Search results for "automatic"

showing 10 items of 730 documents

Using privacy-transformed speech in the automatic speech recognition acoustic model training

2020

Automatic Speech Recognition (ASR) requires huge amounts of real user speech data to reach state-of-the-art performance. However, speech data conveys sensitive speaker attributes like identity that can be inferred and exploited for malicious purposes. Therefore, there is an interest in the collection of anonymized speech data that is processed by some voice conversion method. In this paper, we evaluate one of the voice conversion methods on Latvian speech data and also investigate if privacy-transformed data can be used to improve ASR acoustic models. Results show the effectiveness of voice conversion against state-of-the-art speaker verification models on Latvian speech and the effectivene…

Speaker verificationevaluationvoice conversionComputer scienceSpeech recognitionautomatic speech recognitionLatvianAcoustic model[INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG]privacylanguage.human_language[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]anonymization[INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG][INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL]Identity (object-oriented programming)languageConversion methodautomatic speaker verification
researchProduct

Combining split-and-merge and multi-seed region growing algorithms for uterine fibroid segmentation in MRgFUS treatments

2016

Uterine fibroids are benign tumors that can affect female patients during reproductive years. Magnetic resonance-guided focused ultrasound (MRgFUS) represents a noninvasive approach that uses thermal ablation principles to treat symptomatic fibroids. During traditional treatment planning, uterus, fibroids, and surrounding organs at risk must be manually marked on MR images by an operator. After treatment, an operator must segment, again manually, treated areas to evaluate the non-perfused volume (NPV) inside the fibroids. Both pre- and post-treatment procedures are time-consuming and operator-dependent. This paper presents a novel method, based on an advanced direct region detection model, …

SpeedupUterine fibroidsImage ProcessingBiomedical EngineeringThermal ablation02 engineering and technologyMagnetic Resonance Imaging InterventionalFocused ultrasound030218 nuclear medicine & medical imaging03 medical and health sciencesComputer-Assisted0302 clinical medicineImage Processing Computer-Assisted0202 electrical engineering electronic engineering information engineeringmedicineHumansSegmentationRadiation treatment planningSplit-and-merge segmentationSettore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniMRgFUS treatmentsInterventionalLeiomyomaMulti-seed adaptive region growingbusiness.industrymedicine.diseaseMagnetic Resonance Imagingfemale genital diseases and pregnancy complicationsComputer Science ApplicationsAutomatic segmentation MRgFUS treatments Multi-seed adaptive region growing Split-and-merge segmentation Uterine fibroids Algorithms Female High-Intensity Focused Ultrasound Ablation Humans Leiomyoma Magnetic Resonance Imaging Magnetic Resonance Imaging Interventional Image Processing Computer-AssistedMRgFUS treatmentRegion growingAutomatic segmentation; MRgFUS treatments; Multi-seed adaptive region growing; Split-and-merge segmentation; Uterine fibroids; Algorithms; Female; High-Intensity Focused Ultrasound Ablation; Humans; Leiomyoma; Magnetic Resonance Imaging; Magnetic Resonance Imaging Interventional; Image Processing Computer-AssistedHigh-Intensity Focused Ultrasound AblationFemale020201 artificial intelligence & image processingAutomatic segmentationbusinessMerge (version control)AlgorithmAlgorithmsUterine fibroidsMedical & Biological Engineering & Computing
researchProduct

Modeling and Experimental Validation of a Voltage-Controlled Split-Pi Converter Interfacing a High-Voltage ESS with a DC Microgrid

2023

The Split-pi converter can suitably interface an energy storage system (ESS) with a DC microgrid when galvanic isolation is not needed. Usually, the ESS voltage is lower than the grid-side voltage. However, limitations in terms of the ESS current make the use of a high-voltage ESS unavoidable when high power levels are required. In such cases, the ESS voltage can be higher than the microgrid voltage, especially with low microgrid voltages such as 48 V. Despite its bidirectionality and symmetry, the Split-pi exhibits a completely different dynamic behavior if its input and output ports are exchanged. Thus, the present work aims to model the Split-pi converter operating with an ESS voltage hi…

Split-pidroop controlControl and OptimizationRenewable Energy Sustainability and the Environmentenergy storage systemfeed-forward controlEnergy Engineering and Power TechnologyBuilding and ConstructionSplit-pi bidirectional converter energy storage system droop control feed-forward control DC microgridbidirectional converterSettore ING-INF/04 - AutomaticaDC microgridElectrical and Electronic EngineeringEngineering (miscellaneous)Energy (miscellaneous)
researchProduct

Distance-based functions for image comparison

1999

The interest in digital image comparison is steadily growing in the computer vision community. The definition of a suitable comparison measure for non-binary images is relevant in many image processing applications. Visual tasks like segmentation and classification require the evaluation of equivalence classes. Measures of similarity are also used to evaluate lossy compression algorithms and to define pictorial indices in image content based retrieval methods. In this paper we develop a distance-based approach to image similarity evaluation and we present several image distances which are based on low level features. The sensitivity and eAectiveness are tested on real data. ” 1999 Published…

Standard test imagebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage processingPattern recognitionImage segmentationAutomatic image annotationImage textureArtificial IntelligenceSignal ProcessingDigital image processingComputer visionComputer Vision and Pattern RecognitionArtificial intelligencebusinessImage retrievalSoftwareMathematicsFeature detection (computer vision)Pattern Recognition Letters
researchProduct

Stata Automatic Report (SAR) 1.0

2011

The output provided by most Stata commands is a plain text not suitable to be presented or published. After the numerical output is obtained, the user has to copy it in a word processor to complete the editing process. Some Stata commands help you to obtain well formatted output, expecially tabulating results in LaTex or other formats, but they are not a complete solution and they are not friendly tools. Stata automatic report (Sar) is an easy to use macro for Microsoft Word for Windows which allows a powerful integration between Stata and the word processor by Microsoft. Using Sar the user can retrieve numerical results from Stata and automatically insert them in a well formatted Word docu…

StataSettore SECS-S/02 - Statistica Per La Ricerca Sperimentale E TecnologicaStata; Word; automatic reportWordautomatic report
researchProduct

Sar, Automatic Generation of Statistical Report Using Stata and Microsoft Word for Windows

2012

The output provided by most Stata commands is a plain text not suitable to be presented or published. After the numerical output is obtained, the user has to copy it in a word processor to complete the editing process. Some Stata commands help you to obtain well formatted output, expecially tabulating results in LaTex or other formats, but they are not a complete solution and they are not friendly tools. Stata automatic report (Sar) is an easy to use macro for Microsoft Word for Windows which allows a powerful integration between Stata and the word processor by Microsoft. Using Sar the user can retrieve numerical results from Stata and automatically insert them in a well formatted Word docu…

StataSettore SECS-S/02 - Statistica Per La Ricerca Sperimentale E TecnologicaWordautomatic report
researchProduct

State Space-Vector Model of Linear Induction Motors Including Iron Losses Part I: Theoretical Analysis

2018

This is the first part of a paper, divided into two parts, dealing with the definition of a space-vector dynamic model of the linear Induction motor (LIM) taking into consideration both the dynamic end-effects and the iron losses and its off-line identification. This first part specifically treats the theoretical formulation of this model, which has been expressed in a state form, so to be, in perspective, suitably adopted for developing novel non linear control techniques, non-linear observers as well as electrical losses minimization techniques (ELMTs). Besides the formulation of the dynamic model in space-vector state form, a steady-state analysis is proposed, highlighting the combined e…

State modelEnd effectLinear Induction Motor (LIM)Computer scienceState ModelEnd-effectsEnd-effectIdentification (information)Perspective (geometry)State formSettore ING-INF/04 - AutomaticaControl theoryLinear induction motorState spaceMinificationSpace-vector
researchProduct

State Space-Vector Model of Linear Induction Motors Including Iron Losses: Part II: Model Identification and Results

2018

This is the second part of a paper, divided into two parts, dealing with the definition of a space-vector dynamic model of the linear Induction motor (LIM) taking into consideration both the dynamic end-effects and the iron losses as well as the off-line identification of its parameters. The first part has treated the theoretical framework of the model. This second part is devoted to the description of an identification technique which has been suitably developed for the estimation of the parameters of the LIM dynamic model accounting for both the dynamic end-effects and iron losses, described in the first part of the paper. Such an identification technique is strictly related to the state …

State modelLinear Induction Motor (LIM)Computer scienceSystem identificationState ModelState (functional analysis)Function (mathematics)End-effectsFinite element methodEnd-effectIdentification (information)Settore ING-INF/04 - AutomaticaControl theoryLinear induction motorState spaceSpace-vector2018 IEEE Energy Conversion Congress and Exposition (ECCE)
researchProduct

A Space-Vector State Dynamic Model of the Synchronous Reluctance Motor Including Self and Cross-Saturation Effects and its Parameters Estimation

2018

This paper proposes a space-vector dynamic model of the Synchronous Reluctance Motor (SynRM) including both self-saturation and cross-saturation effects and selecting as state variables the stator currents. The proposed dynamic model is based on an original function between the stator flux and stator current components, and relies on 8 coefficients (fewer than other models in the scientific literature), presenting an interesting physical interpretation. Starting from this approach, both the static and dynamic inductances expressions of the model have been analytically developed, so that the reciprocity conditions for the cross saturation is satisfied. This paper presents also a technique fo…

State variableComputer simulationStatorComputer scienceEstimation theorySpace-vector dynamic model05 social sciences020207 software engineering02 engineering and technologylaw.inventionError functionSettore ING-INF/04 - AutomaticalawControl theoryParameters' estimation0202 electrical engineering electronic engineering information engineering0501 psychology and cognitive sciencesMinificationSynchronous Reluctance Motor (SynRM)Magnetic characteristicsSynchronous reluctance motorSaturation (magnetic)050107 human factors2018 IEEE Energy Conversion Congress and Exposition (ECCE)
researchProduct

Descriptor-type Kalman Filter and TLS EXIN Speed Estimate for Sensorless Control of a Linear Induction Motor.

2014

This paper proposes a speed observer for linear induction motors (LIMs), which is composed of two parts: 1) a linear Kalman filter (KF) for the online estimation of the inductor currents and induced part flux linkage components; and 2) a speed estimator based on the total least squares (TLS) EXIN neuron. The TLS estimator receives as inputs the state variables, estimated by the KF, and provides as output the LIM linear speed, which is fed back to the KF and the control system. The KF is based on the classic space-vector model of the rotating induction machine. The end effects of the LIMs have been considered an uncertainty treated by the KF. The TLS EXIN neuron has been used to compute, in …

State variableEngineeringObserver (quantum physics)neural networks (NNs)linear induction motor controlLinear Induction Motor (LIM) Kalman Filter Total Least-Squares Neural Networks.Industrial and Manufacturing EngineeringSettore ING-INF/04 - AutomaticaKalman filter (KF)Control theorylinear induction motor (LIM)state estimationElectrical and Electronic EngineeringTotal least squaresAlpha beta filterArtificial neural networkbusiness.industryEstimatorKalman filterLinear motorFlux linkagetotal least squares (TLS)Control and Systems EngineeringLinear induction motorbusinessInduction motor
researchProduct