Les Learning Games sont des environnements d’apprentissage, souvent informatisés, qui utilisent des ressorts ludiques pour catalyser l’attention des apprenants et ainsi faciliter leur apprentissage. Ils ont des atouts indéniables mais présentent également certaines limites, comme des situations d’apprentissage trop artificielles. Ces limites peuvent être dépassées par l’intégration d’interactions en Réalité Mixte dans les Learning Games, que nous appelons alors des Mixed Reality Learning Games (MRLG). La Réalité Mixte, qui combine environnements numériques et objets réels, ouvre de nouvelles possibilités d’interactions et d’apprentissage qui gomment les limites précédentes et qu’il faut repérer et explorer. Dans ce contexte, nous nous intéressons au processus de conception des MRLG. Dans un premier temps, nous présentons une étude sur l’utilisation de la Réalité Mixte dans les domaines de l’apprentissage et du jeu, incluant un état de l’art des MRLG. Cette étude montre que, malgré de nombreux atouts, la conception des MRLG reste difficile à maîtriser. En effet, il n’existe ni méthode ni outil adapté à la conception de ce type d’environnements. Dans un second temps, nous analysons et modélisons l’activité de conception des MRLG à travers la littérature et des expériences de conception, dont une menée dans le cadre du projet SEGAREM. Cette démarche révèle des verrous spécifiques tels que l’absence d’aide à la modélisation (ou formalisation), à la créativité et à la vérification de la cohérence des idées. Nous éclairons nos réponses à ces besoins par un recensement des outils utilisés dans les domaines liés aux MRLG : situations d’apprentissage, jeux et environnements de la Réalité Mixte. Ceci nous amène à proposer deux outils conceptuels : un modèle de description de MRLG (f-MRLG) et des aides à la créativité sous la forme de propositions puis de recommandations. Le modèle de description a pour objectif de formaliser l’ensemble des éléments constituant un MRLG, mais aussi d’être un moyen d’identifier les éléments à définir, de structurer et de vérifier les idées. Les listes de propositions et recommandations ont pour but d’aider le concepteur à faire des choix cohérents par rapport à la situation d’apprentissage visée, en particulier en ce qui concerne les types de jeux et les dispositifs de Réalité Mixte. Une première évaluation de ces propositions a conduit à leur amélioration. Ces propositions sont à l’origine de la conception et du développement d’un outil auteur informatisé : MIRLEGADEE (Mixed Reality Learning Game DEsign Environment). MIRLEGADEE est basé sur LEGADEE, un environnement auteur pour la conception de Learning Games. Une expérimentation auprès de 20 enseignants et concepteurs de formation a validé le bienfondé de cet outil qui guide effectivement les concepteurs dans les phases amont du processus de conception de MRLG malgré des limites pour l’accompagnement de tâches complexes. / Game-based learning is one efficient pedagogical concept that uses game principles to incite learners to engage into learning activities. Learning Games (LG) are commonly known as digital environments. They have undeniable assets but also some limits, such as the artificiality of the learning context. In the mean time, new technologies have been increasingly developed, thus providing new perspectives in game-based learning. In particular, Mixed Reality (MR) technologies merge both real and digital worlds. Mixed Reality Learning Games (MRLG) offer real benefits for teaching: they enable active pedagogy trough the physical immersion of learners, “in situ” information while practicing and authentic context. In our work, we focus on the design process of MRLG. The first part of the thesis presents how Mixed Reality is used for educational and gaming purposes. An analysis of existing MRLG shows both their assets and the complexity of their design. MRLG designers have to cope with all the difficulties of learning design, game design and mixed reality design at the same time, and with the integration of all aspects in a coherent way. Besides, there is a lack of specific tool or methodology. In order to understand the specific needs of MRLG designers, we analyze and model the MRLG design activity from MRLG design processes described in papers and existing methodologies for LG and MR. We also illustrate and clarify MRLG design needs with the observation of a MRLG design activity in the SEGAREM project. We highlight some needs for modeling, creativity, and verification of coherence. To meet the identified needs, the third part is dedicated to a state of the art of tools available for learning design, game design and Mixed Reality design. This study leads us to three solutions to assist MRLG design: a model, a set of tools for creativity, and an authoring tool. We first propose a model called f-MRLG to describe fully and clearly a MRLG. f-MRLG is a support to MRLG design as it helps designer to organize their ideas and to identify which elements must be described. It also reinforces mutual comprehension in a team. Our second proposal is a set of tools for creativity: lists of possibilities, examples and suggestions for game types and Mixed Reality systems choices. We conducted a first experiment on the two proposals, which led to their improvement. These two proposals drove to the design and development of an authoring tool, named MIRLEGADEE (MIxed Reality LEarning GAme DEsign Environment), to support the MRLG design. This tool is an extension of LEGADEE, which already supports the design of learning games using a computer. An experiment with 20 teachers and training designers validated that MIRLEGADEE successfully guides the designers in the MRLG design process, in spite of limits for the support of complex tasks.

The use of instructional technology has opened up new avenues in education with broad implications in the foreign or additional language (L2) learning context. One of the research priorities is to explore student perceptions of the use of such modern means in their education which otherwise might not be anticipated. The present study aimed to determine (a) the perceived affordances as well as limitations of the information and communication technology (ICT) pedagogical application in coded corrective feedback (e-feedback) provision on L2 writing, (b) English as a foreign language (EFL) learners’ perspectives on using e-feedback to reduce their local and global mistakes, and (c) the type of self-regulated learning (SRL) behaviours, according to EFL students’ self-reports, electronic feedback and learning logs called forth in cognitive, affective, and metacognitive domains. The participants (n=48) were high-intermediate to advanced EFL learners from four cohorts enrolled on an International English Language Testing System (IELTS) preparation course in a branch of the Institute of Science and Technology in Tehran. Each cohort went through 84 face-to-face tutorial sessions in four months. During this period, they also wrote essays and received e-feedback on 12 IELTS Writing Task 2 prompts with a minimum of drafting work three times for each on an e-learning platform (www.ekbatani.ir) specially designed for this study. The data from all four cohorts were collected over the course of 11 months, using semi-structured interviews, online structured and unstructured learning logs, and an open-ended questionnaire to provide an in-depth picture of student perceptions of this technology mediation. Through a purely qualitative research design, the log, interview, and open-ended questionnaire data were analysed, categorised and coded. The findings represented students’ perceptions of the benefits of the e-feedback and learning logs as (i) offering a motivating and empowering means of providing EFL writing support, (ii) enhancing the thinking and problem-solving processes, (iii) a flexible and fast scaffolding approach for L2 writing improvement, and (iv) encouraging student writers’ active knowledge construction by helping them notice mistakes, focus on writing specifics, overcome the fear of writing, and grow confidence in L2 learning. The self-reported data indicated perceived limitations including (i) the time-consuming nature of the e-feedback processes, (ii) the occasional need for face-to-face discussions, peer feedback addition, providing supplements to e-feedback such as on-demand e-tutorials, and (iii) increased workload for the teacher in proportion to the number of students. Specific writing improvement was perceived to be locally in the use of punctuation signs and grammar, in spelling skills and the scope of vocabulary; and globally in organising ideas, finding ideas in the form of blueprints, and developing ideas into full-length essays. The student perceptions demonstrated that the learner-centred e-feedback environment created different affordances for students’ cognitive, affective, and metacognitive behaviours: (i) cognitively, it assisted the use and development of various learning strategies, enhanced student EFL writing experience, and increased awareness of error patterns in their essays; (ii) affectively, it supported students’ motivational processes, ability to appraise their progress, restore, and sustain positivity, and greater perceived self-efficacy beliefs in their own L2 writing skills; finally, (iii) metacognitive affordances included the ability to rethink and amend their plans as well as seek out support, ability to reflect on the writing processes holistically, ability to self-monitor to remain on course, and ability to devise and implement a plan of action mostly by finding a strategy to deal with mistakes and by taking greater caution in writing their future drafts. Despite arising from a particular contextual framework with the experience of particular cohorts of students, the findings can hopefully be of value to researchers and practitioners in the fields of online language pedagogy, second language acquisition (SLA), EFL writing, and computer-assisted language learning (CALL) with communication uses. The findings can assist language courseware designers, e-feedback platform developers, and L2 writing course administrators to support and enhance their practices and decisions, especially in providing and implementing ICT and SRL initiatives in EFL writing.

Educators who teach international students English as a second language (ESL) or English speakers teaching English as a foreign language (EFL) in universities in non- English speaking countries in the Asia-Pacific region are often challenged to develop culturally appropriate curriculum for a diverse group of learners. Prompted by educational policy over the past two decades, the technological infrastructure in most universities throughout the world has advanced. Innovative tools for language learning have been developed for computer-assisted instruction. The purpose of the present study was to assess to what extent teachers use multimedia in EFL/ESL university classrooms in relation to the theoretical underpinnings of constructivism as well as Rogers' (1995) theory of diffusion of innovations and adopter categories. Further, the study aimed to ascertain what factors contribute to or discourage teachers' use of multimedia in tertiary level English language teaching classrooms. A mixed- method research design was used and both quantitative and qualitative data were collected. One hundred and seventy-nine English-language teachers from five universities in the Asia-Pacific region were interviewed and data were collected on their use of multimedia. Complex relationships were found among teacher-held educational and cultural values, teaching experience, formal computer professional learning, nationality, institution, region, age, gender, and collaboration with colleagues. Results showed that even with adequate access to hardware, software, technical support and computer professional learning, most teachers in the study made limited use of multimedia in the EFL/ESL classroom. As well, the results indicated that teachers in all three universities in Taiwan used multimedia in the EFL/ESL classroom less than teachers in Australia and in Thailand. Teachers who endorsed constructivist teaching methodologies tended to use multimedia more. Also, teachers with fewer than ten years teaching experience tended to use technology in teaching more. Data showed the use of integrated technology by teachers usually diminished as teachers got older. However, results showed that teachers who engaged in professional learning tended to use multimedia more regardless of age. Future directions in technology integration and recommendations for creating and sustaining a culture of technology at educational institutions are offered. Suggestions for professional development to encourage the integrated use of technology in English language teaching programs are outlined.

Les travaux de thèse s'inscrivent dans le domaine des Environnements Informatiques pour l'Apprentissage Humain (EIAH). Ils portent sur la proposition de processus, méthodes et outils pour assister les enseignants et les formateurs dans la réutilisation et la capitalisation des scénarios d'apprentissage. L'approche proposée nommée CAPtuRe a pour objectif de modéliser, évaluer et exploiter les informations contextuelles relatives à un scénario en se basant sur des observations effectives de ce dernier pour améliorer la réutilisation.Les problématiques étudiées concernent : (1) l'expression et l'analyse du contexte d'usage, (2) l'évaluation de la pertinence du scénario dans un contexte précis, (3) l'indexation des contextes sur la base de critères de réussite et d'efficacité du scénario pour la définition de son périmètre de réutilisation et (4) la suggestion proactive de réutilisation.Nous avons commencé par la spécification d'un cadre global d'ingénierie et de réutilisation de scénarios d'apprentissage. Dans ce cadre, nous avons défini un processus qui spécifie le cycle de vie du scénario explicitant la dimension contextuelle et son utilisation dans un environnement de "conception par la réutilisation". Pour opérationnaliser ce processus, nous avons défini une approche générique de modélisation de l'information contextuelle enrichie par les indicateurs, une méthode d'indexation et un algorithme de calcul de similarités contextuelles pour la sélection et la recommandation de scénarios appropriés à une situation d'apprentissage cible. Ces contributions ont été implémentées sous la forme d'une plateforme logicielle et appliquées sur des cas d'usage de scénarios hybrides. / The work presented in this thesis is a part of the Technology Enhanced Learning domain. It focuses on the proposal of processes, methods and tools that assist teachers and trainers in the reuse and the capitalization of educational scenarios. The objective of the proposed approach named CAPtuRe is to model, evaluate and exploit the contextual information related to a scenario based on its effective observations with the aim to enhance reuse. The main concerns are: (1) the expression and the analysis of the usage context, (2) the evaluation of the relevance of the scenario in a specific context, (3) the indexing of the contexts based on criteria of success and effectiveness of the scenario to define its reuse scope and (4) the proactive suggestion of reuse. We started by specifying a global framework for the engineering and the reuse of educational scenarios. In this context, we have defined a process specifying the scenario lifecycle introducing the contextual dimension and its utilization in a "design by reuse" environment. In order to operationalize this process, we define a generic approach to model the contextual information of a scenario that is enriched by the indicators, an indexing method and an algorithm calculating contextual similarities for the selection and the recommendation of appropriated scenarios to a target learning situation. These contributions are implemented as a software platform and applied to hybrid scenarios usage cases.

La question générale envisagée dans cette recherche est le développement d'une représentation de scénarios d'apprentissage adaptable et facile à utiliser sous la forme d'une table (considéré comme un artefact de facile manipulation par les enseignants), associée à un modèle informatique sous la forme d'en arbre (comme un moyen d'intégrer des services avancés). Cette représentation permet à des enseignants sans entraînement méthodologique et ayant des compétences technologiques de base d'éditer et mettre en œuvre des scénarios d'apprentissage à partir d'une interface graphique intuitive et flexible. Bien que cette thèse soit centrée sur des scénarios collaboratifs, l'approche basée sur un modèle table-arbre (nommé T2) que nous proposons présente un intérêt plus général. Dans une première phase, nous avons développé à partir de ce modèle un éditeur de scénarios d'apprentissage (nommé ediT2) proposant des notions de modélisation utilisées dans les scénarios collaboratifs. Dans une seconde phase, nous avons considéré des questions de généralisation à travers l'extension de l'implémentation initiale, de telle manière à permettre aux utilisateurs d'éditer les notions et leurs attributs. Nous avons examiné à travers des études et expériences comment des enseignants ont utilisé notre proposition en tenant en compte comme objectifs/critères d'évaluation: (1) son expressivité pédagogique, i.e., si des éditeurs basés sur tables peuvent représenter une large gamme de scénarios d'apprentissage ; (2) sa facilité et son intuitivité ; (3) son expressivité informatique, i.e., si l'approche permet l'implémentation de services demandant des manipulations informatiques complexes ; et (4) sa flexibilité informatique, i.e., s'il est facile d'adapter l'éditeur à des besoins locaux. / The general issue considered in this research is the development of an adaptable and easy-to-use representation of learning scenarios in the form of a table (considered as an artefact of easy manipulation by teachers) associated with a computational model as a tree (as a way to integrate advanced services). In this way, teachers with basic technological skills and without methodological training can edit and operationalize learning scenarios from flexible and friendly graphical interfaces. Although this thesis has its focus on CSCL scripts, the table-tree-based approach (named T2) presents a more general interest. In a first moment, we implemented from this model a learning scenario editor (named ediT2) using notions from CSCL scripts. In a second moment, we considered generalization issues through the extension of the initial implementation, in order to allow teachers to edit their own notions and respective attributes. We investigated from different studies and experiments how teachers used our proposal considering as objectives/evaluation criteria the following features: (1) pedagogical expressiveness (can table-based editors represent a wide range of learning scenarios?); (2) usability (do teachers find the editor easy to use and intuitive?); (3) computational expressiveness (does the approach allow implementation of advanced services?), and; (4) computational flexibility (is the editor easy to adapt to local needs?).

Computer assisted language learning (CALL) comprises a wide range of information technologies that aim to broaden the context of teaching by getting advantages of IT. For example, a few efforts have been put on including a combination of voice and its visual representation for language learning, and some studies are reporting positive outcomes. However, more research is needed in order to assess the impact caused by specific visualization styles such as: highlighting syllables and/or wave of sound. In order to explore this issue, we focused at measuring the potential impact that two distinct visualization styles and its combination can have on teaching children the pronunciation of English as a second language. We built a prototype which was designed to assist students while learning pronunciation of syllables. This system was employing two different real-time interactive visualization styles. One of these visualization styles utilizes audio capturing and processing, using a recent technology development: Web Audio API.We evaluated the effect of our prototype with an experiment with children aged from 9 to 11years old. We followed an experimental approach with a control group and three experimental groups. We tested our hypothesis that states that the use of a combined visualization style can have greater impact at learning pronunciation in comparison with traditional learning approach.Initial descriptive analyses were suggesting promising results for the group that used the combined visualization prototype. However, additional statistical analyses were carried out in order to measure the effect of prototype as accurately as possible within the constraints of our study. Further analyses provided evidence that our combined visualizations prototype has positively affected the learning of pronunciation. Nonetheless, the difference was not big comparing to the system that employed only wave of sound visualization. Ability to perceive visual information differs among individuals. Therefore, further research with different sample division is needed to determine whether is the combination of visualizations that does the effect, or is the wave in itself. Slitting groups based on this characteristic and perform the testing will be considered for the future research.Eventually, we can be confident to continue exploring further the possibility of integrating our proposed combination of two visualization styles in teaching practices of second language learning, due to positive outcomes that our current research outlined. In addition, from a technological perspective, our work is at the forefront of exploring the use of tools such as Web Audio API for CALL.

Learning Management Systems (LMSs), in a blended learning educational environment, support face to face education and enable enhanced communication and interaction among instructors and students as well as among students. However, Technology-Enhanced Learning (TEL), which improves the learning process, does not come without challenges. The aim of this research is double fold. Firstly, it aims to explore users’ –instructors and students- perceptions on how the LMS Open eClass, in TEI of Athens Greece, supports and facilitates their communication and interaction. Secondly, based on users’ needs and desires, the study aims to formulate suggestions for improving communication and interaction through the platform. The study adopts an interpretivist stance and is built upon an inductive qualitative approach. Firstly, users’ perceptions are solicited through semi-structured interviews and the collected data are analyzed through the thematic analysis method. Subsequently, the study adopts Soft Systems Methodology (SSM) to capture the complexity of the situation, derived from the different worldviews of instructors and students in their association with Open eClass and emerge suggestions for improvements. The results indicate that Open eClass is used to facilitate instructors convey material and information to students, while neither meaningful communication and interaction nor collaboration is performed adequately through the platform. However, the users have expressed a positive disposition towards utilizing these capabilities of the platform, as they recognize their fundamental importance to learning, especially during an economic crisis which constraints the physical presence of many students in classes. Therefore, the study proposes three, accommodating to all, systemically desirable and culturally feasible changes that could improve the situation, mainly based on pedagogy. Overall, this research contributes to existing knowledge about the usage of LMS regarding interaction and communication in a blended learning environment by providing a holistic view on users’ perceptions and identifying changes capable to bring about improvements.

Les connaissances perceptivo-gestuelles sont difficiles à saisir dans les Systèmes Tutoriels Intelligents. Ces connaissances sont multimodales : elles combinent des connaissances théoriques, ainsi que des connaissances perceptuelles et gestuelles. Leur enregistrement dans les Systèmes Tutoriels Intelligents implique l'utilisation de plusieurs périphériques ou capteurs couvrant les différentes modalités des interactions qui les sous-tendent. Les « traces » de ces interactions –aussi désignées sous le terme "traces d'activité"- constituent la matière première pour la production de services tutoriels couvrant leurs différentes facettes. Les analyses de l'apprentissage ou les services tutoriels privilégiant une facette de ces connaissances au détriment des autres, sont incomplets. Cependant, en raison de la diversité des périphériques, les traces d'activité enregistrées sont hétérogènes et, de ce fait, difficiles à modéliser et à traiter. Mon projet doctoral adresse la problématique de la production de services tutoriels adaptés à ce type de connaissances. Je m'y intéresse tout particulièrement dans le cadre des domaines dits mal-définis. Le cas d'étude de mes recherches est le Système Tutoriel Intelligent TELEOS, un simulateur dédié à la chirurgie orthopédique percutanée. Les propositions formulées se regroupent sous trois volets : (1) la formalisation des séquences d'interactions perceptivo-gestuelles ; (2) l'implémentation d'outils capables de réifier le modèle conceptuel de leur représentation ; (3) la conception et l'implémentation d'outils algorithmiques favorisant l'analyse de ces séquences d'un point de vue didactique. / Perceptual-gestural knowledge is multimodal : they combine theoretical and perceptual and gestural knowledge. It is difficult to capture in Intelligent Tutoring Systems. In fact, its capture in such systems involves the use of multiple devices or sensors covering all the modalities of underlying interactions. The "traces" of these interactions -also referred to as "activity traces"- are the raw material for the production of key tutoring services that consider their multimodal nature. Methods for "learning analytics" and production of "tutoring services" that favor one or another facet over others, are incomplete. However, the use of diverse devices generates heterogeneous activity traces. Those latter are hard to model and treat.My doctoral project addresses the challenge related to the production of tutoring services that are congruent to this type of knowledge. I am specifically interested to this type of knowledge in the context of "ill-defined domains". My research case study is the Intelligent Tutoring System TELEOS, a simulation platform dedicated to percutaneous orthopedic surgery.The contributions of this thesis are threefold : (1) the formalization of perceptual-gestural interactions sequences; (2) the implementation of tools capable of reifying the proposed conceptual model; (3) the conception and implementation of algorithmic tools fostering the analysis of these sequences from a didactic point of view.

This thesis will concentrate on previous and current learning methods of French as a foreign language. This understanding will help to plot the rapidness of evolution within foreign-language teaching. In conjunction with this evolution the thesis will also give a brief overview of the exponential development of technology. It will focus specifically on how technology created a new way of learning. The aim of this thesis is to depict whether there is a need to adapt the French language classroom with the current learning technologies in use. The thesis will also show that since people are different and since each generation differs in its learning preference, that technology can help to bridge the ever-growing gap between the learner and the learning material since people learn work on different ways. According to the proof that generations differ from each other and that the current young generation is referred to as the Net-generation, it will be clearly shown that this generation prefers to learn with technology. The correct mix of learning methods, learning technologies and different learning styles is one that is humanly impossible to achieve in a conventional way. It is on this basis then that the thesis will show that the correct e-learning technology should form an integral part of the new language classroom as it is the only solution to ensure that learning stays current and adaptive, and that it keeps on playing an important part in the evolution of mankind. Furthermore, a brief study will be conducted on the current and prospective use of e-learning technologies in the French language classroom of South Africa. / Thesis (MA (French))--University of Pretoria, 2004. / Modern European Languages / unrestricted

[EN] In recent years, on-line multimedia repositories have experiencied a strong growth that have made them consolidated as essential knowledge assets, especially in the area of education, where large repositories of video lectures have been built in order to complement or even replace traditional teaching methods. However, most of these video lectures are neither transcribed nor translated due to a lack of cost-effective solutions to do so in a way that gives accurate enough results. Solutions of this kind are clearly necessary in order to make these lectures accessible to speakers of different languages and to people with hearing disabilities. They would also facilitate lecture searchability and analysis functions, such as classification, recommendation or plagiarism detection, as well as the development of advanced educational functionalities like content summarisation to assist student note-taking. For this reason, the main aim of this thesis is to develop a cost-effective solution capable of transcribing and translating video lectures to a reasonable degree of accuracy. More specifically, we address the integration of state-of-the-art techniques in Automatic Speech Recognition and Machine Translation into large video lecture repositories to generate high-quality multilingual video subtitles without human intervention and at a reduced computational cost. Also, we explore the potential benefits of the exploitation of the information that we know a priori about these repositories, that is, lecture-specific knowledge such as speaker, topic or slides, to create specialised, in-domain transcription and translation systems by means of massive adaptation techniques. The proposed solutions have been tested in real-life scenarios by carrying out several objective and subjective evaluations, obtaining very positive results. The main outcome derived from this thesis, The transLectures-UPV Platform, has been publicly released as an open-source software, and, at the time of writing, it is serving automatic transcriptions and translations for several thousands of video lectures in many Spanish and European universities and institutions. / [ES] Durante estos últimos años, los repositorios multimedia on-line han experimentado un gran crecimiento que les ha hecho establecerse como fuentes fundamentales de conocimiento, especialmente en el área de la educación, donde se han creado grandes repositorios de vídeo charlas educativas para complementar e incluso reemplazar los métodos de enseñanza tradicionales. No obstante, la mayoría de estas charlas no están transcritas ni traducidas debido a la ausencia de soluciones de bajo coste que sean capaces de hacerlo garantizando una calidad mínima aceptable. Soluciones de este tipo son claramente necesarias para hacer que las vídeo charlas sean más accesibles para hablantes de otras lenguas o para personas con discapacidades auditivas. Además, dichas soluciones podrían facilitar la aplicación de funciones de búsqueda y de análisis tales como clasificación, recomendación o detección de plagios, así como el desarrollo de funcionalidades educativas avanzadas, como por ejemplo la generación de resúmenes automáticos de contenidos para ayudar al estudiante a tomar apuntes. Por este motivo, el principal objetivo de esta tesis es desarrollar una solución de bajo coste capaz de transcribir y traducir vídeo charlas con un nivel de calidad razonable. Más específicamente, abordamos la integración de técnicas estado del arte de Reconocimiento del Habla Automático y Traducción Automática en grandes repositorios de vídeo charlas educativas para la generación de subtítulos multilingües de alta calidad sin requerir intervención humana y con un reducido coste computacional. Además, también exploramos los beneficios potenciales que conllevaría la explotación de la información de la que disponemos a priori sobre estos repositorios, es decir, conocimientos específicos sobre las charlas tales como el locutor, la temática o las transparencias, para crear sistemas de transcripción y traducción especializados mediante técnicas de adaptación masiva. Las soluciones propuestas en esta tesis han sido testeadas en escenarios reales llevando a cabo nombrosas evaluaciones objetivas y subjetivas, obteniendo muy buenos resultados. El principal legado de esta tesis, The transLectures-UPV Platform, ha sido liberado públicamente como software de código abierto, y, en el momento de escribir estas líneas, está sirviendo transcripciones y traducciones automáticas para diversos miles de vídeo charlas educativas en nombrosas universidades e instituciones Españolas y Europeas. / [CAT] Durant aquests darrers anys, els repositoris multimèdia on-line han experimentat un gran creixement que els ha fet consolidar-se com a fonts fonamentals de coneixement, especialment a l'àrea de l'educació, on s'han creat grans repositoris de vídeo xarrades educatives per tal de complementar o inclús reemplaçar els mètodes d'ensenyament tradicionals. No obstant això, la majoria d'aquestes xarrades no estan transcrites ni traduïdes degut a l'absència de solucions de baix cost capaces de fer-ho garantint una qualitat mínima acceptable. Solucions d'aquest tipus són clarament necessàries per a fer que les vídeo xarres siguen més accessibles per a parlants d'altres llengües o per a persones amb discapacitats auditives. A més, aquestes solucions podrien facilitar l'aplicació de funcions de cerca i d'anàlisi tals com classificació, recomanació o detecció de plagis, així com el desenvolupament de funcionalitats educatives avançades, com per exemple la generació de resums automàtics de continguts per ajudar a l'estudiant a prendre anotacions. Per aquest motiu, el principal objectiu d'aquesta tesi és desenvolupar una solució de baix cost capaç de transcriure i traduir vídeo xarrades amb un nivell de qualitat raonable. Més específicament, abordem la integració de tècniques estat de l'art de Reconeixement de la Parla Automàtic i Traducció Automàtica en grans repositoris de vídeo xarrades educatives per a la generació de subtítols multilingües d'alta qualitat sense requerir intervenció humana i amb un reduït cost computacional. A més, també explorem els beneficis potencials que comportaria l'explotació de la informació de la que disposem a priori sobre aquests repositoris, és a dir, coneixements específics sobre les xarrades tals com el locutor, la temàtica o les transparències, per a crear sistemes de transcripció i traducció especialitzats mitjançant tècniques d'adaptació massiva. Les solucions proposades en aquesta tesi han estat testejades en escenaris reals duent a terme nombroses avaluacions objectives i subjectives, obtenint molt bons resultats. El principal llegat d'aquesta tesi, The transLectures-UPV Platform, ha sigut alliberat públicament com a programari de codi obert, i, en el moment d'escriure aquestes línies, està servint transcripcions i traduccions automàtiques per a diversos milers de vídeo xarrades educatives en nombroses universitats i institucions Espanyoles i Europees. / Silvestre Cerdà, JA. (2016). Different Contributions to Cost-Effective Transcription and Translation of Video Lectures [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/62194 / TESIS