- About
-
The Global ETD Search service is a free service for researchers
to find electronic theses and dissertations. This service is
provided by the
Networked Digital Library of Theses and Dissertations.
Our metadata is collected from universities around the world. If you manage a university/consortium/country archive and want to be added, details can be found on the NDLTD website.
Search results
Showing 621 to 630 of 1298 (0.024 seconds)Spelling suggestions: "subject:"signs inn"" "subject:"signs iin""
| 621 |
A critical investigation of deaf comprehension of signed tv news interpretationWehrmeyer, Jennifer Ella January 2013 (has links)
This study investigates factors hampering comprehension of sign language interpretations rendered on South African TV news bulletins in terms of Deaf viewers’ expectancy norms and corpus analysis of authentic interpretations. The research fills a gap in the emerging discipline of Sign Language Interpreting Studies, specifically with reference to corpus studies. The study presents a new model for translation/interpretation evaluation based on the introduction of Grounded Theory (GT) into a reception-oriented model. The research question is addressed holistically in terms of target audience competencies and expectations, aspects of the physical setting, interpreters’ use of language and interpreting choices. The South African Deaf community are incorporated as experts into the assessment process, thereby empirically grounding the research within the socio-dynamic context of the target audience. Triangulation in data collection and analysis was provided by applying multiple mixed data collection methods, namely questionnaires, interviews, eye-tracking and corpus tools. The primary variables identified by the study are the small picture size and use of dialect. Secondary variables identified include inconsistent or inadequate use of non-manual features, incoherent or non-simultaneous mouthing, careless or incorrect sign execution, too fast signing, loss of visibility against skin or clothing, omission of vital elements of sentence structure, adherence to source language structures, meaningless additions, incorrect referencing, oversimplification and violations of Deaf norms of restructuring, information transfer, gatekeeping and third person interpreting. The identification of these factors allows the construction of a series of testable hypotheses, thereby providing a broad platform for further research. Apart from pioneering corpus-driven sign language interpreting research, the study makes significant contributions to present knowledge of evaluative models, interpreting strategies and norms and systems of transcription and annotation. / Linguistics / Thesis (D. Litt.et Phil. (Linguistics)
|
| 622 |
A critical investigation of deaf comprehension of signed tv news interpretationWehrmeyer, Jennifer Ella January 2013 (has links)
This study investigates factors hampering comprehension of sign language interpretations rendered on South African TV news bulletins in terms of Deaf viewers’ expectancy norms and corpus analysis of authentic interpretations. The research fills a gap in the emerging discipline of Sign Language Interpreting Studies, specifically with reference to corpus studies. The study presents a new model for translation/interpretation evaluation based on the introduction of Grounded Theory (GT) into a reception-oriented model. The research question is addressed holistically in terms of target audience competencies and expectations, aspects of the physical setting, interpreters’ use of language and interpreting choices. The South African Deaf community are incorporated as experts into the assessment process, thereby empirically grounding the research within the socio-dynamic context of the target audience. Triangulation in data collection and analysis was provided by applying multiple mixed data collection methods, namely questionnaires, interviews, eye-tracking and corpus tools. The primary variables identified by the study are the small picture size and use of dialect. Secondary variables identified include inconsistent or inadequate use of non-manual features, incoherent or non-simultaneous mouthing, careless or incorrect sign execution, too fast signing, loss of visibility against skin or clothing, omission of vital elements of sentence structure, adherence to source language structures, meaningless additions, incorrect referencing, oversimplification and violations of Deaf norms of restructuring, information transfer, gatekeeping and third person interpreting. The identification of these factors allows the construction of a series of testable hypotheses, thereby providing a broad platform for further research. Apart from pioneering corpus-driven sign language interpreting research, the study makes significant contributions to present knowledge of evaluative models, interpreting strategies and norms and systems of transcription and annotation. / Linguistics and Modern Languages / Thesis (D. Litt.et Phil. (Linguistics)
|
| 623 |
Sprachproduktionstest zu narrativen Kompetenzen in Deutscher Gebärdensprache (NaKom DGS) - eine TestadaptionKolbe, Vera 09 February 2023 (has links)
Diese Erwerbsstudie beschreibt die Adaption eines Testverfahrens aus der Britischen Gebärdensprache von Herman et al. (2004) in Deutsche Gebärdensprache (DGS). NaKom DGS ist ein Testverfahren das narrative und grammatische Kompetenzen in Kindererzählungen analysiert. NaKom DGS elizitiert Erzählungen mittels eines kurzen sprachfreien Stimulus-Videos und ist für Kinder im Alter von 4-11 Jahren validiert. In einer Querschnittsstudie wurde das Testverfahren mit 97 Kindern deutschlandweit durchgeführt, um das Testverfahren zu validieren. Die Referenzwerte für NaKom DGS basieren auf den Erzählungen von 72 Kindern mit Zugang zu DGS ab Geburt durch taube in DGS kommunizierende Eltern.
Durch diese Studie wurden neue Erkenntnisse zum Spracherwerb von DGS gewonnen. Die gefundenen Erwerbsverläufe bieten Wissenschaftler_innen in vielen der untersuchten Strukturen erste Anhaltspunkte für den Spracherwerb in DGS, mit denen zukünftige Forschungsergebnisse verglichen werden können.
Ausgewertet werden als narrative Kompetenzen Strukturelemente nach dem globalen Strukturmodell von Labov and Waletzky (1973), sowie Erzählinhalt und Reihenfolge der Erzählung. Als grammatische Kompetenzen werden in Anlehnung an Johnston (2016) auf kleiner satzähnlicher Ebene Verbmodifikationen analysiert: Modifikationen der Art und Weise, direktionale Modifikationen, aspektuelle Modifikationen und abbildende Verben. Auf Textebene, d.h. in Bezug zur gesamten Erzählung, wird konstruierte Aktion untersucht.
Die Referenzwerte von NaKom DGS werden cross-linguistisch mit den Ergebnissen des Grundlagentests, sowie einer weiteren Adaption in Amerikanische Gebärdensprache (Enns et al. 2019) verglichen und dadurch zusätzlich bestätigt. / This acquisition study describes the test adaptation process of the British Sign Language (BSL) Productive Skills test from Herman et al. (2004) to German Sign Language (DGS), resulting in the new assessment tool „Sprachproduktionstest zu narrativen Kompetenzen in Deutscher Gebärdensprache“ (NaKom DGS). NaKom DGS analyzes narrative and grammatical competences in children´s narrations, that are elicited via a short language free videoclip. In a nationwide cross-sectional study NaKom DGS was validated with data from 97 signing children, 4-11 years old. The standards for the test are derived from the results of 72 native signing children, that acquire DGS from Deaf DGS signing parents.
This study provides new insights in language acquisition in DGS. Up to now research in DGS acquisition is sparse, therefore the results of NaKom DGS are the first insights in many of the analyzed areas. The results provide scholars with first insights and stepping stones for future research.
This study focuses on narrative competences as the global structural elements from the model of Labov and Waletzky (1973), as well as narrative content and narrative sequence. Grammatic competences specifically modifications of verbs are analyzed on the level of small clause like units, following Johnston (2016): indicating directional modifications, depicting verbs, aspect and manner. On text level constructed action is analyzed across the whole narration.
Additionally the newly developed standards for NaKom DGS are compared to the standards from the BSL test as well as another adaptation to American Sign Language (Enns et al. 2019). This cross-linguistic comparison supports the validity of the German test results.
|
| 624 |
Modeling of guide sign illumination and retroreflectivity to improve driver’s visibility and safetyObeidat, Mohammed January 1900 (has links)
Doctor of Philosophy / Department of Industrial & Manufacturing Systems Engineering / Malgorzata J. Rys / This dissertation is the result of studying different methods of increasing guide sign visibility and legibility to drivers during nighttime, to increase safety on roadways. It also studies intersection lighting to indicate the lighting benefits on nighttime crash frequency reduction.
From a survey conducted, practices related to overhead guide sign illumination and retroreflectivity in United States were summarized. A laboratory experiment was conducted to compare light distribution of five light sources: Metal Halide, Mercury Vapor, High Pressure Sodium, induction lighting, and Light Emitting Diode (LED). Cost analysis of the five light sources was performed. Combining results of the laboratory experiment and the cost analysis, induction lighting was recommended for states that want to continue external sign illumination. A retroreflectivity experiment was conducted to compare three types of retroreflective sheeting: Engineering Grade (type I), Diamond Grade (type XI), and High Intensity (type IV), to determine the sheeting that best increases visibility and legibility. Diamond Grade (type XI) was found to be the optimal sheeting that increases visibility and legibility to drivers during nighttime. A glare experiment was conducted to expand the retroreflectivity experiment results. Four sheeting-font combinations of High Intensity (type IV) and Diamond Grade (type XI) materials and Series E (Modified) and Clearview fonts were compared. Results revealed an optimal sheeting-font combination of Diamond Grade (type XI) sheeting and Clearview font which increases the visibility and legibility of guide signs to drivers under presence of oncoming glare source. The Highway Safety Information System (HSIS) database was used to study the effect of intersection lighting on the expected crash frequency. Illuminated intersections showed 3.61% and 6.54% decrease in the expected nighttime crash frequency as compared to dark intersections in Minnesota and California, respectively. In addition, partial lighting at intersections decreases the expected nighttime crash frequency by 4.72% compared to continuous lighting in Minnesota.
The recommended sheeting-font combination for Departments of Transportation was Diamond Grade (type XI) and Clearview. This combination will increase signs’ visibility and legibility to drivers, and consequently increase safety on roadways. Adding partial lighting at intersections will reduce the expected nighttime crash frequency, and increase safety on roadways.
|
| 625 |
The design of a generic signing avatar animation systemFourie, Jaco 12 1900 (has links)
Thesis (MScIng)--University of Stellenbosch, 2006. / ENGLISH ABSTRACT: We designed a generic avatar animator for use in sign language related projects.
The animator is capable of animating any given avatar that is compliant with the
H-Anim standard for humanoid animation. The system was designed with the
South African Sign Language Machine Translation (SASL-MT) project in mind,
but can easily be adapted to other sign language projects due to its generic design.
An avatar that is capable of accurately performing sign language gestures is
a special kind of avatar and is referred to as a signing avatar. In this thesis we
investigate the special characteristics of signing avatars and address the issue of
finding a generic design for the animation of such an avatar. / AFRIKAANSE OPSOMMING: Ons het ’n generiese karakteranimasiestelsel ontwikkel vir gebruik in gebaretaal
verwante projekte. Die animasiestelsel het die vermo¨e om enige karaktermodel
wat met die H-Anim standaard versoenbaar is, te animeer. Die animasiestelsel
is ontwerp met die oog op gebruik in die South African Sign Language Machine
Translation (SASL-MT) projek, maar kan maklik aangepas word vir ander
gebaretaalprojekte te danke aan die generiese ontwerp.
’n Karaktermodel wat in staat is om gebare akkuraat te maak is ’n spesiale
tipe karaktermodel wat bekend staan as ’n gebaretaal avatar (Engels : signing
avatar). In hierdie tesis ondersoek ons die spesiale eienskappe van ’n gebaretaal
avatar en beskou die soektog na ’n generiese ontwerp vir die animering van
so ’n karaktermodel.
|
| 626 |
Contribution à la traduction automatique français/langue des signes française (LSF) au moyen de personnages virtuels : Contribution à la génération automatique de la LSFKervajan, LoÏc 09 December 2011 (has links)
Depuis la loi du 11-02-2005 pour l’égalité des droits et des chances, les lieux ouverts au public doivent accueillir les Sourds en Langue des Signes Française (LSF). C’est dans le cadre du développement d’outils technologiques de diffusion de LSF que nous avons travaillé, plus particulièrement au niveau de la traduction automatique du français écrit vers la LSF. Notre thèse commence par un état de l’art relatif aux connaissances sur la LSF (ressources disponibles et supports d’expression de la LSF) avant d’approfondir des notions de grammaire descriptive. Notre hypothèse de travail est la suivant : la LSF est une langue et, à ce titre, la traduction automatique lui est applicable.Nous décrivons ensuite les spécifications linguistiques pour le traitement automatique, en fonction des observations mises en avant dans l’état de l’art et des propositions de nos informateurs. Nous détaillons notre méthodologie et présentons l’avancée de nos travaux autour de la formalisation des données linguistiques à partir des spécificités de la LSF dont certaines (model verbal, modification adjectivale et adverbiale, organisation des substantifs, problématiques de l’accord) ont nécessité un traitement plus approfondi. Nous présentons le cadre applicatif dans lequel nous avons travaillé : les systèmes de traduction automatique et d’animation de personnage virtuel de France Telecom R&D. Puis, après un rapide état de l’art sur les technologies avatar nous décrivons nos modalités de contrôle du moteur de synthèse de geste grâce au format d’échange mis au point. Enfin, nous terminons par nos évaluations et perspectives de recherche et de développements qui pourront suivre cette Thèse.Notre approche a donné ses premiers résultats puisque nous avons atteint notre objectif de faire fonctionner la chaîne complète de traduction : de la saisie d'un énoncé en français jusqu'à la réalisation de l'énoncé correspondant en LSF par un personnage de synthèse. / Since the law was voted the 11-02-2005 for equal rights and opportunities: places open to anyone (public places, shops, internet, etc.) should welcome the Deaf in French Sign Language (FSL). We have worked on the development of technological tools to promote LSF, especially in machine translation from written French to FSL.Our thesis begins with a presentation of knowledge on FSL (theoretical resources and ways to edit FSL) and follows by further concepts of descriptive grammar. Our working hypothesis is: FSL is a language and, therefore, machine translation is relevant.We describe the language specifications for automatic processing, based on scientific knowledge and proposals of our native FSL speaker informants. We also expose our methodology, and do present the advancement of our work in the formalization of linguistic data based on the specificities of FSL which certain (verbs scheme, adjective and adverb modification, organization of nouns, agreement patterns) require further analysis.We do present the application framework in which we worked on: the machine translation system and virtual characters animation system of France Telecom R&D.After a short avatar technology presentation, we explain our control modalities of the gesture synthesis engine through the exchange format that we developed.Finally, we conclude with an evaluation, researches and developments perspectives that could follow this thesis.Our approach has produced its first results since we have achieved our goal of running the full translation chain: from the input of a sentence in French to the realization of the corresponding sentence in FSL with a synthetic character.
|
| 627 |
Undersökning av webbsidors säkerhet vid användning avFacebook Login : Vidareutveckling och analys av OAuthGuardHedmark, Alice January 2019 (has links)
Single Sign-On (SSO) är en autentiseringsprocess som tillåter en utvecklare att delegera autentiseringsansvaret till en dedikerad tjänst. OAuth 2.0 är ett auktoriseringsramverk som ofta står som grund för ett autentiseringslager som i sin tur möjliggör SSO. En identitetsleverantör är tjänsten som står för hantering av användaruppgifterna och autentiseringen, två vanliga identitetsleverantörer är Google och Facebook som i sin tur implementerar SSO med hjälp utav autentiseringslagren OpenID Connect respektive Facebooks egna autentiseringslager. Det har visat sig att många klienter som ska utnyttja SSO med OAuth 2.0 implementerar det fel så att säkerhetsbrister uppstår, studier har utförts med förslag till lösningar men många bristande implementationer fortsätter produceras och existera. Att skapa diverse verktyg för att främja säkerhet i dessa sammanhang är en metod där OAuthGuard utvecklats med visionen att även kunna skydda användaren, direkt från en webbläsare. OAuthGuard har även tidigare använts för att analysera säkerheten med Google SSO och visat att 50% av undersökta klienter har brister, men motsvarande studie eller verktyg saknas för Facebook SSO. Denna studie gjorde en motsvarande undersökning för Facebook SSO-klienter med en vidareutvecklad version av OAuthGuard och fann att de lider av brister med liknande trend som tidigare studies resultat mot Google-SSO-klienter, men att färre Facebook- SSO-klienter har brister i jämförelse. Vid vidareutvecklingen av OAuthGuard upptäcktes ett antal svårigheter och framtiden för denna typ av verktyg behöver vidare analyseras. Vidare analys behöver även göras för att bedöma om Facebook-SSO kan vara att föredra över Google-SSO ur säkerhetsperspektiv samt vidare utforskande av nya säkerhetsfrämjande metoder behöver utföras. / Single Sign-On (SSO) is an authentication process that allows a developer to delegate the authentication responsibility to a dedicated service. OAuth 2.0 is an authorization framework that often serves as a base for authentication layers to be built upon that in turn allows for SSO. An identity provider is the service that is responsible for handling user credentials and the authentication, two common identity providers are Google and Facebook that implement SSO with the authentication layers OpenID Connect respectively Facebooks own authentication layer. It has been shown that many clients using OAuth 2.0 as base for SSO make faulty implementations leading to security issues, a number of studies has proposed solutions to these issues but faulty implementations are continually being made. To create various tools to promote security in these contexts is a method where OAuthGuard has been developed with the vision to also directly protect the common website user directly from the browser. OAuthGuard has been used in an earlier study to analyze the security of clients using Google SSO and discovered that 50% of the analyzed clients had flaws, no comparable study has been done for clients using Facebook SSO, which is the second largest third party log in variant. This study made a comparable investigation for Facebook SSO clients with a further developed version of OAuthGuard and found that these clients suffer from flaws with a similar trend as the previous study with Google-SSO clients, although fewer Facebook-SSO clients suffer from these flaws. When further developing OAuthGuard a dumber of difficulties was discovered and the future of these kind of tools needs to be investigated. Further analysis needs to be done to assess if Facebook-SSO should be recommended over Google-SSO from a security perspective and also further exploration of new methods to promote security needs to be done.
|
| 628 |
Recherche de la production exotique de paires de quarks top de même signe au LHC avec le détecteur ATLAS / Search for same-sign top quark pair exotic production at the LHC with the ATLAS detectorBerlendis, Simon 21 September 2017 (has links)
Le Modèle Standard, qui décrit les interactions entre les particules à l’échelle quantique, est une théorie imparfaite. Il possède plusieurs problèmes théoriques non-résolus et ne permet pas d’expliquer certaines observations astrophysiques comme celles de la matière noire et de l’asymétrie baryonique. Plusieurs théories, dites au-delà du Modèle Standard, ont été proposées afin de résoudre certains de ces problèmes, et une grande partie d’entre elles prévoient l’apparition de nouveaux phénomènes à haute énergie. L’objectif principal de cette thèse est de rechercher ces phénomènes dans les collisions proton-proton produites par le Large Hadron Collider à une énergie de centre de masse de 13 TeV. Une partie des travaux présentés dans cette thèse a en particulier été dédiée à la recherche de processus de production de quarks top de même signe, c’est-à-dire de même charge électrique, qui sont prédits par des modèles de supersymétrie à R-parité violée. Ces processus engendrent des évènements composés de leptons de même charge accompagnés de b-jets, lesquels ont l’avantage d’être faiblement contaminer par le bruit de fond provenant du Modèle Standard.Les travaux présentés dans cette thèse ont essentiellement porté sur deux analyses, chacune recherchant des phénomènes de nouvelle physique de nature différente dans les évènements composés de leptons de même charge dans les données enregistrées par le détecteur ATLAS. Une première analyse a porté sur la recherche de processus supersymétriques sur les données enregistrées en 2015 et en 2016 avec 36.1 fb$^{-1}$ de luminosité intégrée. Des signaux de production de quarks top de même signe ont été implémentés en se basant sur des processus supersymétriques violant la R-parité, et des régions de signal associées à ces processus ont été optimisées. Une deuxième analyse a porté sur la recherche de processus non-supersymétriques, dits exotiques, dans les données enregistrées en 2015 avec 3.2 fb$^{-1}$ de luminosité intégrée. Cette analyse a surtout été motivée par les résultats obtenus à 8 TeV, dans lesquels un modeste excès de nombre d’évènements par rapport aux prédictions du Modèle Standard a été observé dans deux régions de signal. Une partie des études relatives à cette analyse a été dédiée au développement et à la validation des méthodes d’estimation des différentes sources de bruit de fond.Aucune déviation par rapport aux prédictions du Modèle Standard n’a été observée dans chacune des régions de signal considérées dans les deux analyses. L’excès qui avait été observé dans les résultats obtenus à 8 TeV n’est donc pas confirmé. Des limites d’exclusion sur les modèles de nouvelle physique ont de plus été extraites à partir des résultats obtenus, en particulier sur les modèles de supersymétrie à R-parité violée utilisés pour produire les processus de production de quarks top de même signe. / The Standard Model, which describes the particle interactions at quantum level, is an imperfect theory. It has several theoretical problems and is unable to explain astrophysical observations like the dark matter and the baryonic asymmetry of the universe. Several beyond-standard models have been proposed to solve some of these issues, and predict new-physics phenomena at high energy. The aim of this thesis is to search for these phenomena in proton-proton collisions produced by the Large Hadron Collider at a center-of-mass energy of 13 TeV. Part of the studies presented in this thesis was dedicated to the search for production of same-sign top quarks based on R-parity violating supersymmetric models. These processes lead to a signature of same-sign leptons and b-jets, which have the advantage to be lowly contaminated by the Standard Model background.The studies presented in this thesis focused on two analyses, both searching for new-physics phenomena of different nature in same-sign leptons events in data recorded by the ATLAS detector. A first analysis focused on supersymmetric processes with data recorded in 2015 and in 2016 with 36.1 fb$^{-1}$ of integrated luminosity. Same-sign top quarks signals were implemented using R-parity violating supersymmetric processes, and signal regions associated to these processes were optimized. A second analysis focused on exotic (non-supersymmetric) processes with data recorded in 2015 with 3.2 fb$^{-1}$ of integrated luminosity. This analysis was motivated by a modest excess seen in two signal regions in the 8 TeV results. Several studies were focused on the development and the validation of background estimation methods.No deviations from the Standard Model predictions were observed the signal regions considered in both analyses. The 8 TeV excess is therefore not confirmed with the most recent data. Exclusion limits on new-physics models were extracted, in particular for the R-parity violating supersymmetric models that were used to produce the same-sign top quarks processes.
|
| 629 |
Recherche d'évènements à deux quarks top de même charge avec le détecteur ATLAS. Etalonnage du calorimètre hadronique d’ATLAS avec un système laser / Search of events with two same-sign top quarks with the ATLAS detector. Calibration of the ATLAS hadronic calorimeter with a laser systemDubreuil, Emmanuelle 17 October 2014 (has links)
Le Modèle Standard de la physique des particules permet de décrire le comportement des particules et leurs interactions. L’une d’elles, le quark top, est la particule élémentaire la plus lourde connue à ce jour. Cette propriété lui confère un rôle privilégié dans les théories dites de Nouvelle Physique, il pourrait se coupler préférentiellement aux nouvelles particules prédites par ces modèles.Cette thèse a été menée auprès du détecteur ATLAS installé au LHC. La première partie de ce travail a porté sur l’étalonnage du calorimètre hadronique, une partie du détecteur servant entre autres à mesurer l’énergie des hadrons produits lors des collisions. Ce calorimètre est étalonné grâce à un système laser, qui envoie des pulses de lumière dans les 9852 canaux du calorimètre. Cette étude a permis de corriger les canaux dont le gain dérive en appliquant des facteurs correctifs aux données. La deuxième partie de cette thèse a été consacrée à la recherche d’évènements à deux quarks top de même charge. La topologie avec deux leptons de même charge permet d’avoir une signature claire et présente peu de bruits de fond prédits par le Modèle Standard. Deux versions de l’analyse sont présentées : l’une avec une partie des données enregistrées par ATLAS en 2012, la deuxième plus optimisée avec le lot complet de données de 2012. Ces optimisations ont améliorées d’un facteur 3 la sensibilité sur le signal. N’ayant pas observé d’excès dans les données, une limite sur la section efficace de production d’évènements à deux quarks top de même charge a été calculée dans le cadre de deux modèles effectifs. / The Standard Model of particle physics is used to describe the behavior of the particles and their interactions. One of them, the top quark, is the heaviest elementary particle. This property gives it a favored role in the New Physics theories, it could interact preferentially with new particles predicted by these models.This thesis was performed using the ATLAS detector at LHC. The first part of this work was on the calibration of the ATLAS hadronic calorimeter, part of the detector which is used to measure the energy of the hadrons produced during the collisions. The hadronic calorimeter is calibrated with a laser system, which sends pulses to the 9852 calorimeter’s channels. With this study, drifting channels were corrected by applying correction factors on the data.The second part of this thesis was dedicated to the search of events with two same-sign top quarks. The topology with a same-sign dilepton pair is used to have a clear signature and show only a few Standard Model backgroud processes. Two versions of this analysis are discussed : one of them with a part of the data collected in 2012 and the other one, with a lot of optimizations and with the complete dataset of 2012. These optimizations permits to improve the sensitivity of the signal by a factor 3. Without any excess observed in the data events, it is possible to calculate a limit on the cross section of the same-sign top quarks pair and interpreted in the case of two effective models.
|
| 630 |
Uma solu??o para gera??o autom?tica de trilhas em l?ngua brasileira de sinais em conte?dos multim?diaAra?jo, Tiago Maritan Ugulino de 14 September 2012 (has links)
Made available in DSpace on 2014-12-17T14:55:05Z (GMT). No. of bitstreams: 1
TiagoMUA_TESE.pdf: 1442352 bytes, checksum: a9909ef0bb9ebf04b3cad967bbf8be1c (MD5)
Previous issue date: 2012-09-14 / Conselho Nacional de Desenvolvimento Cient?fico e Tecnol?gico / Deaf people have serious difficulties to access information. The support for sign
languages is rarely addressed in Information and Communication Technologies (ICT).
Furthermore, in scientific literature, there is a lack of works related to machine translation
for sign languages in real-time and open-domain scenarios, such as TV. To minimize
these problems, in this work, we propose a solution for automatic generation of Brazilian
Sign Language (LIBRAS) video tracks into captioned digital multimedia contents. These
tracks are generated from a real-time machine translation strategy, which performs the
translation from a Brazilian Portuguese subtitle stream (e.g., a movie subtitle or a closed
caption stream). Furthermore, the proposed solution is open-domain and has a set
of mechanisms that exploit human computation to generate and maintain their linguistic
constructions. Some implementations of the proposed solution were developed for digital
TV, Web and Digital Cinema platforms, and a set of experiments with deaf users was developed
to evaluate the main aspects of the solution. The results showed that the proposed
solution is efficient and able to generate and embed LIBRAS tracks in real-time scenarios
and is a practical and feasible alternative to reduce barriers of deaf to access information,
especially when human interpreters are not available / Os surdos enfrentam s?rias dificuldades para acessar informa??es. As Tecnologias de
Informa??o e Comunica??o (TIC) quando s?o desenvolvidas dificilmente levam em considera??o
os requisitos espec?ficos destes usu?rios especiais. O suporte para l?nguas de
sinais, por exemplo, ? raramente explorado nessas tecnologias. Al?m disso, as solu??es
presentes na literatura relacionadas a tradu??o autom?tica para l?nguas de sinais s?o restritas
a um dom?nio de aplica??o espec?fico ou n?o s?o vi?veis para cen?rios que necessitam
de tradu??o em tempo real, como, por exemplo, na TV. Para reduzir esses problemas,
neste trabalho ? proposta uma solu??o para gera??o autom?tica de trilhas em L?ngua Brasileira
de Sinais (LIBRAS) em conte?dos digitais multim?dia legendados. As trilhas de
LIBRAS s?o geradas a partir de uma estrat?gia de tradu??o autom?tica e em tempo real
para LIBRAS, que realiza a tradu??o a partir de fluxos de legendas (como, por exemplo,
legendas ou closed caption) em l?ngua portuguesa. Al?m disso, a solu??o proposta
? de dom?nio geral e dotada de um conjunto de mecanismos que exploram a colabora??o
e a computa??o humana para gerar e manter suas constru??es ling??sticas de forma
eficiente. Implementa??es da solu??o proposta foram desenvolvidas para as plataformas
de TV Digital, Web e Cinema Digital, e um conjunto de experimentos, incluindo testes
com usu?rios surdos, foi desenvolvido para avaliar os principais aspectos da solu??o. Os
resultados mostraram que a solu??o proposta ? eficiente, capaz de gerar e embarcar as
trilhas de LIBRAS em cen?rios que exigem tradu??o em tempo real, al?m de ser uma
alternativa pr?tica e vi?vel para redu??o das barreiras de acesso ? informa??o dos surdos,
especialmente quando int?rpretes humanos n?o est?o dispon?veis
|
Page generated in 0.0765 seconds