Filters
total: 1360
filtered: 509
Search results for: TEXT-TO-SPEECH TRANSCRIPTION
-
Wikipedia Articles Representation with Matrix'u
PublicationIn the article we evaluate different text representation methods used for a task of Wikipedia articles categorization. We present the Matrix’u application used for creating computational datasets ofWikipedia articles. The representations have been evaluated with SVM classifiers used for reconstruction human made categories.
-
Rural Landscape Planning for Sustainable Development. The Case of Poland
PublicationThis text results from theoretical study on the possibilities of rural landscape renovation in Poland. The introduction marks new spatial phenomena and the scope of their influence. It indicates social and cultural reasons of the changes, and states the need of their renewed interpretation. The second part of the article contains a description of the degrading cultural landscape of the country and presents its features. It then...
-
EU-Turkey Customs Union and Bilateral Foreign Direct Investment Flows
PublicationMain aim of this text is presentation of the effects of customs union between the European Union and turkey on bilateral FDI flows in light of the theory of linkages between economic integration and FDI flows. First section of the text is a survey of main theoretical links between economic integration and FDI flows. Second section focuses on the history and scope of the customs union. Third and fourth sections are empirical and...
-
Evaluation Criteria for Affect-Annotated Databases
PublicationIn this paper a set of comprehensive evaluation criteria for affect-annotated databases is proposed. These criteria can be used for evaluation of the quality of a database on the stage of its creation as well as for evaluation and comparison of existing databases. The usefulness of these criteria is demonstrated on several databases selected from affect computing domain. The databases contain different kind of data: video or still...
-
Intelligent multimedia solutions supporting special education needs.
PublicationThe role of computers in school education is briefly discussed. Multimodal interfaces development history is shortly reviewed. Examples of applications of multimodal interfaces for learners with special educational needs are presented, including interactive electronic whiteboard based on video image analysis, application for controlling computers with facial expression and speech stretching audio interface representing audio modality....
-
Intelligent video and audio applications for learning enhancement
PublicationThe role of computers in school education is briefly discussed. Multimodal interfaces development history is shortly reviewed. Examples of applications of multimodal interfaces for learners with special educational needs are presented, including interactive electronic whiteboard based on video image analysis, application for controlling computers with facial expression and speech stretching audio interface representing audio modality....
-
The role of epigenetics in regeneration
PublicationComplex changes in chromatin structure and at the transcriptional level occur from the creation of a single parental gamete throughout fertilization, embryo development and the life of an adult organism. Epigenetic changes, such as methylation and hydroxymethylation of DNA or histone methylation and acetylation, are an important part of these processes. Epigenetic regulation has an essential influence on gene expression level. DNA...
-
Improving css-KNN Classification Performance by Shifts in Training Data
PublicationThis paper presents a new approach to improve the performance of a css-k-NN classifier for categorization of text documents. The css-k-NN classifier (i.e., a threshold-based variation of a standard k-NN classifier we proposed in [1]) is a lazy-learning instance-based classifier. It does not have parameters associated with features and/or classes of objects, that would be optimized during off-line learning. In this paper we propose...
-
A Method of MOS Evaluation for Video Based Services
PublicationThis paper deals with a method for QoE evaluation for the services transmitting large amount of data perceived by the end user in relatively short time periods, e.g. streaming video in mobile operator...
-
CONTEMPORARY ART AND CIVIC ENGAGEMENT
PublicationThe paper aims to explore the potential role of contemporary art as a catalyst for social transformation and civic engagement. The research focuses on the visual arts and their power to change social attitudes in contemporary society. On the basis of theoretical, transdisciplinary approaches and analysis of artwork the paper investigates emerging forms of art and how they address pressing social issues and concerns that would otherwise...
-
Analysis-by-synthesis paradigm evolved into a new concept
PublicationThis work aims at showing how the well-known analysis-by-synthesis paradigm has recently been evolved into a new concept. However, in contrast to the original idea stating that the created sound should not fail to pass the foolproof synthesis test, the recent development is a consequence of the need to create new data. Deep learning models are greedy algorithms requiring a vast amount of data that, in addition, should be correctly...
-
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...
-
Improved RSS-Based DoA Estimation Accuracy in Low-Profile ESPAR Antenna Using SVM Approach
PublicationIn this paper, we have shown how the overall performance of direction-of-arrival (DoA) estimation using lowprofile electronically steerable parasitic array radiator (ESPAR) antenna, which has been proposed for Internet of Things (IoT) applications, can significantly be improved when support vector machine (SVM) approach is applied. Because the SVM-based DoA estimation method used herein relies solely...
-
Selection of Features for Multimodal Vocalic Segments Classification
PublicationEnglish speech recognition experiments are presented employing both: audio signal and Facial Motion Capture (FMC) recordings. The principal aim of the study was to evaluate the influence of feature vector dimension reduction for the accuracy of vocalic segments classification employing neural networks. Several parameter reduction strategies were adopted, namely: Extremely Randomized Trees, Principal Component Analysis and Recursive...
-
A study on signal processing methods applied to hearing aids
PublicationThis paper presents a short survey on current technology available in hearing aids with a focus on digital signal processing techniques used. First, factors influencing the hearing aid effectiveness are introduced. Then, examples of the present DSP methods and strategies are provided. Also, a description of current limitations of hearing aids and future trends of development are shown. Finally, the notion of computational auditory...
-
Anticancer imidazoacridinone C-1311 inhibits hypoxia-inducible factor-1α (HIF-1α), vascular endothelial growth factor (VEGF) and angiogenesis
PublicationAntitumor imidazoacridinone C-1311 is a DNA-reactive topoisomerase II and FLT3 receptor tyrosine kinase inhibitor. Here, we demonstrate the mechanism of C-1311 inhibitory action on novel targets: hypoxia-inducible factor-1α (HIF-1α), vascular-endothelial growth factor (VEGF), and angiogenesis. In a cell-free system, C-1311 prevented HIF-1α binding to an oligonucleotide encompassing a canonical hypoxia-responsive element (HRE),...
-
Towards a Framework for Context Awareness Based on Textual Process Data
PublicationContext awareness is critical for the successful execution of processes. In the abundance of business process management (BPM) research, frameworks exclusively devoted to extracting context from textual process data are scarce. With the deluge of textual data and its increasing value for organizations, it be-comes essential to employ relevant text analytics techniques to increase the awareness of business process (BP) workers,...
-
Information Extraction from Polish Radiology Reports using Language Models
PublicationRadiology reports are vital elements of directing patient care. They are usually delivered in free text form, which makes them prone to errors, such as omission in reporting radiological findings and using difficult-to-comprehend mental shortcuts. Although structured reporting is the recommended method, its adoption continues to be limited. Radiologists find structured reports too limiting and burdensome. In this paper, we propose...
-
Improving the Accuracy in Sentiment Classification in the Light of Modelling the Latent Semantic Relations
PublicationThe research presents the methodology of improving the accuracy in sentiment classification in the light of modelling the latent semantic relations (LSR). The objective of this methodology is to find ways of eliminating the limitations of the discriminant and probabilistic methods for LSR revealing and customizing the sentiment classification process (SCP) to the more accurate recognition of text tonality. This objective was achieved...
-
Path-based methods on categorical structures for conceptual representation of wikipedia articles
PublicationMachine learning algorithms applied to text categorization mostly employ the Bag of Words (BoW) representation to describe the content of the documents. This method has been successfully used in many applications, but it is known to have several limitations. One way of improving text representation is usage of Wikipedia as the lexical knowledge base – an approach that has already shown promising results in many research studies....
-
Just look at to open it up: A biometric verification facility for password autofill to protect electronic documents
PublicationElectronic documents constitute specific units of information, and protecting them against unauthorized access is a challenging task. This is because a password protected document may be stolen from its host computer or intercepted while on transfer and exposed to unlimited offline attacks. The key issue is, therefore, making document passwords hard to crack. We propose to augment a common text password authentication interface...
-
DoA Estimation Using Reconfigurable Antennas in Millimiter-Wave Frequency 5G Systems
PublicationTo achieve low latency and high throughputs, future 5G systems will have to utilize complex antenna systems able to provide beamforming and direction-of-arrival (DoA) estimation capabilities. Most of the concepts available in the literature rely on analog or digital beamforming, which is well developed and can be used both at a base station and in a user terminal. However, in applications, in which...
-
Greenhouse control system design
PublicationCoraz większa populacja i zmniejszające się tereny uprawne wymusza efektywniejsze metody uprawy roślin. Zaradzić temu mogą układu hydroponiczne, które dzięki rozwojowi techniki są w stanie osiągać znacznie większe oraz bardziej jednorodne plony. Jest to możliwe dzięki zaawansowanym systemom opartym na dokładnych urządzeniach pomiarowych, sterowaniu w zamkniętej pętli oraz mikrokontrolerom umożliwiającym...
-
Ocena efektywności przedsięwzięć informatycznych w przedsiębiorstwie
PublicationPrzedmiotem badania rozprawy doktorskiej była metodologia oceny efektywności przedsięwzięć informatycznych w przedsiębiorstwie. Celem badawczym rozprawy było stworzenie skutecznej i bardziej jednoznacznej metody oceny efektywności przedsięwzięć informatycznych w przedsiębiorstwie, opartej o koncepcję adaptacyjną, która pozwalałaby uwzględniać szczególne warunki panujące...
-
MACHINE LEARNING–BASED ANALYSIS OF ENGLISH LATERAL ALLOPHONES
PublicationAutomatic classification methods, such as artificial neural networks (ANNs), the k-nearest neighbor (kNN) and selforganizing maps (SOMs), are applied to allophone analysis based on recorded speech. A list of 650 words was created for that purpose, containing positionally and/or contextually conditioned allophones. For each word, a group of 16 native and non-native speakers were audio-video recorded, from which seven native speakers’...
-
Influence of intermixing at the Ta/CoFeB interface on spin Hall angle in Ta/CoFeB/MgO heterostructures
PublicationWhen a current is passed through a non-magnetic metal with strong spin-orbit coupling, an orthogonal spin current is generated. This spin current can be used to switch the magnetization of an adjacent ferromagnetic layer or drive its magnetization into continuous precession. The interface, which is not necessarily sharp, and the crystallographic structure of the nonmagnetic metal can both affect the strength of current-induced...
-
Contemporary Spaces of Memory - Towards Transdisciplinarity in Architecture
PublicationThe paper explores new phenomena in the contemporary practice of commemoration implemented through architecture. Architectural objects related to memory can be a place where new trends and phenomena appear earlier than in other architectural objects. The text is an attempt to prove that these new spaces of memory are a kind of laboratory where new ideas taking place in architecture and related disciplines are being tested. Research...
-
Resilient Routing in Communication Networks
PublicationThis important text/reference addresses the latest issues in end-to-end resilient routing in communication networks. The work highlights the main causes of failures of network nodes and links, and presents an overview of resilient routing mechanisms, covering issues related to the Future Internet (FI), wireless mesh networks (WMNs), and vehicular ad-hoc networks (VANETs). For each of these network architectures, a selection of...
-
HDAC Inhibitors: Innovative Strategies for Their Design and Applications
PublicationHistone deacetylases (HDACs) are a large family of epigenetic metalloenzymes that are involved in gene transcription and regulation, cell proliferation, differentiation, migration, and death, as well as angiogenesis. Particularly, disorders of the HDACs expression are linked to the development of many types of cancer and neurodegenerative diseases, making them interesting molecular targets for the design of new efficient drugs...
-
Triazoloacridone C-1305 impairs XBP1 splicing by acting as a potential IRE1α endoribonuclease inhibitor
PublicationInositol requiring enzyme 1 alpha (IRE1α) is one of three signaling sensors in the unfolding protein response (UPR) that alleviates endoplasmic reticulum (ER) stress in cells and functions to promote cell survival. During conditions of irrevocable stress, proapoptotic gene expression is induced to promote cell death. One of the three signaling stressors, IRE1α is an serine/threonine-protein kinase/endoribonuclease (RNase) that...
-
Justification of quasi-stationary approximation in models of gene expression of a self-regulating protein
PublicationWe analyse a model of Hes1 gene transcription and protein synthesis with a negative feedback loop. The effect of multiple binding sites in the Hes1 promoter as well as the dimer formation process are taken into account. We consider three, possibly different, time scales connected with: (i) the process of binding to/dissolving from a binding site, (ii) formation and dissociation of dimers, (iii) production and degradation of Hes1...
-
Sound engineering as our commitment to its creators in Poland
PublicationSound engineering is an interdisciplinary and rapidly expanding domain. It covers many aspects, such as sound perception, studio and sound mastering technology, music information retrieval including content-based search systems and automatic music transcription frameworks, sound synthesis, sound restoration, electroacoustics, and other ones constituting multimedia technology. Moreover, machine learning methods applied to the topics...
-
On the Possibilities of Decreasing Power Loss in Large Tilting Pad Thrust Bearings
PublicationJournal Menu About this Journal Abstracting and Indexing Aims and Scope Article Processing Charges Articles in Press Author Guidelines Bibliographic Information Citations to this Journal Contact Information Editorial Board Editorial Workflow Free eTOC Alerts Publication Ethics Submit a Manuscript Table of Contents Abstract Full-Text PDF Full-Text HTML...
-
Investigation of Continuous Wave Jamming in an IEEE 802.15.4 Network
PublicationThis paper presents how continuous wave jamming affects IEEE 802.15.4 network. To this end, an office-based measurement setup has been proposed. Within the measurement area, 25 nodes have been set up in order to create a IEEE 802.15.4 tree-based test network structure. A dedicated jamming device that generates and transmits a continuous wave signal has been developed. Several tests have been conducted and presented to demonstrate...
-
Time Synchronization between the eNBs in E-UTRAN under the Asymmetric IP Network
PublicationIn this paper, we present a method for a time synchronization between the two eNodeBs (eNBs) in E-UTRAN (Evolved Universal Terrestrial Radio Access) network. The...
-
COMPLEXITY OF INNOVATIVE FINANCIAL PRODUCTS: THE CASE OF SYNTHETIC EXCHANGE TRADED FUNDS IN EUROPE
PublicationThe aim of the text is the presentation of the most important categories of exchange traded funds (ETFs) – physical and synthetic ones. A theoretical part of the text includes an overview of the main features of ETFs, the presentation of differences between physical and synthetic funds and the main risks posed by both types to their users and the whole financial systems. An empirical part focuses on the European market. Time span...
-
Post-comatose patients with minimal consciousness tend to preserve reading comprehension skills but neglect syntax and spelling
PublicationModern eye tracking technology provides a means for communication with patients suffering from disorders of consciousness (DoC) or remaining in locked-in-state. However, being able to use an eye tracker for controlling text-based contents by such patients requires preserved reading ability in the first place. To our knowledge, this aspect, although of great social importance, so far has seemed to be neglected. In the paper, we...
-
Words context analysis for improvement of information retrieval
PublicationIn the article we present an approach to improvement of retrieval informationfrom large text collections using words context vectors. The vectorshave been created analyzing English Wikipedia with Hyperspace Analogue to Language model of words similarity. For test phrases we evaluate retrieval with direct user queries as well as retrieval with context vectors of these queries. The results indicate that the proposed method can not...
-
Concept description vectors and the 20 question game
PublicationKnowledge of properties that are applicable to a given object is a necessary prerequisite to formulate intelligent question. Concept description vectors provide simplest representation of this knowledge, storing for each object information about the values of its properties. Experiments with automatic creation of concept description vectors from various sources, including ontologies, dictionaries, encyclopedias and unstructured...
-
Dynamic Bayesian Networks for Symbolic Polyphonic Pitch Modeling
PublicationSymbolic pitch modeling is a way of incorporating knowledge about relations between pitches into the process of an- alyzing musical information or signals. In this paper, we propose a family of probabilistic symbolic polyphonic pitch models, which account for both the “horizontal” and the “vertical” pitch struc- ture. These models are formulated as linear or log-linear interpo- lations of up to fi ve sub-models, each of which is...
-
Genre-Based Music Language Modeling with Latent Hierarchical Pitman-Yor Process Allocation
PublicationIn this work we present a new Bayesian topic model: latent hierarchical Pitman-Yor process allocation (LHPYA), which uses hierarchical Pitman-Yor pr ocess priors for both word and topic distributions, and generalizes a few of the existing topic models, including the latent Dirichlet allocation (LDA), the bi- gram topic model and the hierarchical Pitman-Yor topic model. Using such priors allows for integration of -grams with a topic model,...
-
Elimination of Impulsive Disturbances From Stereo Audio Recordings Using Vector Autoregressive Modeling and Variable-order Kalman Filtering
PublicationThis paper presents a new approach to elimination of impulsive disturbances from stereo audio recordings. The proposed solution is based on vector autoregressive modeling of audio signals. Online tracking of signal model parameters is performed using the exponential ly weighted least squares algo- rithm. Detection of noise pulses an d model-based interpolation of the irrevocably distorted sampl es is realized using an adaptive, variable-order...
-
Automatic music signal mixing system based on one-dimensional Wave-U-Net autoencoders
PublicationThe purpose of this paper is to show a music mixing system that is capable of automatically mixing separate raw recordings with good quality regardless of the music genre. This work recalls selected methods for automatic audio mixing first. Then, a novel deep model based on one-dimensional Wave-U-Net autoencoders is proposed for automatic music mixing. The model is trained on a custom-prepared database. Mixes created using the...
-
Elimination of Impulsive Disturbances From Archive Audio Signals Using Bidirectional Processing
PublicationIn this application-oriented paper we consider the problem of elimination of impulsive disturbances, such as clicks, pops and record scratches, from archive audio recordings. The proposed approach is based on bidirectional processing—noise pulses are localized by combining the results of forward-time and backward-time signal analysis. Based on the results of specially designed empirical tests (rather than on the results of theoretical analysis),...
-
Vocalic Segments Classification Assisted by Mouth Motion Capture
PublicationVisual features convey important information for automatic speech recognition (ASR), especially in noisy environment. The purpose of this study is to evaluate to what extent visual data (i.e. lip reading) can enhance recognition accuracy in the multi-modal approach. For that purpose motion capture markers were placed on speakers' faces to obtain lips tracking data during speaking. Different parameterizations strategies were tested...
-
Software Tools to Measure the Duplication of Information
PublicationData stored in average computer system usually is not unique, portions of stored data are duplicated. When duplicated data are stored in separate files containing source code of computer program of student homework, a possibility of cheating should be seriously considered. This paper presents software tools built, in order to detect re-use of pieces of code in supplied text files. Three aspects of information atching are considered:...
-
Previous Opinions is All You Need - Legal Information Retrieval System
PublicationWe present a system for retrieving the most relevant legal opinions to a given legal case or question. To this end, we checked several state-of-the-art neural language models. As a training and testing data, we use tens of thousands of legal cases as question-opinion pairs. Text data has been subjected to advanced pre-processing adapted to the specifics of the legal domain. We empirically chose the BERT-based HerBERT model to perform...
-
Macroeconomic functions of the Russian stock market
PublicationThe purpose of this article is to present the structure of the stock market in the Russian Federation and the significance of this part of national financial system for the whole economy, particularly the degree of main macroeconomic functions fulfillment. First part of the text includes an overview of the main theoretical concepts linked with the stock market roles as well as a brief description of results of selected studies...
-
Blockchain based Secure Data Exchange between Cloud Networks and Smart Hand-held Devices for use in Smart Cities
PublicationIn relation to smart city planning and management, processing huge amounts of generated data and execution of non-lightweight cryptographic algorithms on resource constraint devices at disposal, is the primary focus of researchers today. To enable secure exchange of data between cloud networks and mobile devices, in particular smart hand held devices, this paper presents Blockchain based approach that disperses a public/free key...
-
Evaluation of a company’s image on social media using the Net Sentiment Rate
PublicationVast amounts of new types of data are constantly being created as a result of dynamic digitization in all areas of our lives. One of the most important and valuable categories for business is data from social networks such as Facebook. Feedback resulting from the sharing of thoughts and emotions, expressed in comments on various products and services, is becoming the key factor on which modern business is based. This feedback is...