Filtry
wszystkich: 808
wybranych: 697
Wyniki wyszukiwania dla: REAL-TIME SPEECH STRETCHING
-
Elimination of Impulsive Disturbances From Archive Audio Signals Using Bidirectional Processing
PublikacjaIn 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),...
-
Minimizing Distribution and Data Loading Overheads in Parallel Training of DNN Acoustic Models with Frequent Parameter Averaging
PublikacjaIn 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...
-
Analysis of a caustic formed by a spherical reflector: Impact of a caustic on architectural acoustics
PublikacjaFocusing sound in rooms intended for listening to music or speech is an acoustic defect. Design recommendations provide remedial steps to effectively prevent this. However, there is a category of objects of high historical or architectural value in which the sound focus correction is limited or even abandoned. This also applies to indoor or outdoor concert shells, installations for teaching and acoustic presentations, etc. The...
-
Destruction of shell structures under the dynamic load on the human skull trauma basis
PublikacjaThe main aim of this work is to investigate patterns of potential orbital bone fractures due to mechanical injuries. The solution of the main problem is followed by analysis of several testing examples having straight correlation with civil engineering structures, in which materials of wide range of stiffness are applied. To solve the main problem, the three-dimensional finite element method (FEM) model of the orbital region has...
-
HILS for the Design of Three-Wheeled Mobile Platform Motion Surveillance System with a Use of Energy Performance Index
PublikacjaCurrent tendency in mechatronic design requires the use of comprehensive development of an environment, which gives the possibility to prototype, design, simulate and integrate with dedicated hardware. The paper discusses the Hardware-In-the-Loop Simulations (HILS) mechatronic technique, used during the design of the surveillance system based on energy performance index. The presented test configuration (physical controller – emulated...
-
Acceleration of decision making in sound event recognition employing supercomputing cluster
PublikacjaParallel processing of audio data streams is introduced to shorten the decision making time in hazardous sound event recognition. A supercomputing cluster environment with a framework dedicated to processing multimedia data streams in real time is used. The sound event recognition algorithms employed are based on detecting foreground events, calculating their features in short time frames, and classifying the events with Support...
-
Comparison of Lithuanian and Polish Consonant Phonemes Based on Acoustic Analysis – Preliminary Results
PublikacjaThe goal of this research is to find a set of acoustic parameters that are related to differences between Polish and Lithuanian language consonants. In order to identify these differences, an acoustic analysis is performed, and the phoneme sounds are described as the vectors of acoustic parameters. Parameters known from the speech domain as well as those from the music information retrieval area are employed. These parameters are...
-
Detection of Anomalies in the Operation of a Road Lighting System Based on Data from Smart Electricity Meters
PublikacjaSmart meters in road lighting systems create new opportunities for automatic diagnostics of undesirable phenomena such as lamp failures, schedule deviations, or energy theft from the power grid. Such a solution fits into the smart cities concept, where an adaptive lighting system creates new challenges with respect to the monitoring function. This article presents research results indicating the practical feasibility of real‐time...
-
How to render FDTD computations more effective using agraphics accelerator.
PublikacjaGraphics processing units (GPUs) for years have been dedicated mostly to real time rendering. Recently leading GPU manufactures have extended their research area and decided to support also graphics computing. In this paper, we describe an impact of new GPU features on development process of an efficient finite difference time domain (FDTD) implementation.
-
Rough Set-Based Classification of EEG Signals Related to Real and Imagery Motion
PublikacjaA rough set-based approach to classification of EEG signals registered while subjects were performing real and imagery motions is presented in the paper. The appropriate subset of EEG channels is selected, the recordings are segmented, and features are extracted, based on time-frequency decomposition of the signal. Rough set classifier is trained in several scenarios, comparing accuracy of classification for real and imagery motion....
-
Camera Orientation-Independent Parking Events Detection
PublikacjaThe paper describes the method for detecting precise position and time of vehicles parking in a parking lot. This task is trivial in case of favorable camera orientation but gets much more complex when an angle between the camera viewing axis and the ground is small. The method utilizes background subtraction and object tracking algorithms for detecting moving objects in a video stream. Objects are classified into vehicles and...
-
Optical method supported by machine learning for dynamics of C‐reactive protein concentrations changes detection in biological matrix samples
PublikacjaIn this article we present the novel spectroscopy method supported with machine learning for real-time detection of infectious agents in wastewater. In the case of infectious diseases, wastewater monitoring can be used to detect the presence of inflammation biomarkers, such as the proposed C-reactive protein, for monitoring inflammatory conditions and mass screening during epidemics for early detection in communities of concern,...
-
Novel application of dynamic electrochemical impedance monitoring to a cataphoretic coating process
PublikacjaThe paper presents a novel method of on-line impedance monitoring of cataphoretic coating application process. Utilization of dynamic electrochemical impedance spectroscopy (DEIS) overcame the fundamental problem connected with non-stationarity of the aforementioned coating deposition process, which eliminates classical impedance spectroscopy technique from a real-time description of cataphoresis. The paper illustrates selected examples...
-
Investigation of the Dynamism of Nanosized SOA Particle Formation in Indoor Air by a Scanning Mobility Particle Sizer and Proton-Transfer-Reaction Mass Spectrometry
PublikacjaTerpenes are VOCs of particular importance, since they are emitted from a wide range of indoor sources and are considered to be precursors of Secondary Organic Aerosol (SOA) formation. It has been proven that SOA particles, especially nanosized ones, pose a threat to human health. In this research, experiments with the application of an environmental chamber and real-time measurement techniques were carried out to investigate in...
-
Audio Content and Crowdsourcing: A Subjective Quality Evaluation of Radio Programs Streamed Online
PublikacjaRadio broadcasting has been present in our lives for over 100 years. The transmission of speech and music signals accompanies us from an early age. Broadcasts provide the latest information from home and abroad. They also shape musical tastes and allow many artists to share their creativity. Modern distribution involves transmission over a number of terrestrial systems. The most popular are analog FM (Frequency Modulation) and...
-
Optimization of Execution Time under Power Consumption Constraints in a Heterogeneous Parallel System with GPUs and CPUs
PublikacjaThe paper proposes an approach for parallelization of computations across a collection of clusters with heterogeneous nodes with both GPUs and CPUs. The proposed system partitions input data into chunks and assigns to par- ticular devices for processing using OpenCL kernels defined by the user. The sys- tem is able to minimize the execution time of the application while maintaining the power consumption of the utilized GPUs and...
-
Determining QoS in the Video Telephony Service in an IP Environment
PublikacjaIP networks are indispensable nowadays. They are among the most efficient platforms. The constantly growing number of users and new services in these networks - the largest being the Internet - requires a good quality of any application used.Determining the QoS in real-time services is particularly important. This work is dedicated to exactly this aspect of the real-time service Video Telephony over IP (VToIP). First, the ITU-T...
-
Designing Intelligent Factory: Conceptual Framework and Empirical Validation
PublikacjaThis paper presents a framework for monitoring, analysing and decision making for a smart manufacturing environment. We maintain that this approach could play a vital role in developing an architecture and implementation of Industry 4.0. The proposed model has features like experience based knowledge representation and semantic analysis of engineering objects and manufacturing process. It is also capable of continuous real time...
-
Training of Deep Learning Models Using Synthetic Datasets
PublikacjaIn order to solve increasingly complex problems, the complexity of Deep Neural Networks also needs to be constantly increased, and therefore training such networks requires more and more data. Unfortunately, obtaining such massive real world training data to optimize neural networks parameters is a challenging and time-consuming task. To solve this problem, we propose an easy-touse and general approach to training deep learning...
-
Residence time distribution in rapid multiphase reactors
PublikacjaResidence time distribution (RTD) provides information about average hydraulic residence time and the distribution of material in the reactor. A method for determining RTD for reactors with very short hydraulic residence times is deconvolution based on extraction of real RTD by the analysis of a non-ideal input signal. The mean residence time and dispersion were determined for the spinning fluids reactor (SFR). For the first time...
-
Hybridization of valuation procedures as a medicine supporting the real estate market and sustainable land use development during the covid-19 pandemic and afterwards
PublikacjaCurrently we are facing the pandemic situation that occur all over the world. Regardless the country or even the region, the negative consequences that are expected could be very big and the level of crisis is not predictable. This situation is the challenge for the real estate market as well. Due to this fact, the authors believe that there is the time when deep transformation of approaches, procedures and awareness related to...
-
Conception of interactive information and decision support system - model and evaluation
PublikacjaThis article presents conception of interactive information and decision support system for urban and industrial air quality management. The emphasis of the project is on real-time analysis and multi-media information, and support of distributed and mobile clients through the Internet.
-
Mechatronic design o strongly nonlinear systems on a basis of three wheeled mobile platform
PublikacjaRemarkable grow in demand both of mobile platform operability performance and reduction of project leading time development encourage to apply modern algorithms and reliable engineering tools for the design process. The paper discusses the mechatronic design applied for the surveillance system based on the energy performance index algorithm. The exploited mechatronic techniques i.e. virtual prototyping, Hardware-In-the-Loop Simulation...
-
Photoplethysmographic Time-Domain Heart Rate Measurement Algorithm for Resource-Constrained Wearable Devices and its Implementation
PublikacjaThis paper presents an algorithm for the measurement of the human heart rate, using photoplethysmography (PPG), i.e., the detection of the light at the skin surface. The signal from the PPG sensor is processed in time-domain; the peaks in the preprocessed and conditioned PPG waveform are detected by using a peak detection algorithm to find the heart rate in real time. Apart from the PPG sensor, the accelerometer is also used to...
-
Derivation of Executable Test Models From Embedded System Models using Model Driven Architecture Artefacts - Automotive Domain
PublikacjaThe approach towards system engineering compliant to Model-Driven Architecture (MDA) implies an increased need for research on the automation of the model-based test generation. This applies especially to embedded real-time system development where safety critical requirements must be met by a system. The following paper presents a methodology to derive basic Simulink test models from Simulink system models so as to execute them...
-
Monitoring the curing process of epoxy adhesive using ultrasound and Lamb wave dispersion curves
PublikacjaMonitoring the stiffness of adhesives is a crucial issue when considering the durability andstrength of adhesive joints. While there are many studies conducted on specimens madeonly from adhesive, the problem of curing of an adhesive film in real joints is moderatelyconsidered. This paper presents the monitoring of stiffening of epoxy adhesive using ultra-sound. Ultrasonic pulse velocity method was firstly applied for monitoring...
-
MACHINE LEARNING–BASED ANALYSIS OF ENGLISH LATERAL ALLOPHONES
PublikacjaAutomatic 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’...
-
Examining Feature Vector for Phoneme Recognition
PublikacjaThe aim of this paper is to analyze usability of descriptors coming from music information retrieval to the phoneme analysis. The case study presented consists in several steps. First, a short overview of parameters utilized in speech analysis is given. Then, a set of time and frequency domain-based parameters is selected and discussed in the context of stop consonant acoustical characteristics. A toolbox created for this purpose...
-
Effective Air Quality Prediction Using Reinforced Swarm Optimization and Bi-Directional Gated Recurrent Unit
PublikacjaIn the present scenario, air quality prediction (AQP) is a complex task due to high variability, volatility, and dynamic nature in space and time of particulates and pollutants. Recently, several nations have had poor air quality due to the high emission of particulate matter (PM2.5) that affects human health conditions, especially in urban areas. In this research, a new optimization-based regression model was implemented for effective...
-
New results on estimation bandwidth adaptation
PublikacjaThe problem of identification of a nonstationary autoregressive signal using non-causal estimation schemes is considered. Noncausal estimators can be used in applications that are not time-critical, i.e., do not require real-time processing. A new adaptive estimation bandwidth selection rule based on evaluation of pseudoprediction errors is proposed, allowing one to adjust tracking characteristics of noncausal estimators to unknown...
-
Visualization of events using various kinds of synchronized data for the Border Guard
PublikacjaSTRADAR project is dedicated to streaming real-time data in a distributed dispatcher and teleinfor-mation system of the Border Guard. The Events Visualization Post is a software designed for simultaneous visualization of data of different types in BG headquarters. The software allows the operator to visualize files, images, SMS, SDS, video, audio, and current or archival data on naval situation on digital maps. All the visualized...
-
Efficient signal processing in spectroscopic optical coherence tomography
PublikacjaSpectroscopic optical coherence tomography (SOCT) is an extension of a standard OCT technique, which allows to obtain depth-resolved, spectroscopic information on the examined sample. It can be used as a source of additional contrast in OCT images e.g. by encoding certain features of the light spectrum into the hue of the image pixels. However, SOCT require computation of time-frequency distributions of each OCT A-scan, what is...
-
Power Hardware-in-the-Loop Approach In Power System Development
PublikacjaThe main objective of the research is the verification of the Power Hardware-In-The-Loop (PHIL) approach in power system analysis and design. The premise of the article is that using PHIL approach the performance of the power system in steady and transient state conditions can be analysed in real power system conditions. Models of induction machine were developed and real time simulations were performed. Simulation variables were...
-
Ship Evolutionary Trajectory Planning Method with Application of Polynomial Interpolation
PublikacjaPaper presents the application of evolutionary algorithms and polynomial interpolation in ship evolutionary trajectory planning method. Evolutionary algorithms allows to find a coIlision free trajectory in real time, while polynomial interpolation allows to model smooth trajectory which keeps continuity of velocity and acceleration values along path. Combination of this two methods allows to find trajectory, which under some assumptions,...
-
Zastosowanie trendów przełącznikowych w analizie płac realnych w Polsce
PublikacjaStreszczenie W początkowej części artykułu zostały przedstawione i omówione informacje o poziomie miesięcznych nominalnych płac (WN) oraz indeksie cen dóbr konsumpcyjnych (ICK) w gospodarce polskiej w latach 1995-2015. Następnie opisano poziomy realnych płac (W) wyrażone w cenach roku 2015. Na bazie tych informacji przedstawiono i przedyskutowano zagadnienia dotyczące rocznych przyrostów płac realnych oraz ich rocznych stóp wzrostu....
-
Innovations in Wastewater Treatment: Harnessing Mathematical Modeling and Computer Simulations with Cutting-Edge Technologies and Advanced Control Systems
PublikacjaThe wastewater treatment landscape in Central Europe, particularly in Poland, has undergone a profound transformation due to European Union (EU) integration. Fueled by EU funding and rapid technological advancements, wastewater treatment plants (WWTPs) have adopted cutting-edge control methods to adhere to EU Water Framework Directive mandates. WWTPs contend with complexities such as variable flow rates, temperature fluctuations,...
-
Mobile devices and computing cloud resources allocation for interactive applications
PublikacjaUsing mobile devices such as smartphones or iPads for various interactive applications is currently very common. In the case of complex applications, e.g. chess games, the capabilities of these devices are insufficient to run the application in real time. One of the solutions is to use cloud computing. However, there is an optimization problem of mobile device and cloud resources allocation. An iterative heuristic algorithm for...
-
Optical monitoring of electrochemical processes with ITO-based lossy-mode resonance optical fiber sensor applied as an electrode
PublikacjaIn this work we discuss the application of optical fiber sensors based on lossy-mode resonance (LMR) phenomenon for real-time optical monitoring of electrochemical processes. The sensors were obtained by a reactive high power impulse magnetron sputtering of indium tin oxide (ITO) on a 2.5 cm-long core of polymer-clad silica fibers. The LMR effect made monitoring of changes in optical properties of both ITO and its surrounding medium...
-
Comparison of Single and Multi-Population Evolutionary Algorithm for Path Planning in Navigation Situation
PublikacjaIn this paper a comparison of single and multi-population evolutionary algorithm is presented. Tested algorithms are used to determine close to optimal ship paths in collision avoidance situation. For this purpose a path planning problem is defined. A specific structure of the individual path and fitness function is presented. Principle of operation of single-population and multi-population evolutionary algorithm is described....
-
Evaluation of RTKLIB's Positioning Accuracy Using low-cost GNSS Receiver and ASG-EUPOS
PublikacjaThe paper focuses on a comparison of different positioning methods provided by free and open source software (FOSS) package called RTKLIB. The RTKLIB supports real‐time and post‐processed positioning. The most important modes of operation tested by the authors are Kinematic, Static, Fixed and Precise Point Positioning (PPP). The data for evaluation were obtained from low‐cost Global Navigation Satellite System (GNSS) receiver....
-
3D Imaging Of Underwater Objects Using Multi-Beam Data
PublikacjaOne of the main applications of multibeam sonars is high resolution bathymetry measurement, as well as detecting and imaging of underwater objects like shipwrecks. In order to obtain the visualisation quality good enough to allow the researcher to investigate an object in more detail, the approach relying on construction of three-dimensional model of an imaged object, e.g. consisting of nodes, edges and plane elements (facets)...
-
Detection of Face Position and Orientation Using Depth Data
PublikacjaIn this paper an original approach is presented for real-time detection of user's face position and orientation based only on depth channel from a Microsoft Kinect sensor which can be used in facial analysis on scenes with poor lighting conditions where traditional algorithms based on optical channel may have failed. Thus the proposed approach can support, or even replace, algorithms based on optical channel or based on skeleton...
-
Emulator and simulator of Terma SCANTER and ARPA radar data server
PublikacjaThe software solutions presented in this paper generate real-time data compatible with ARPA radar standard as well as Terma SCANTER 2001 radar cooperating with Video Distribution and Tracking (VDT) server. Two different approaches to this problem are considered: emulation based on the data captured from real devices and simulation of objects on the sea. For both of them architecture, implementation details and functional test results...
-
Adaptacja akustyczna pomieszczenia wykładowego - studium przypadku
PublikacjaW niniejszej pracy przedstawiono analizę rozkładu pola akustycznego sali wykładowej znajdującej się w budynku Wydziału Elektroniki i Telekomunikacji Politechniki Gdańskiej. Badania przeprowadzono metodą pomiarową oraz symulacyjną z wykorzystaniem programu Odeon. Wybór parametrów oceny akustyki wnętrz sugerowany jest wymaganiami stawianymi pomieszczeniom lekcyjnym z zaznaczeniem multimedialnego charakteru wykładów prowadzonych...
-
Azimuth estimator for a rotating array radar with wide beam
PublikacjaThe problem of estimating azimuth in rotating array radar with a beam, wide in the azimuth plane, is considered. Under such setup the echo signal usually has a very low signal to noise ratio, but the number of observations is large, because of long dwell times. The proposed solution is based on the maximum likelihood approach, but it employs simplifications which facilitate its implementation in real time systems. Results, obtained...
-
Person Tracking in a Ferry Environment Using Ultra-Wide Band Radio Interface
PublikacjaThis article presents research and analysis of effectiveness of tracking moving people in an environment of passenger ferry, using measurements of propagation time of ultra-wide band radio signal (UWB - Ultra-Wide Band). Constructed measurement stand and results of measurements carried out in a real propagation conditions were shortly discussed.
-
Waveguide model of the hearing aid earmold system
PublikacjaBackground The earmold system of the Behind-The-Ear hearing aid is an acoustic system that modifies the spectrum of the propagated sound waves. Improper selection of the earmold system may result in deterioration of sound quality and speech intelligibility. Computer modeling methods may be useful in the process of hearing aid fitting, allowing physician to examine various earmold system configurations and choose the optimum one...
-
Waveguide model of the hearing aid earmold system
PublikacjaBackground The earmold system of the Behind-The-Ear hearing aid is an acoustic system that modifies the spectrum of the propagated sound waves. Improper selection of the earmold system may result in deterioration of sound quality and speech intelligibility. Computer modeling methods may be useful in the process of hearing aid fitting, allowing physician to examine various earmold system configurations and choose the optimum one...
-
Evaluation of excessive noise effects on hearing employing psychoacoustic dosimetry
PublikacjaResearch results regarding the noise impact on hearing applying the concept of the Psychoacoustic Noise Dosimetry (PND) are presented. The general characteristics of the PND algorithm are discussed. Additionally, the results of hearing examinations conducted in the laboratory conditions are shown. The main objective of the research was to determine the time needed for the Temporary Threshold Shift to reverse. The results were used...
-
Waveform design for fast clutter cancellation in noise radars
PublikacjaCanceling clutter is an important, but computation-ally intensive part of signal processing in noise radars. It is shown that considerable improvements can be made to a simple least squares canceler if minor constraints are imposed onto noise waveform. The proposed scheme is potentially capable of canceling clutter in real-time, even for high sampling rates.