Search results for " processing"

showing 10 items of 7549 documents

Optimized Kernel Entropy Components

2016

This work addresses two main issues of the standard Kernel Entropy Component Analysis (KECA) algorithm: the optimization of the kernel decomposition and the optimization of the Gaussian kernel parameter. KECA roughly reduces to a sorting of the importance of kernel eigenvectors by entropy instead of by variance as in Kernel Principal Components Analysis. In this work, we propose an extension of the KECA method, named Optimized KECA (OKECA), that directly extracts the optimal features retaining most of the data entropy by means of compacting the information in very few features (often in just one or two). The proposed method produces features which have higher expressive power. In particular…

FOS: Computer and information sciencesComputer Networks and CommunicationsKernel density estimationMachine Learning (stat.ML)02 engineering and technologyKernel principal component analysisMachine Learning (cs.LG)Artificial IntelligencePolynomial kernelStatistics - Machine Learning0202 electrical engineering electronic engineering information engineeringMathematicsbusiness.industry020206 networking & telecommunicationsPattern recognitionComputer Science ApplicationsComputer Science - LearningKernel methodKernel embedding of distributionsVariable kernel density estimationRadial basis function kernelKernel smoother020201 artificial intelligence & image processingArtificial intelligencebusinessSoftwareIEEE Transactions on Neural Networks and Learning Systems
researchProduct

Perceptually Optimized Image Rendering

2017

We develop a framework for rendering photographic images by directly optimizing their perceptual similarity to the original visual scene. Specifically, over the set of all images that can be rendered on a given display, we minimize the normalized Laplacian pyramid distance (NLPD), a measure of perceptual dissimilarity that is derived from a simple model of the early stages of the human visual system. When rendering images acquired with a higher dynamic range than that of the display, we find that the optimization boosts the contrast of low-contrast features without introducing significant artifacts, yielding results of comparable visual quality to current state-of-the-art methods, but witho…

FOS: Computer and information sciencesComputer Science - Artificial IntelligenceImage qualityComputer scienceComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern RecognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage processing02 engineering and technologyLuminanceRendering (computer graphics)Computer Science - GraphicsOptics0202 electrical engineering electronic engineering information engineeringComputer visionPower functionComputingMethodologies_COMPUTERGRAPHICSbusiness.industryDynamic range020207 software engineeringAtomic and Molecular Physics and OpticsGraphics (cs.GR)Electronic Optical and Magnetic MaterialsArtificial Intelligence (cs.AI)Human visual system model020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionArtificial intelligencebusinessImage compression
researchProduct

ASR performance prediction on unseen broadcast programs using convolutional neural networks

2018

In this paper, we address a relatively new task: prediction of ASR performance on unseen broadcast programs. We first propose an heterogenous French corpus dedicated to this task. Two prediction approaches are compared: a state-of-the-art performance prediction based on regression (engineered features) and a new strategy based on convolutional neural networks (learnt features). We particularly focus on the combination of both textual (ASR transcription) and signal inputs. While the joint use of textual and signal features did not work for the regression baseline, the combination of inputs for CNNs leads to the best WER prediction performance. We also show that our CNN prediction remarkably …

FOS: Computer and information sciencesComputer Science - Computation and LanguageComputer scienceSpeech recognitionFeature extractionInformationSystems_INFORMATIONSTORAGEANDRETRIEVAL02 engineering and technology010501 environmental sciences01 natural sciencesConvolutional neural network[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]Task (project management)[INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL]0202 electrical engineering electronic engineering information engineeringTask analysisPerformance prediction020201 artificial intelligence & image processingMel-frequency cepstrumTranscription (software)Hidden Markov modelComputation and Language (cs.CL)ComputingMilieux_MISCELLANEOUS0105 earth and related environmental sciences
researchProduct

Analyzing Learned Representations of a Deep ASR Performance Prediction Model

2018

This paper addresses a relatively new task: prediction of ASR performance on unseen broadcast programs. In a previous paper, we presented an ASR performance prediction system using CNNs that encode both text (ASR transcript) and speech, in order to predict word error rate. This work is dedicated to the analysis of speech signal embeddings and text embeddings learnt by the CNN while training our prediction model. We try to better understand which information is captured by the deep model and its relation with different conditioning factors. It is shown that hidden layers convey a clear signal about speech style, accent and broadcast type. We then try to leverage these 3 types of information …

FOS: Computer and information sciencesComputer Science - Computation and LanguageComputer scienceSpeech recognitionWord error rate02 engineering and technology010501 environmental sciences01 natural sciences[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL][INFO.INFO-CL] Computer Science [cs]/Computation and Language [cs.CL]0202 electrical engineering electronic engineering information engineeringPerformance predictionLeverage (statistics)020201 artificial intelligence & image processingComputation and Language (cs.CL)0105 earth and related environmental sciences
researchProduct

Multilingual Clustering of Streaming News

2018

Clustering news across languages enables efficient media monitoring by aggregating articles from multilingual sources into coherent stories. Doing so in an online setting allows scalable processing of massive news streams. To this end, we describe a novel method for clustering an incoming stream of multilingual documents into monolingual and crosslingual story clusters. Unlike typical clustering approaches that consider a small and known number of labels, we tackle the problem of discovering an ever growing number of cluster labels in an online fashion, using real news datasets in multiple languages. Our method is simple to implement, computationally efficient and produces state-of-the-art …

FOS: Computer and information sciencesComputer Science - Computation and LanguageInformation retrievalComputer scienceInformationSystems_INFORMATIONSTORAGEANDRETRIEVAL02 engineering and technologyClusteringMedia MonitoringComputer Science - Information RetrievalComputingMethodologies_PATTERNRECOGNITIONMultilingual Methods0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingCluster analysisComputation and Language (cs.CL)Information Retrieval (cs.IR)
researchProduct

Polysemy in Controlled Natural Language Texts

2015

Computational semantics and logic-based controlled natural languages (CNL) do not address systematically the word sense disambiguation problem of content words, i.e., they tend to interpret only some functional words that are crucial for construction of discourse representation structures. We show that micro-ontologies and multi-word units allow integration of the rich and polysemous multi-domain background knowledge into CNL thus providing interpretation for the content words. The proposed approach is demonstrated by extending the Attempto Controlled English (ACE) with polysemous and procedural constructs resulting in a more natural CNL named PAO covering narrative multi-domain texts.

FOS: Computer and information sciencesComputer Science - Computation and LanguageInterpretation (logic)Computer sciencebusiness.industryRepresentation (arts)Content wordcomputer.software_genrelanguage.human_languageControlled natural languageComputational semanticslanguageAttempto Controlled EnglishArtificial intelligencePolysemybusinessComputation and Language (cs.CL)computerNatural languageNatural language processing
researchProduct

Towards the evaluation of automatic simultaneous speech translation from a communicative perspective

2021

In recent years, automatic speech-to-speech and speech-to-text translation has gained momentum thanks to advances in artificial intelligence, especially in the domains of speech recognition and machine translation. The quality of such applications is commonly tested with automatic metrics, such as BLEU, primarily with the goal of assessing improvements of releases or in the context of evaluation campaigns. However, little is known about how the output of such systems is perceived by end users or how they compare to human performances in similar communicative tasks. In this paper, we present the results of an experiment aimed at evaluating the quality of a real-time speech translation engine…

FOS: Computer and information sciencesComputer Science - Computation and LanguageMachine translationEnd userComputer sciencebusiness.industrymedia_common.quotation_subjectSample (statistics)Context (language use)Intelligibility (communication)computer.software_genreSpeech translationQuality (business)Artificial intelligencebusinessComputation and Language (cs.CL)computerInterpreterNatural language processingmedia_commonProceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)
researchProduct

Hybrid blind robust image watermarking technique based on DFT-DCT and Arnold transform

2018

In this paper, a robust blind image watermarking method is proposed for copyright protection of digital images. This hybrid method relies on combining two well-known transforms that are the discrete Fourier transform (DFT) and the discrete cosine transform (DCT). The motivation behind this combination is to enhance the imperceptibility and the robustness. The imperceptibility requirement is achieved by using magnitudes of DFT coefficients while the robustness improvement is ensured by applying DCT to the DFT coefficients magnitude. The watermark is embedded by modifying the coefficients of the middle band of the DCT using a secret key. The security of the proposed method is enhanced by appl…

FOS: Computer and information sciencesComputer Science - Cryptography and SecurityComputer Networks and CommunicationsComputer scienceMultiple Watermarking02 engineering and technologyDiscrete Fourier transformImage (mathematics)Digital imageDiscrete Fourier transform (DFT)SchemeRobustness (computer science)Quantization0202 electrical engineering electronic engineering information engineeringMedia TechnologyDiscrete cosine transformHybrid method[INFO]Computer Science [cs]Digital watermarkingDiscrete cosine transform (DCT)DistanceImage watermarking020207 software engineeringWatermarkMultimedia (cs.MM)Hardware and ArchitectureMedical ImagesEmbedding020201 artificial intelligence & image processingArnold transformWavelet DomainSvdCryptography and Security (cs.CR)AlgorithmCopyright protectionSoftwareComputer Science - Multimedia
researchProduct

A Robust Blind 3-D Mesh Watermarking Technique Based on SCS Quantization and Mesh Saliency for Copyright Protection

2019

Due to the recent demand of 3-D meshes in a wide range of applications such as video games, medical imaging, film special effect making, computer-aided design (CAD), among others, the necessity of implementing 3-D mesh watermarking schemes aiming to protect copyright has increased in the last decade. Nowadays, the majority of robust 3-D watermarking approaches have mainly focused on the robustness against attacks while the imperceptibility of these techniques is still a serious challenge. In this context, a blind robust 3-D mesh watermarking method based on mesh saliency and scalar Costa scheme (SCS) for Copyright protection is proposed. The watermark is embedded by quantifying the vertex n…

FOS: Computer and information sciencesComputer Science - Cryptography and SecurityComputer science[INFO.INFO-TS] Computer Science [cs]/Signal and Image ProcessingQuantization (signal processing)Data_MISCELLANEOUS020207 software engineeringWatermark02 engineering and technologyGraphics (cs.GR)Computer Science - Graphics[INFO.INFO-TS]Computer Science [cs]/Signal and Image ProcessingComputer engineering0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingPolygon meshVertex normalQuantization (image processing)Digital watermarkingCryptography and Security (cs.CR)ComputingMilieux_MISCELLANEOUSSmoothing
researchProduct

A blind Robust Image Watermarking Approach exploiting the DFT Magnitude

2019

Due to the current progress in Internet, digital contents (video, audio and images) are widely used. Distribution of multimedia contents is now faster and it allows for easy unauthorized reproduction of information. Digital watermarking came up while trying to solve this problem. Its main idea is to embed a watermark into a host digital content without affecting its quality. Moreover, watermarking can be used in several applications such as authentication, copy control, indexation, Copyright protection, etc. In this paper, we propose a blind robust image watermarking approach as a solution to the problem of copyright protection of digital images. The underlying concept of our method is to a…

FOS: Computer and information sciencesComputer Science - Cryptography and SecurityComputer sciencebusiness.industryComputer Vision and Pattern Recognition (cs.CV)Gaussian blurComputer Science - Computer Vision and Pattern RecognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONWatermarkFilter (signal processing)Discrete Fourier transformsymbols.namesakeDigital imageGaussian noisesymbolsDiscrete cosine transformComputer visionArtificial intelligencebusinessDigital watermarkingCryptography and Security (cs.CR)Histogram equalization
researchProduct