Search results for "Conversion method"

showing 3 items of 3 documents

Extended View Angle Integral Imaging 3D Display using Smart Pseudoscopic-to-orthoscopic Conversion with Head Tracking

2016

We overview a head tracking integral imaging display using the smart pseudoscopic-to-orthoscopic conversion method. The crosstalk for a large viewing angle in integral imaging is eliminated by generating a new set of elemental images.

Integral imagingComputer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONHead trackingStereo displayViewing angleCrosstalkOpticsConversion methodComputer visionArtificial intelligenceView angleImage sensorbusinessImaging and Applied Optics 2016
researchProduct

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

Multiple-Planes Pseudoscopic-to-Orthoscopic Conversion for 3D Integral Imaging Display

2015

In this paper, we propose an advanced pseudoscopic-to-orthoscopic conversion method for 3D integral imaging display systems. Compared to previous works, this method can generate more accurate images for orthoscopic 3D display using multiple reference planes and estimated depth information. 3D display results show the superiority of the proposed pseudoscopic-to-orthoscopic conversion method.

Integral imagingComputer sciencebusiness.industryImage processingIterative reconstructionCondensed Matter PhysicsStereo displayElectronic Optical and Magnetic MaterialsThree dimensional imagingComputer graphics (images)Conversion methodComputer visionArtificial intelligenceElectrical and Electronic EngineeringbusinessJournal of Display Technology
researchProduct