of endoscopic video analysis algorithms is measured...
-
Musical Instrument Tagging Using Data Augmentation and Effective Noisy Data Processing
PublicationDeveloping signal processing methods to extract information automatically has potential in several applications, for example searching for multimedia based on its audio content, making context-aware mobile applications (e.g., tuning apps), or pre-processing for an automatic mixing system. However, the last-mentioned application needs a significant amount of research to reliably recognize real musical instruments in recordings....
-
Microwave radiation in the synthesis of urethane prepolymers
PublicationThis paper describes the use of microwave radiation in the synthesis of urethane prepolymers in bulk (without solvent). The prepolymers were synthesized using 1,6-hexamethylene diisocyanate (HDI) and poly (ε-caprolactone) diol (PCL) at a molar ratio of 4:1. The reaction was carried out without a catalyst in the reactor with a conventional heating system (oil bath) or in the microwave reactor (MW Reactor NOVA 09) at temperatures...
-
International Multilingual Research Journal
Journals -
Translation and Translanguaging in Multilingual Contexts
Journals -
JOURNAL OF MULTILINGUAL AND MULTICULTURAL DEVELOPMENT
Journals -
Human-computer interactions in speech therapy using a blowing interface
PublicationIn this paper we present a new human-computer interface for the quantitative measurement of blowing activities. The interface can measure the air flow and air pressure during the blowing activity. The measured values are stored and used to control the state of the graphical objects in the graphical user interface. In speech therapy children will find easier to play attractive therapeutic games than to perform repetitive and tedious,...
-
Data in Brief
Journals -
Scientific Data
Journals -
Distributed correlations and information flows within a hybrid multipartite quantum-classical system
PublicationUnderstanding the non-Markovian mechanisms underlying the revivals of quantum entanglement in the presence of classical environments is central in the theory of quantum information. Tentative interpretations have been given by either the role of the environment as a control device or the concept of hidden entanglement. We address this issue from an information-theoretic point of view. To this aim, we consider a paradigmatic tripartite...
-
Vident-synth: a synthetic intra-oral video dataset for optical flow estimation
Open Research DataWe introduce Vident-synth, a large dataset of synthetic dental videos with corresponding ground truth forward and backward optical flows and occlusion masks. It can be used for:
-
Speech and Drama
Journals -
LANGUAGE AND SPEECH
Journals -
Data Analysis in Bridge of Data
PublicationThe chapter presents the data analysis aspects of the Bridge of Data project. The software framework used, Jupyter, and its configuration are presented. The solution’s architecture, including the TRYTON supercomputer as the underlying infrastructure, is described. The use case templates provided by the Stat-reducer application are presented, including data analysis related to spatial points’ cloud-, audio- and wind-related research.
-
Sample Rate Conversion Based on Frequency Response Masking Filter
PublicationThe sample rate conversion with high resampling ratios requires low-pass digital filters with very narrow transition band which results in high computational complexity and makes filter design problematic. Therefore in this work we propose to use the FRM method, which breaks the filter with a narrow transition band into a group of filters with reduced design requirements. These decreases the number of non-zero coefficients and...
-
Data Warehouses 2023/2024
e-Learning CoursesThe aim of the course is to familiarize students with the development process of data warehouses for BI systems. The course is prepared for students of Data Engineering.
-
Categorization of emotions in dog behavior based on the deep neural network
PublicationThe aim of this article is to present a neural system based on stock architecture for recognizing emotional behavior in dogs. Our considerations are inspired by the original work of Franzoni et al. on recognizing dog emotions. An appropriate set of photographic data has been compiled taking into account five classes of emotional behavior in dogs of one breed, including joy, anger, licking, yawning, and sleeping. Focusing on a particular...
-
A Bayesian regularization-backpropagation neural network model for peeling computations
PublicationA Bayesian regularization-backpropagation neural network (BRBPNN) model is employed to predict some aspects of the gecko spatula peeling, viz. the variation of the maximum normal and tangential pull-off forces and the resultant force angle at detachment with the peeling angle. K-fold cross validation is used to improve the effectiveness of the model. The input data is taken from finite element (FE) peeling results. The neural network...
-
Identification of the Contamination Source Location in the Drinking Water Distribution System Based on the Neural Network Classifier
PublicationThe contamination ingression to the Water Distribution System (WDS) may have a major impact on the drinking water consumers health. In the case of the WDS contamination the data from the water quality sensors may be efficiently used for the appropriate disaster management. In this paper the methodology based on the Learning Vector Quantization (LVQ) neural network classifier for the identification of the contamination source location...
-
Investigations of Energy Conversion and Surface Effect for Laser-Illuminated Gold Nanorod Platforms
PublicationAchieving a quick temperature increase is a burning issue for biophysical applications, like germ inactivation and tumor ablation, and for energy performances, like solar collectors and steam generators. Based on the plasmon resonance phenomenon, noble metallic nanoparticles have emerged as promising weapons due to their very high biocompatibility, optical properties, and high surface-to-volume ratio, increasing energy conversion...
-
A Wind Energy Conversion System Based on a Generator with Modulated Magnetic Flux
PublicationIn this work, the concept of an energy conversion system for wind turbines based on the modified permanent magnet synchronous generator (PMSG) is presented. In the generator, a pair of three-phase windings is used, one of which is connected in a “star” and the second in a “delta” configuration. At the outputs of both windings, two six-pulse uncontrolled (diode) rectifiers are included. These rectifiers are mutually coupled by a...
-
An analysis of solar energy conversion systems based on photon and thermal processes
PublicationSolar spectral irradiance covers a fairly broad wavelength range. Solar radiation is part of the electromagnetic spectrum which is described by the concept of wave-particle duality. The corpuscular theory of electromagnetic radiation states that energy is transmitted by photons. Photons carry specific amounts of energy which can be used to convert solar energy into other types of energy, in particular electricity. The internal...
-
Key issues in modeling and optimization of lignocellulosic biomass fermentative conversion to gaseous biofuels
PublicationThe industrial-scale production of lignocellulosic-based biofuels from biomass is expected to benefit society and the environment. The main pathways of residues processing include advanced hydrolysis and fermentation, pyrolysis, gasification, chemical synthesis and biological processes. The products of such treatment are second generation biofuels. The degree of fermentation of organic substances depends primarily on their composition...
-
Neural Network Subgraphs Correlation with Trained Model Accuracy
PublicationNeural Architecture Search (NAS) is a computationally demanding process of finding optimal neural network architecture for a given task. Conceptually, NAS comprises applying a search strategy on a predefined search space accompanied by a performance evaluation method. The design of search space alone is expected to substantially impact NAS efficiency. We consider neural networks as graphs and find a correlation between the presence...
-
SkinDepth - synthetic 3D skin lesion database
Open Research DataSkinDepth is the first synthetic 3D skin lesion database. The release of SkinDepth dataset intends to contribute to the development of algorithms for:
-
Neural modelling of dynamic systems with time delays based on an adjusted NEAT algorithm
PublicationA problem related to the development of an algorithm designed to find an architecture of artificial neural network used for black-box modelling of dynamic systems with time delays has been addressed in this paper. The proposed algorithm is based on a well-known NeuroEvolution of Augmenting Topologies (NEAT) algorithm. The NEAT algorithm has been adjusted by allowing additional connections within an artificial neural network and...
-
Big Data processing frameworks - 2022
e-Learning CoursesInformatics, postgraduate studies Data Engineering, undergraduate studies
-
Big Data processing frameworks - 2023
e-Learning CoursesInformatics, postgraduate studies Data Engineering, undergraduate studies
-
Big Data processing frameworks - 2024
e-Learning CoursesInformatics, postgraduate studies Data Engineering, undergraduate studies
-
Rediscovering Automatic Detection of Stuttering and Its Subclasses through Machine Learning—The Impact of Changing Deep Model Architecture and Amount of Data in the Training Set
PublicationThis work deals with automatically detecting stuttering and its subclasses. An effective classification of stuttering along with its subclasses could find wide application in determining the severity of stuttering by speech therapists, preliminary patient diagnosis, and enabling communication with the previously mentioned voice assistants. The first part of this work provides an overview of examples of classical and deep learning...
-
ACS Synthetic Biology
Journals -
Synthetic and Systems Biotechnology
Journals -
Comparison of selected clustering algorithms of raw data obtained by interferometric methods using artificial neural networks
Publication -
Collaborative Data Acquisition and Learning Support
PublicationWith the constant development of neural networks, traditional algorithms relying on data structures lose their significance as more and more solutions are using AI rather than traditional algorithms. This in turn requires a lot of correctly annotated and informative data samples. In this paper, we propose a crowdsourcing based approach for data acquisition and tagging with support for Active Learning where the system acts as an...
-
Biologically active compounds based on the carbazole scaffold - synthetic and mechanistic aspects
PublicationDoctoral dissertation is divided into three main parts: introduction, results and discussion and experimental. The introduction is divided into four main parts which describe: 5-hydroxytryptamine receptors, the most popular antidepressants, new compounds based on the carbazole structure with affinity for serotonin receptors, telomeres and telomerase with their functions, telomerase inhibition strategies, carbazoles approved in...
-
Clinical situations text database for Polish language
Open Research DataDataset contains a database of anonymized texts in Polish for the purposes of building a medical speech corpus, for clinical situations in the following areas: medical interview, interview and description of the result of an oncological examination, description of a radiological examination, description of a pathomorphological examination, description...