O rápido desenvolvimento da tecnologia da informação traz oportunidades para área da educação, colocando a educação a distância e aprendizagem online como opções para o modelo tradicional, sobretudo os Massive Open Online Courses (MOOCs), os quais, no contexto do movimento de educação aberta, são apresentados como meio para aumentar o acesso e a qualidade da educação, proporcionando redução dos custos e da desigualdade educacional, sobretudo nos países em desenvolvimento. A revisão sistemática de 74 artigos evidenciou que as IES estão incorporando os MOOCs às suas práticas - em parte, produzindo seus próprios MOOCs, mas também os integrando a seus currículos, tanto para revisar conteúdo do Ensino Médio com alunos ingressantes no Ensino Superior quanto para melhorar seus cursos.Assim, considerando que as pesquisas que avaliam a incorporação dos MOOCs aos currículos das IES investigam, sobretudo, o desempenho e o nível de satisfação dos alunos, o objetivo principal desse estudo foi compreender como os MOOCs estão sendo incorporados aos cursos presenciais de graduação e qual o valor funcional percebido pelos alunos com relação a essa prática. Para tal, foi realizada uma revisão sistemática da literatura e um estudo de caso de caráter exploratório e descritivo, que integra os enfoques qualitativo e quantitativo. A unidade de análise do estudo de caso foi a disciplina de Fundamentos de Administração, lecionada no primeiro ano do curso bacharelado em Administração, e quatro fontes de evidências foram utilizadas: documentos sobre o MOOC, documentação sobre a disciplina que utilizou o MOOC, entrevistas com o Chefe de Departamento e os professores responsáveis pela disciplina e levantamento (survey) com 101 alunos. As evidências obtidas nas etapas de investigação documental e entrevistas foram analisadas baseando-se nas questões de pesquisas, enquanto o levantamento com os alunos valeu-se da técnica de análise estatística de modelagem de equações estruturais, utilizando o software R. Os resultados do estudo permitiram identificar que, assim como sugerido pela literatura, o MOOC foi utilizado como recurso online no método blended learning em uma disciplina introdutória e substituindo parte da carga horária presencial, possibilitando o aumento do número de alunos por professor, além de tornar a disciplina mais atrativa para o alunado. Além disso, que o MOOC foi usado como recurso online para apresentação do conteúdo, enquanto os exercícios de fixação, as avaliações e as atividades complementares foram desenvolvidos pelos professores. As hipóteses propostas no estudo foram validadas: valor funcional percebido tem efeito positivo (r=0,801) na intenção de recompra (R2=64,15%), a qualidade percebida com relação ao processo de blended learning e a qualidade percebida com relação ao MOOC têm efeitos positivos (r=0,22e r=0,2929, respectivamente) no valor funcional percebido pelo aluno (R2=20,46%); a preferência e autodisciplina para realização de cursos a distância têm efeito positivo na qualidade percebida com relação ao processo de blended learning (r=0,2636 e R2=6,95%) e com relação ao MOOC (r=0,347 e R2=12,04%). Conclui-se que o valor funcional percebido pelo aluno é favorável, com escore de 4,53 (escala de 7 pontos), e é influenciado pela qualidade percebida com relação ao MOOC e ao processo de blended learning. / The rapid development of information technology brings opportunities for education, putting distance education and online learning as options for the traditional model of education, especially the Massive Open Online Courses (MOOCs), which in the context of the open education are presented as a means to increase access and quality of education, proportionate educational costs and inequality, especially in developing countries. The systematic review of 74 articles showed that HEIs are incorporating MOOCs into their practices. In part, by producing their own MOOCs, but also integrating them into their curricula, both to revise high school content with incoming higher education students and to improve their courses. Thus, considering that research evaluating the incorporation of MOOCs into The main objectives of this study were to understand how the MOOCs are being incorporated into undergraduate courses and what functional value students perceive in relation to this practice. For such, a systematic review of the literature and an exploratory and descriptive case study were carried out, integrating the qualitative and quantitative approaches. The unit of analysis of the case study was the Fundamentals of Administration discipline taught in the first year of the baccalaureate course in Administration and four sources of evidence were used: documents about the MOOC, documentation about the discipline that used the MOOC, interviews with teachers responsible for discipline and survey with the students. The evidence obtained in the documentary analysis and interviews were analyzed based on the research questions while the student lifting was based on the technique of statistical analysis modeling of structural equations using software R. The results of the study allowed to identify, that as suggested by the literature, the MOOC was used as an online resource in the blendedlearning method in an introductory discipline and replacing part of the classroom workload, making it possible to increase the number of students per teacher, in addition to making the course more attractive for the student. The MOOC was used as an online resource for content presentation, while the attachment exercises, assessments, and complementary activities were developed by teachers. The hypotheses proposed in the study were validated: perceived functional value has a positive effect (r = 0.801) on the intention to buy back (R2 = 64.15%), the quality perceived in relation to the blended learning process and perceived quality in relation to the MOOC have positive effects (r = 0.22 and r = 0.2929, respectively) on the functional value perceived by the student (R2 = 20.46%); (r = 0.2636 and R2 = 6.95%) and in relation to the MOOC (r = 0.347 and R 2 = 12), the preference and self-discipline for distance courses have a positive effect on the perceived quality of the blended learning process , 04%).It is concluded that the functional value perceived by the student is favorable, obtaining a score of 4.53 on a 7-point scale, and that this is influenced by the perceived quality in relation to the MOOC and in relation to the process of blended learning.

O rápido desenvolvimento da tecnologia da informação traz oportunidades para área da educação, colocando a educação a distância e aprendizagem online como opções para o modelo tradicional, sobretudo os Massive Open Online Courses (MOOCs), os quais, no contexto do movimento de educação aberta, são apresentados como meio para aumentar o acesso e a qualidade da educação, proporcionando redução dos custos e da desigualdade educacional, sobretudo nos países em desenvolvimento. A revisão sistemática de 74 artigos evidenciou que as IES estão incorporando os MOOCs às suas práticas - em parte, produzindo seus próprios MOOCs, mas também os integrando a seus currículos, tanto para revisar conteúdo do Ensino Médio com alunos ingressantes no Ensino Superior quanto para melhorar seus cursos.Assim, considerando que as pesquisas que avaliam a incorporação dos MOOCs aos currículos das IES investigam, sobretudo, o desempenho e o nível de satisfação dos alunos, o objetivo principal desse estudo foi compreender como os MOOCs estão sendo incorporados aos cursos presenciais de graduação e qual o valor funcional percebido pelos alunos com relação a essa prática. Para tal, foi realizada uma revisão sistemática da literatura e um estudo de caso de caráter exploratório e descritivo, que integra os enfoques qualitativo e quantitativo. A unidade de análise do estudo de caso foi a disciplina de Fundamentos de Administração, lecionada no primeiro ano do curso bacharelado em Administração, e quatro fontes de evidências foram utilizadas: documentos sobre o MOOC, documentação sobre a disciplina que utilizou o MOOC, entrevistas com o Chefe de Departamento e os professores responsáveis pela disciplina e levantamento (survey) com 101 alunos. As evidências obtidas nas etapas de investigação documental e entrevistas foram analisadas baseando-se nas questões de pesquisas, enquanto o levantamento com os alunos valeu-se da técnica de análise estatística de modelagem de equações estruturais, utilizando o software R. Os resultados do estudo permitiram identificar que, assim como sugerido pela literatura, o MOOC foi utilizado como recurso online no método blended learning em uma disciplina introdutória e substituindo parte da carga horária presencial, possibilitando o aumento do número de alunos por professor, além de tornar a disciplina mais atrativa para o alunado. Além disso, que o MOOC foi usado como recurso online para apresentação do conteúdo, enquanto os exercícios de fixação, as avaliações e as atividades complementares foram desenvolvidos pelos professores. As hipóteses propostas no estudo foram validadas: valor funcional percebido tem efeito positivo (r=0,801) na intenção de recompra (R2=64,15%), a qualidade percebida com relação ao processo de blended learning e a qualidade percebida com relação ao MOOC têm efeitos positivos (r=0,22e r=0,2929, respectivamente) no valor funcional percebido pelo aluno (R2=20,46%); a preferência e autodisciplina para realização de cursos a distância têm efeito positivo na qualidade percebida com relação ao processo de blended learning (r=0,2636 e R2=6,95%) e com relação ao MOOC (r=0,347 e R2=12,04%). Conclui-se que o valor funcional percebido pelo aluno é favorável, com escore de 4,53 (escala de 7 pontos), e é influenciado pela qualidade percebida com relação ao MOOC e ao processo de blended learning. / The rapid development of information technology brings opportunities for education, putting distance education and online learning as options for the traditional model of education, especially the Massive Open Online Courses (MOOCs), which in the context of the open education are presented as a means to increase access and quality of education, proportionate educational costs and inequality, especially in developing countries. The systematic review of 74 articles showed that HEIs are incorporating MOOCs into their practices. In part, by producing their own MOOCs, but also integrating them into their curricula, both to revise high school content with incoming higher education students and to improve their courses. Thus, considering that research evaluating the incorporation of MOOCs into The main objectives of this study were to understand how the MOOCs are being incorporated into undergraduate courses and what functional value students perceive in relation to this practice. For such, a systematic review of the literature and an exploratory and descriptive case study were carried out, integrating the qualitative and quantitative approaches. The unit of analysis of the case study was the Fundamentals of Administration discipline taught in the first year of the baccalaureate course in Administration and four sources of evidence were used: documents about the MOOC, documentation about the discipline that used the MOOC, interviews with teachers responsible for discipline and survey with the students. The evidence obtained in the documentary analysis and interviews were analyzed based on the research questions while the student lifting was based on the technique of statistical analysis modeling of structural equations using software R. The results of the study allowed to identify, that as suggested by the literature, the MOOC was used as an online resource in the blendedlearning method in an introductory discipline and replacing part of the classroom workload, making it possible to increase the number of students per teacher, in addition to making the course more attractive for the student. The MOOC was used as an online resource for content presentation, while the attachment exercises, assessments, and complementary activities were developed by teachers. The hypotheses proposed in the study were validated: perceived functional value has a positive effect (r = 0.801) on the intention to buy back (R2 = 64.15%), the quality perceived in relation to the blended learning process and perceived quality in relation to the MOOC have positive effects (r = 0.22 and r = 0.2929, respectively) on the functional value perceived by the student (R2 = 20.46%); (r = 0.2636 and R2 = 6.95%) and in relation to the MOOC (r = 0.347 and R 2 = 12), the preference and self-discipline for distance courses have a positive effect on the perceived quality of the blended learning process , 04%).It is concluded that the functional value perceived by the student is favorable, obtaining a score of 4.53 on a 7-point scale, and that this is influenced by the perceived quality in relation to the MOOC and in relation to the process of blended learning.

In recent years thousands of people worldwide have been using Massive open on- line courses (MOOCs) for various reasons, including career development and change, continuing education, lifelong learning, and training. MOOCs are free online courses that anyone can enroll in and are an affordable and flexible way to learn new skills, develop professionally, and provide quality educational experience across the globe. Having an exemplary user interface will make users prefer most MOOC platforms, which inspired this study to know which MOOC platform has usability and better user experience by using the survey evaluation. The main objective of this study is to measure the usability components(effectiveness, efficiency, and overall user satisfaction level) to determine which MOOC platform, Coursera or Udemy, has a better user experience using the heuristic principles. A quantitative research method has been used in this paper, which focuses on sta- tistical, mathematical, and numerical analysis of data collected through surveys, questionnaires, and polls. In this paper, a questionnaire to determine user satis- faction through surveys has been developed. Usability has been evaluated for each MOOC platform (Coursera and Udemy) by calculating usability components. Sta- tistical methods like variance and standard deviations has been calculated using the survey results. Responses from the survey evaluation are collected and are graphically represented in bar graphs and pie charts. Respondent’s timings and statistical method results are presented in a tabular form. The satisfaction level is calculated and represented in a Likert scale format. The usability of two MOOC platforms (Coursera and Udemy) was measured by cal- culating usability components. Better user experience among Coursera and Udemy is measured using usability heuristic principles. This study concludes that effec- tiveness, efficiency, and satisfaction level while performing eight tasks given to the user is similar in both MOOC platforms (Coursera and Udemy). From the survey evaluation, the users preferred Udemy over Coursera.

Advocates of Massive Open Online Courses (MOOCs), a cross-cultural phenomenon that has attracted public attention throughout the world, portray them as an equalizing force in international higher education; but researchers have noted discrepancies in how learners from different countries have engaged with them. The number of MOOC learners in China is growing rapidly, and Chinese learners are enthusiastic about the unprecedented freedom they now have in selecting courses and accessing resources from the best international universities. However, they have a significantly low completion rate and may experience unique challenges about which little is known. This study took into account the diversity of MOOC learners and proposed changes to its course design to make it more inclusive for Chinese students. I used a mixed method—including document analysis, surveys, and interviews—to investigate the Chinese experience of taking Western MOOCs and also to explore the educational theories and design principles of MOOCs that have been discussed in the Western and Chinese literature. My analysis of the literature revealed issues of contextualization that may play a critical role in improving the MOOC experience for Chinese students. Drawing on theoretical educational frameworks—including motivation, community of inquiry, self-regulated learning, and social identity—my analysis of surveys and interviews identified common themes in the Chinese experience of Western MOOCs. In accordance with the results of my analysis, and also in line with interaction equivalency and situational principles, this study provided suggestions for adapting MOOCs to Chinese learners, such as enhancing content quality, improving learner–learner and learner–instructor interactions, providing social support, and collaborating with local universities and agencies in providing technical and credentialing support.

MOOCs實現了高等教育的跨國性、大量性與開放性，成功將世界各地的學習者、教學者與相關機構帶進全球網絡，為全球知識與傳播提供一個全新的平台。這場由世界頂尖大學所引發的MOOCs風暴，短時間內便席捲全球，在高等教育界掀起一陣波瀾。《紐約時報》甚至將MOOCs形容成一場「校園海嘯」，以迅雷不及掩耳的速度，衝擊高等教育的百年現場。 然而，究竟這場MOOCs風暴是如何一路延燒到世界各地？不同階段的影響因素又有何不同？為了釐清這些問題，本研究利用複雜理論「系統性」與「動態性」的觀點，探討MOOCs創新擴散之動態歷程，分析相關因素如何影響各個階段的歷程演變，以及因素之間互動後所產生的回饋關係。 本研究採用歷史研究法，並參考王美雅（2005）的創新擴散之動態模型，做為研究架構之基礎，探討MOOCs各階段擴散歷程之初始狀態、演化與正向回饋效果以及自我組織的現象。 研究結果發現，MOOCs的擴散事實上是一個自我組織的過程。在MOOCs擴散過程中，以「創新者的網路位置」與「理解創新的難易程度」兩項變數的影響尤其顯著。而各項變數之間不僅擁有正向回饋效果，亦存在著負向回饋效果，進而影響MOOCs的擴散與演化。 / MOOCs successfully brought global students, educators, and related organization into a global network, forming a platform for global diffusion of knowledge. Started by top universities around the globe, MOOCs’ forces have swept around the globe in a short amount of time, creating ripples in the higher education web. The New York Times describes MOOCs as a “Campus Tsunami,” sweeping through the sectors of higher education. How did this “Campus Tsunami” sweep around the globe? What are the factors that affect its dynamic diffusion process? In order to clarify these questions, this study employs the systematic and dynamic point of view of the complex theory to analyze how the factors influence each of MOOCs diffusion stages and what effects the factors create after interaction. This study employs the historical study method and Mei Ya, Wang’s (2005) dynamic innovation diffusion model as the fundamental structure to explore the initial conditions, evolution and positive reinforcements, and self-organization of each diffusion stage. The results demonstrate that MOOCs’ diffusion is based on self-organization. Within the seven factors, innovator networks and the difficulties in understanding innovation are the foremost influential factors. During MOOCs diffusion stages, the different factors interact with each other, producing both positive reinforcements and negative reinforcements, thus influencing MOOCs continuous diffusion and development.

This thesis contributes to knowledge about how Massive Open Online Courses (MOOCs) as educational online platforms can be utilized in achieving the purposes of Education for Sustainable Development (ESD). Starting out from a view that, in the face of global challenges every individual is an important actor with agency to drive for necessary social changes, the overall ambition of this thesis is to investigate the role of MOOCs, as a specific form of online learning, in empowering and enabling learners to acquire the competences needed to take responsible actions and informed decisions in a rapidly changing, interdependent and unequal world. More specifically, this thesis aims at providing a deeper insight into the question of whether the pedagogic approaches used in ESD (learner-centered, action-oriented and transformative learning) and the learning processes that they promote, can be incorporated in the MOOC environment. This issue holds importance due to the global and intergenerational character of ESD where providing access to training and learning for sustainable development for all is vital. In this respect, MOOCs have been envisioned as revolutionary in the provision of access to education to a wider audience. Nevertheless, the “massive” part of MOOCs could pose a challenge in connection to ESD, due to the fact that ESD is not easily generalized and aims at upholding local relevance. Therefore, this thesis also looks into the question of the implications posed by scale and the issue of scalability when investigating how MOOCs can enable the application of ESD pedagogic approaches, thus also contributing to the achievement of the purposes and learning objectives of ESD and Climate Change Education as its constituent part. Utilizing a case study methodology, the MOOC in Climate Change Leadership at Uppsala University is chosen as a case example of the MOOC learning environment and learning circumstances. By conducting a content analysis of the MOOC materials as presented on the online platform, and developing an analytical framework based on the ESD pedagogic approaches, this thesis reaches the conclusion that some aspects of the ESD approaches benefit from the networked environment and large-scale participation in the MOOC environment, while the incorporation of others is more challenging and asks for further research and improvement of the MOOC learning environment in order for them to provide for the optimal learning circumstances and outcomes in connection to ESD.

Cette thèse porte sur les tests adaptatifs dans les environnements d’apprentissage. Elle s’inscrit dans les contextes de fouille de données éducatives et d’analytique de l’apprentissage, où l’on s’intéresse à utiliser les données laissées par les apprenants dans des environnements éducatifs pour optimiser l’apprentissage au sens large.L’évaluation par ordinateur permet de stocker les réponses des apprenants facilement, afin de les analyser et d’améliorer les évaluations futures. Dans cette thèse, nous nous intéressons à un certain type de test par ordinateur, les tests adaptatifs. Ceux-ci permettent de poser une question à un apprenant, de traiter sa réponse à la volée, et de choisir la question suivante à lui poser en fonction de ses réponses précédentes. Ce processus réduit le nombre de questions à poser à un apprenant tout en conservant une mesure précise de son niveau. Les tests adaptatifs sont aujourd’hui implémentés pour des tests standardisés tels que le GMAT ou le GRE, administrés à des centaines de milliers d’étudiants. Toutefois, les modèles de tests adaptatifs traditionnels se contentent de noter les apprenants, ce qui est utile pour l’institution qui évalue, mais pas pour leur apprentissage. C’est pourquoi des modèles plus formatifs ont été proposés, permettant de faire un retour plus riche à l’apprenant à l’issue du test pour qu’il puisse comprendre ses lacunes et y remédier. On parle alors de diagnostic adaptatif.Dans cette thèse, nous avons répertorié des modèles de tests adaptatifs issus de différents pans de la littérature. Nous les avons comparés de façon qualitative et quantitative. Nous avons ainsi proposé un protocole expérimental, que nous avons implémenté pour comparer les principaux modèles de tests adaptatifs sur plusieurs jeux de données réelles. Cela nous a amenés à proposer un modèle hybride de diagnostic de connaissances adaptatif, meilleur que les modèles de tests formatifs existants sur tous les jeux de données testés. Enfin, nous avons élaboré une stratégie pour poser plusieursquestions au tout début du test afin de réaliser une meilleure première estimation des connaissances de l’apprenant. Ce système peut être appliqué à la génération automatique de feuilles d’exercices, par exemple sur un cours en ligne ouvert et massif (MOOC). / This thesis studies adaptive tests within learning environments. It falls within educational data mining and learning analytics, where student educational data is processed so as to optimize their learning.Computerized assessments allow us to store and analyze student data easily, in order to provide better tests for future learners. In this thesis, we focus on computerized adaptive testing. Such adaptive tests which can ask a question to the learner, analyze their answer on the fly, and choose the next question to ask accordingly. This process reduces the number of questions to ask to a learner while keeping an accurate measurement of their level. Adaptive tests are today massively used in practice, for example in the GMAT and GRE standardized tests, that are administered to hundreds of thousands of students. Traditionally, models used for adaptive assessment have been mostly summative : they measure or rank effectively examinees, but do not provide any other feedback. Recent advances have focused on formative assessments, that provide more useful feedback for both the learner and the teacher ; hence, they are more useful for improving student learning.In this thesis, we have reviewed adaptive testing models from various research communities. We have compared them qualitatively and quantitatively. Thus, we have proposed an experimental protocol that we have implemented in order to compare the most popular adaptive testing models, on real data. This led us to provide a hybrid model for adaptive cognitive diagnosis, better than existing models for formative assessment on all tried datasets. Finally, we have developed a strategy for asking several questions at the beginning of a test in order to measure the learner more accurately. This system can be applied to the automatic generation of worksheets, for example on a massive online open course (MOOC).

[EN] This thesis work contributes to the field of the {Automatic Speech Recognition} (ASR). And particularly to the {Interactive Speech Transcription} and {Confidence Measures} (CM) for ASR. The main goals of this thesis work can be summarised as follows: 1. To design IST methods and tools to tackle the problem of improving automatically generated transcripts. 2. To assess the designed IST methods and tools on real-life tasks of transcription in large educational repositories of video lectures. 3. To improve the reliability of the IST by improving the underlying (CM). Abstracts: The {Automatic Speech Recognition} (ASR) is a crucial task in a broad range of important applications which could not accomplished by means of manual transcription. The ASR can provide cost-effective transcripts in scenarios of increasing social impact such as the {Massive Open Online Courses} (MOOC), for which the availability of accurate enough is crucial even if they are not flawless. The transcripts enable search-ability, summarisation, recommendation, translation; they make the contents accessible to non-native speakers and users with impairments, etc. The usefulness is such that students improve their academic performance when learning from subtitled video lectures even when transcript is not perfect. Unfortunately, the current ASR technology is still far from the necessary accuracy. The imperfect transcripts resulting from ASR can be manually supervised and corrected, but the effort can be even higher than manual transcription. For the purpose of alleviating this issue, a novel {Interactive Transcription of Speech} (IST) system is presented in this thesis. This IST succeeded in reducing the effort if a small quantity of errors can be allowed; and also in improving the underlying ASR models in a cost-effective way. In other to adequate the proposed framework into real-life MOOCs, another intelligent interaction methods involving limited user effort were investigated. And also, it was introduced a new method which benefit from the user interactions to improve automatically the unsupervised parts ({Constrained Search} for ASR). The conducted research was deployed into a web-based IST platform with which it was possible to produce a massive number of semi-supervised lectures from two different well-known repositories, videoLectures.net and poliMedia. Finally, the performance of the IST and ASR systems can be easily increased by improving the computation of the {Confidence Measure} (CM) of transcribed words. As so, two contributions were developed: a new particular {Logistic Regresion} (LR) model; and the speaker adaption of the CM for cases in which it is possible, such with MOOCs. / [ES] Este trabajo contribuye en el campo del {reconocimiento automático del habla} (RAH). Y en especial, en el de la {transcripción interactiva del habla} (TIH) y el de las {medidas de confianza} (MC) para RAH. Los objetivos principales son los siguientes: 1. Diseño de métodos y herramientas TIH para mejorar las transcripciones automáticas. 2. Evaluar los métodos y herramientas TIH empleando tareas de transcripción realistas extraídas de grandes repositorios de vídeos educacionales. 3. Mejorar la fiabilidad del TIH mediante la mejora de las MC. Resumen: El {reconocimiento automático del habla} (RAH) es una tarea crucial en una amplia gama de aplicaciones importantes que no podrían realizarse mediante transcripción manual. El RAH puede proporcionar transcripciones rentables en escenarios de creciente impacto social como el de los {cursos abiertos en linea masivos} (MOOC), para el que la disponibilidad de transcripciones es crucial, incluso cuando no son completamente perfectas. Las transcripciones permiten la automatización de procesos como buscar, resumir, recomendar, traducir; hacen que los contenidos sean más accesibles para hablantes no nativos y usuarios con discapacidades, etc. Incluso se ha comprobado que mejora el rendimiento de los estudiantes que aprenden de videos con subtítulos incluso cuando estos no son completamente perfectos. Desafortunadamente, la tecnología RAH actual aún está lejos de la precisión necesaria. Las transcripciones imperfectas resultantes del RAH pueden ser supervisadas y corregidas manualmente, pero el esfuerzo puede ser incluso superior al de la transcripción manual. Con el fin de aliviar este problema, esta tesis presenta un novedoso sistema de {transcripción interactiva del habla} (TIH). Este método TIH consigue reducir el esfuerzo de semi-supervisión siempre que sea aceptable una pequeña cantidad de errores; además mejora a la par los modelos RAH subyacentes. Con objeto de transportar el marco propuesto para MOOCs, también se investigaron otros métodos de interacción inteligentes que involucran esfuerzo limitado por parte del usuario. Además, se introdujo un nuevo método que aprovecha las interacciones para mejorar aún más las partes no supervisadas (ASR con {búsqueda restringida}). La investigación en TIH llevada a cabo se desplegó en una plataforma web con el que fue posible producir un número masivo de transcripciones de videos de dos conocidos repositorios, videoLectures.net y poliMedia. Por último, el rendimiento de la TIH y los sistemas de RAH se puede aumentar directamente mediante la mejora de la estimación de la {medida de confianza} (MC) de las palabras transcritas. Por este motivo se desarrollaron dos contribuciones: un nuevo modelo discriminativo {logístico} (LR); y la adaptación al locutor de la MC para los casos en que es posible, como por ejemplo en MOOCs. / [CA] Aquest treball hi contribueix al camp del {reconeixment automàtic de la parla} (RAP). I en especial, al de la {transcripció interactiva de la parla} i el de {mesures de confiança} (MC) per a RAP. Els objectius principals són els següents: 1. Dissenyar mètodes i eines per a TIP per tal de millorar les transcripcions automàtiques. 2. Avaluar els mètodes i eines TIP per a tasques de transcripció realistes extretes de grans repositoris de vídeos educacionals. 3. Millorar la fiabilitat del TIP, mitjançant la millora de les MC. Resum: El {reconeixment automàtic de la parla} (RAP) és una tasca crucial per una àmplia gamma d'aplicacions importants que no es poden dur a terme per mitjà de la transcripció manual. El RAP pot proporcionar transcripcions en escenaris de creixent impacte social com els {cursos online oberts massius} (MOOC). Les transcripcions permeten automatitzar tasques com ara cercar, resumir, recomanar, traduir; a més a més, fa accessibles els continguts als parlants no nadius i els usuaris amb discapacitat, etc. Fins i tot, pot millorar el rendiment acadèmic de estudiants que aprenen de xerrades amb subtítols, encara que aquests subtítols no siguen perfectes. Malauradament, la tecnologia RAP actual encara està lluny de la precisió necessària. Les transcripcions imperfectes resultants de RAP poden ser supervisades i corregides manualment, però aquest l'esforç pot acabar sent superior a la transcripció manual. Per tal de resoldre aquest problema, en aquest treball es presenta un sistema nou per a {transcripció interactiva de la parla} (TIP). Aquest sistema TIP va ser reeixit en la reducció de l'esforç per quan es pot permetre una certa quantitat d'errors; així com també en en la millora dels models RAP subjacents. Per tal d'adequar el marc proposat per a MOOCs, també es van investigar altres mètodes d'interacció intel·ligents amb esforç d''usuari limitat. A més a més, es va introduir un nou mètode que aprofita les interaccions per tal de millorar encara més les parts no supervisades (RAP amb {cerca restringida}). La investigació en TIP duta a terme es va desplegar en una plataforma web amb la qual va ser possible produir un nombre massiu de transcripcions semi-supervisades de xerrades de repositoris ben coneguts, videoLectures.net i poliMedia. Finalment, el rendiment de la TIP i els sistemes de RAP es pot augmentar directament mitjançant la millora de l'estimació de la {Confiança Mesura} (MC) de les paraules transcrites. Per tant, es van desenvolupar dues contribucions: un nou model discriminatiu logístic (LR); i l'adaptació al locutor de la MC per casos en que és possible, per exemple amb MOOCs. / Sánchez Cortina, I. (2016). Confidence Measures for Automatic and Interactive Speech Recognition [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/61473