An investigation of the performance of a new Mechanical thrombectomy device using Bond Graph modelling: application to the extraction of blood clots in the middle cerebral artery

A number of thrombectomy devices using a variety of methods have now been developed to facilitate clot removal. We present research involving one such experimental device recently developed in the UK, called a ‘GP’ Thrombus Aspiration Device (GPTAD). This device has the potential to bring about the extraction of a thrombus. Although the device is at a relatively early stage of development, the results look encouraging. In this work, we present an analysis and modeling of the GPTAD by means of the bond graph technique; it seems to be a highly effective method of simulating the device under a variety of conditions. Such modeling is useful in optimizing the GPTAD and predicting the result of clot extraction. The aim of this simulation model is to obtain the minimum pressure necessary to extract the clot and to verify that both the pressure and the time required to complete the clot extraction are realistic for use in clinical situations, and are consistent with any experimentally obtained data. We therefore consider aspects of rheology and mechanics in our modeling.

Uniformly Reweighted Belief Propagation: A Factor Graph Approach

Tree-reweighted belief propagation is a message passing method that has certain advantages compared to traditional belief propagation (BP). However, it fails to outperform BP in a consistent manner, does not lend itself well to distributed implementation, and has not been applied to distributions with higher-order interactions. We propose a method called uniformly-reweighted belief propagation that mitigates these drawbacks. After having shown in previous works that this method can substantially outperform BP in distributed inference with pairwise interaction models, in this paper we extend it to higher-order interactions and apply it to LDPC decoding, leading performance gains over BP.

A graph-based approach for latency modeling and optimization in multiview video encoding

We present a novel framework for encoding latency analysis of arbitrary multiview video coding prediction structures. This framework avoids the need to consider an specific encoder architecture for encoding latency analysis by assuming an unlimited processing capacity on the multiview encoder. Under this assumption, only the influence of the prediction structure and the processing times have to be considered, and the encoding latency is solved systematically by means of a graph model. The results obtained with this model are valid for a multiview encoder with sufficient processing capacity and serve as a lower bound otherwise. Furthermore, with the objective of low latency encoder design with low penalty on rate-distortion performance, the graph model allows us to identify the prediction relationships that add higher encoding latency to the encoder. Experimental results for JMVM prediction structures illustrate how low latency prediction structures with a low rate-distortion penalty can be derived in a systematic manner using the new model.

Probabilistic Atlas Based Segmentation Using Affine Moment Descriptors and Graph-Cuts

We show a procedure for constructing a probabilistic atlas based on affine moment descriptors. It uses a normalization procedure over the labeled atlas. The proposed linear registration is defined by closed-form expressions involving only geometric moments. This procedure applies both to atlas construction as atlas-based segmentation. We model the likelihood term for each voxel and each label using parametric or nonparametric distributions and the prior term is determined by applying the vote-rule. The probabilistic atlas is built with the variability of our linear registration. We have two segmentation strategy: a) it applies the proposed affine registration to bring the target image into the coordinate frame of the atlas or b) the probabilistic atlas is non-rigidly aligning with the target image, where the probabilistic atlas is previously aligned to the target image with our affine registration. Finally, we adopt a graph cut - Bayesian framework for implementing the atlas-based segmentation.

Graph based study of allergen cross-reactivity of plant lipid transfer proteins (LTPs) using microarray in a multicenter study.

The study of cross-reactivity in allergy is key to both understanding. the allergic response of many patients and providing them with a rational treatment In the present study, protein microarrays and a co-sensitization graph approach were used in conjunction with an allergen microarray immunoassay. This enabled us to include a wide number of proteins and a large number of patients, and to study sensitization profiles among members of the LTP family. Fourteen LTPs from the most frequent plant food-induced allergies in the geographical area studied were printed into a microarray specifically designed for this research. 212 patients with fruit allergy and 117 food-tolerant pollen allergic subjects were recruited from seven regions of Spain with different pollen profiles, and their sera were tested with allergen microarray. This approach has proven itself to be a good tool to study cross-reactivity between members of LTP family, and could become a useful strategy to analyze other families of allergens.

Time series irreversibility: a visibility graph approach

We propose a method to measure real-valued time series irreversibility which combines two different tools: the horizontal visibility algorithm and the Kullback-Leibler divergence. This method maps a time series to a directed network according to a geometric criterion. The degree of irreversibility of the series is then estimated by the Kullback-Leibler divergence (i.e. the distinguishability) between the in and out degree distributions of the associated graph. The method is computationally efficient and does not require any ad hoc symbolization process. We find that the method correctly distinguishes between reversible and irreversible stationary time series, including analytical and numerical studies of its performance for: (i) reversible stochastic processes (uncorrelated and Gaussian linearly correlated), (ii) irreversible stochastic processes (a discrete flashing ratchet in an asymmetric potential), (iii) reversible (conservative) and irreversible (dissipative) chaotic maps, and (iv) dissipative chaotic maps in the presence of noise. Two alternative graph functionals, the degree and the degree-degree distributions, can be used as the Kullback-Leibler divergence argument. The former is simpler and more intuitive and can be used as a benchmark, but in the case of an irreversible process with null net current, the degree-degree distribution has to be considered to identify the irreversible nature of the series

Segmentation of RV in 4D Cardiac MR Volumes using region-merging graph cuts

Non-invasive quantitative assessment of the right ventricular anatomical and functional parameters is a challenging task. We present a semi-automatic approach for right ventricle (RV) segmentation from 4D MR images in two variants, which differ in the amount of user interaction. The method consists of three main phases: First, foreground and background markers are generated from the user input. Next, an over-segmented region image is obtained applying a watershed transform. Finally, these regions are merged using 4D graph-cuts with an intensity based boundary term. For the first variant the user outlines the inside of the RV wall in a few end-diastole slices, for the second two marker pixels serve as starting point for a statistical atlas application. Results were obtained by blind evaluation on 16 testing 4D MR volumes. They prove our method to be robust against markers location and place it favourably in the ranks of existing approaches.

Learning Analytics and Interactions in Virtual Learning Environments. A Comparative Study of Typologies and their Relationship with Academic Performance

Analysis of learning data (learning analytics) is a new research field with high growth potential. The main objective of Learning analytics is the analysis of data (interactions being the basic data unit) generated in virtual learning environments, in order to maximize the outcomes of the learning process; however, a consensus has not been reached yet on which interactions must be measured and what is their influence on learning outcomes. This research is grounded on the study of e-learning interaction typologies and their relationship with students? academic performance, by means of a comparative study between different interaction typologies (based on the agents involved, frequency of use and participation mode). The main conclusions are a) that classifications based on agents offer a better explanation of academic performance; and b) that each of the three typologies are able to explain academic performance in terms of some of their components (student-teacher and student-student interactions, evaluating students interactions and active interactions, respectively), with the other components being nonrelevant.

Predicting academic performance with learning analytics in virtual learning environments: A comparative study of three interaction classifications

Learning analytics is the analysis of static and dynamic data extracted from virtual learning environments, in order to understand and optimize the learning process. Generally, this dynamic data is generated by the interactions which take place in the virtual learning environment. At the present time, many implementations for grouping of data have been proposed, but there is no consensus yet on which interactions and groups must be measured and analyzed. There is also no agreement on what is the influence of these interactions, if any, on learning outcomes, academic performance or student success. This study presents three different extant interaction typologies in e-learning and analyzes the relation of their components with students? academic performance. The three different classifications are based on the agents involved in the learning process, the frequency of use and the participation mode, respectively. The main findings from the research are: a) that agent-based classifications offer a better explanation of student academic performance; b) that at least one component in each typology predicts academic performance; and c) that student-teacher and student-student, evaluating students, and active interactions, respectively, have a significant impact on academic performance, while the other interaction types are not significantly related to academic performance.

Hierarchical graph maps for visualization of collaborative recommender systems

In this paper we provide a method that allows the visualization of similarity relationships present between items of collaborative filtering recommender systems, as well as the relative importance of each of these. The objective is to offer visual representations of the recommender system?s set of items and of their relationships; these graphs show us where the most representative information can be found and which items are rated in a more similar way by the recommender system?s community of users. The visual representations achieved take the shape of phylogenetic trees, displaying the numerical similarity and the reliability between each pair of items considered to be similar. As a case study we provide the results obtained using the public database Movielens 1M, which contains 3900 movies.

A new label fusion method using graph cuts: application to hippocampus segmentation

The aim of this paper is to develop a probabilistic modeling framework for the segmentation of structures of interest from a collection of atlases. Given a subset of registered atlases into the target image for a particular Region of Interest (ROI), a statistical model of appearance and shape is computed for fusing the labels. Segmentations are obtained by minimizing an energy function associated with the proposed model, using a graph-cut technique. We test different label fusion methods on publicly available MR images of human brains.

A telecom analytics framework for dynamic quality of service management

Since the beginning of Internet, Internet Service Providers (ISP) have seen the need of giving to users? traffic different treatments defined by agree- ments between ISP and customers. This procedure, known as Quality of Service Management, has not much changed in the last years (DiffServ and Deep Pack-et Inspection have been the most chosen mechanisms). However, the incremen-tal growth of Internet users and services jointly with the application of recent Ma- chine Learning techniques, open up the possibility of going one step for-ward in the smart management of network traffic. In this paper, we first make a survey of current tools and techniques for QoS Management. Then we intro-duce clustering and classifying Machine Learning techniques for traffic charac-terization and the concept of Quality of Experience. Finally, with all these com-ponents, we present a brand new framework that will manage in a smart way Quality of Service in a telecom Big Data based scenario, both for mobile and fixed communications.

Diseño y desarrollo de un sistema basado en Learning Analytics para evaluar la competencia de trabajo en equipo.Design and development of a Learning Analytics System to evaluate group work competence

La adquisición de la competencia grupal es algo básico en la docencia universitaria. Esta tarea va a suponer evaluar diferentes factores en un número elevado de alumnos, lo que puede supone gran complejidad y un esfuerzo elevado. De cara a evitar este esfuerzo se puede pensar en emplear los registros de la interacción de los usuarios almacenados en las plataformas de aprendizaje. Para ello el presente trabajo se basa en el desarrollo de un sistema de Learning Analytics que es utilizado como herramienta para analizar las evidencias individuales de los distintos miembros de un equipo de trabajo. El trabajo desarrolla un modelo teórico apoyado en la herramienta, que permite relacionar las evidencias observadas de forma empírica para cada alumno, con indicadores obtenidos tanto de la acción individual como cooperativo de los miembros de un equipo realizadas a través de los foros de trabajo. Abstract — The development of the group work competence is something basic in university teaching. It should be evaluated, but this means to analyze different issues about the participation of a high number of students which is very complex and implies a lot of effort. In order to facilitate this evaluation it is possible to analyze the logs of students’ interaction in Learning Management Systems. The present work describes the development of a Learning Analytics system that analyzes the interaction of each of the members of working group. This tool is supported by a theoretical model, which allows establishing links between the empirical evidences of each student and the indicators of their action in working forums.

Heterogeneous architecture for the optimization of large-scale graph processing data centres

Con el auge del Cloud Computing, las aplicaciones de proceso de datos han sufrido un incremento de demanda, y por ello ha cobrado importancia lograr m�ás eficiencia en los Centros de Proceso de datos. El objetivo de este trabajo es la obtenci�ón de herramientas que permitan analizar la viabilidad y rentabilidad de diseñar Centros de Datos especializados para procesamiento de datos, con una arquitectura, sistemas de refrigeraci�ón, etc. adaptados. Algunas aplicaciones de procesamiento de datos se benefician de las arquitecturas software, mientras que en otras puede ser m�ás eficiente un procesamiento con arquitectura hardware. Debido a que ya hay software con muy buenos resultados en el procesamiento de grafos, como el sistema XPregel, en este proyecto se realizará una arquitectura hardware en VHDL, implementando el algoritmo PageRank de Google de forma escalable. Se ha escogido este algoritmo ya que podr��á ser m�ás eficiente en arquitectura hardware, debido a sus características concretas que se indicaráan m�ás adelante. PageRank sirve para ordenar las p�áginas por su relevancia en la web, utilizando para ello la teorí��a de grafos, siendo cada página web un vértice de un grafo; y los enlaces entre páginas, las aristas del citado grafo. En este proyecto, primero se realizará un an�álisis del estado de la técnica. Se supone que la implementaci�ón en XPregel, un sistema de procesamiento de grafos, es una de las m�ás eficientes. Por ello se estudiará esta �ultima implementaci�ón. Sin embargo, debido a que Xpregel procesa, en general, algoritmos que trabajan con grafos; no tiene en cuenta ciertas caracterí��sticas del algoritmo PageRank, por lo que la implementaci�on no es �optima. Esto es debido a que en PageRank, almacenar todos los datos que manda un mismo v�értice es un gasto innecesario de memoria ya que todos los mensajes que manda un vértice son iguales entre sí e iguales a su PageRank. Se realizará el diseño en VHDL teniendo en cuenta esta caracter��ística del citado algoritmo,evitando almacenar varias veces los mensajes que son iguales. Se ha elegido implementar PageRank en VHDL porque actualmente las arquitecturas de los sistemas operativos no escalan adecuadamente. Se busca evaluar si con otra arquitectura se obtienen mejores resultados. Se realizará un diseño partiendo de cero, utilizando la memoria ROM de IPcore de Xillinx (Software de desarrollo en VHDL), generada autom�áticamente. Se considera hacer cuatro tipos de módulos para que as�� el procesamiento se pueda hacer en paralelo. Se simplificar�á la estructura de XPregel con el fin de intentar aprovechar la particularidad de PageRank mencionada, que hace que XPregel no le saque el m�aximo partido. Despu�és se escribirá el c�ódigo, realizando una estructura escalable, ya que en la computación intervienen millones de páginas web. A continuación, se sintetizar�á y se probará el código en una FPGA. El �ultimo paso será una evaluaci�ón de la implementaci�ón, y de posibles mejoras en cuanto al consumo.

Contributions to Speech Analytics based on Speech Recognition and Topic Identification

La última década ha sido testigo de importantes avances en el campo de la tecnología de reconocimiento de voz. Los sistemas comerciales existentes actualmente poseen la capacidad de reconocer habla continua de múltiples locutores, consiguiendo valores aceptables de error, y sin la necesidad de realizar procedimientos explícitos de adaptación. A pesar del buen momento que vive esta tecnología, el reconocimiento de voz dista de ser un problema resuelto. La mayoría de estos sistemas de reconocimiento se ajustan a dominios particulares y su eficacia depende de manera significativa, entre otros muchos aspectos, de la similitud que exista entre el modelo de lenguaje utilizado y la tarea específica para la cual se está empleando. Esta dependencia cobra aún más importancia en aquellos escenarios en los cuales las propiedades estadísticas del lenguaje varían a lo largo del tiempo, como por ejemplo, en dominios de aplicación que involucren habla espontánea y múltiples temáticas. En los últimos años se ha evidenciado un constante esfuerzo por mejorar los sistemas de reconocimiento para tales dominios. Esto se ha hecho, entre otros muchos enfoques, a través de técnicas automáticas de adaptación. Estas técnicas son aplicadas a sistemas ya existentes, dado que exportar el sistema a una nueva tarea o dominio puede requerir tiempo a la vez que resultar costoso. Las técnicas de adaptación requieren fuentes adicionales de información, y en este sentido, el lenguaje hablado puede aportar algunas de ellas. El habla no sólo transmite un mensaje, también transmite información acerca del contexto en el cual se desarrolla la comunicación hablada (e.g. acerca del tema sobre el cual se está hablando). Por tanto, cuando nos comunicamos a través del habla, es posible identificar los elementos del lenguaje que caracterizan el contexto, y al mismo tiempo, rastrear los cambios que ocurren en estos elementos a lo largo del tiempo. Esta información podría ser capturada y aprovechada por medio de técnicas de recuperación de información (information retrieval) y de aprendizaje de máquina (machine learning). Esto podría permitirnos, dentro del desarrollo de mejores sistemas automáticos de reconocimiento de voz, mejorar la adaptación de modelos del lenguaje a las condiciones del contexto, y por tanto, robustecer al sistema de reconocimiento en dominios con condiciones variables (tales como variaciones potenciales en el vocabulario, el estilo y la temática). En este sentido, la principal contribución de esta Tesis es la propuesta y evaluación de un marco de contextualización motivado por el análisis temático y basado en la adaptación dinámica y no supervisada de modelos de lenguaje para el robustecimiento de un sistema automático de reconocimiento de voz. Esta adaptación toma como base distintos enfoque de los sistemas mencionados (de recuperación de información y aprendizaje de máquina) mediante los cuales buscamos identificar las temáticas sobre las cuales se está hablando en una grabación de audio. Dicha identificación, por lo tanto, permite realizar una adaptación del modelo de lenguaje de acuerdo a las condiciones del contexto. El marco de contextualización propuesto se puede dividir en dos sistemas principales: un sistema de identificación de temática y un sistema de adaptación dinámica de modelos de lenguaje. Esta Tesis puede describirse en detalle desde la perspectiva de las contribuciones particulares realizadas en cada uno de los campos que componen el marco propuesto: _ En lo referente al sistema de identificación de temática, nos hemos enfocado en aportar mejoras a las técnicas de pre-procesamiento de documentos, asimismo en contribuir a la definición de criterios más robustos para la selección de index-terms. – La eficiencia de los sistemas basados tanto en técnicas de recuperación de información como en técnicas de aprendizaje de máquina, y específicamente de aquellos sistemas que particularizan en la tarea de identificación de temática, depende, en gran medida, de los mecanismos de preprocesamiento que se aplican a los documentos. Entre las múltiples operaciones que hacen parte de un esquema de preprocesamiento, la selección adecuada de los términos de indexado (index-terms) es crucial para establecer relaciones semánticas y conceptuales entre los términos y los documentos. Este proceso también puede verse afectado, o bien por una mala elección de stopwords, o bien por la falta de precisión en la definición de reglas de lematización. En este sentido, en este trabajo comparamos y evaluamos diferentes criterios para el preprocesamiento de los documentos, así como también distintas estrategias para la selección de los index-terms. Esto nos permite no sólo reducir el tamaño de la estructura de indexación, sino también mejorar el proceso de identificación de temática. – Uno de los aspectos más importantes en cuanto al rendimiento de los sistemas de identificación de temática es la asignación de diferentes pesos a los términos de acuerdo a su contribución al contenido del documento. En este trabajo evaluamos y proponemos enfoques alternativos a los esquemas tradicionales de ponderado de términos (tales como tf-idf ) que nos permitan mejorar la especificidad de los términos, así como también discriminar mejor las temáticas de los documentos. _ Respecto a la adaptación dinámica de modelos de lenguaje, hemos dividimos el proceso de contextualización en varios pasos. – Para la generación de modelos de lenguaje basados en temática, proponemos dos tipos de enfoques: un enfoque supervisado y un enfoque no supervisado. En el primero de ellos nos basamos en las etiquetas de temática que originalmente acompañan a los documentos del corpus que empleamos. A partir de estas, agrupamos los documentos que forman parte de la misma temática y generamos modelos de lenguaje a partir de dichos grupos. Sin embargo, uno de los objetivos que se persigue en esta Tesis es evaluar si el uso de estas etiquetas para la generación de modelos es óptimo en términos del rendimiento del reconocedor. Por esta razón, nosotros proponemos un segundo enfoque, un enfoque no supervisado, en el cual el objetivo es agrupar, automáticamente, los documentos en clusters temáticos, basándonos en la similaridad semántica existente entre los documentos. Por medio de enfoques de agrupamiento conseguimos mejorar la cohesión conceptual y semántica en cada uno de los clusters, lo que a su vez nos permitió refinar los modelos de lenguaje basados en temática y mejorar el rendimiento del sistema de reconocimiento. – Desarrollamos diversas estrategias para generar un modelo de lenguaje dependiente del contexto. Nuestro objetivo es que este modelo refleje el contexto semántico del habla, i.e. las temáticas más relevantes que se están discutiendo. Este modelo es generado por medio de la interpolación lineal entre aquellos modelos de lenguaje basados en temática que estén relacionados con las temáticas más relevantes. La estimación de los pesos de interpolación está basada principalmente en el resultado del proceso de identificación de temática. – Finalmente, proponemos una metodología para la adaptación dinámica de un modelo de lenguaje general. El proceso de adaptación tiene en cuenta no sólo al modelo dependiente del contexto sino también a la información entregada por el proceso de identificación de temática. El esquema usado para la adaptación es una interpolación lineal entre el modelo general y el modelo dependiente de contexto. Estudiamos también diferentes enfoques para determinar los pesos de interpolación entre ambos modelos. Una vez definida la base teórica de nuestro marco de contextualización, proponemos su aplicación dentro de un sistema automático de reconocimiento de voz. Para esto, nos enfocamos en dos aspectos: la contextualización de los modelos de lenguaje empleados por el sistema y la incorporación de información semántica en el proceso de adaptación basado en temática. En esta Tesis proponemos un marco experimental basado en una arquitectura de reconocimiento en ‘dos etapas’. En la primera etapa, empleamos sistemas basados en técnicas de recuperación de información y aprendizaje de máquina para identificar las temáticas sobre las cuales se habla en una transcripción de un segmento de audio. Esta transcripción es generada por el sistema de reconocimiento empleando un modelo de lenguaje general. De acuerdo con la relevancia de las temáticas que han sido identificadas, se lleva a cabo la adaptación dinámica del modelo de lenguaje. En la segunda etapa de la arquitectura de reconocimiento, usamos este modelo adaptado para realizar de nuevo el reconocimiento del segmento de audio. Para determinar los beneficios del marco de trabajo propuesto, llevamos a cabo la evaluación de cada uno de los sistemas principales previamente mencionados. Esta evaluación es realizada sobre discursos en el dominio de la política usando la base de datos EPPS (European Parliamentary Plenary Sessions - Sesiones Plenarias del Parlamento Europeo) del proyecto europeo TC-STAR. Analizamos distintas métricas acerca del rendimiento de los sistemas y evaluamos las mejoras propuestas con respecto a los sistemas de referencia. ABSTRACT The last decade has witnessed major advances in speech recognition technology. Today’s commercial systems are able to recognize continuous speech from numerous speakers, with acceptable levels of error and without the need for an explicit adaptation procedure. Despite this progress, speech recognition is far from being a solved problem. Most of these systems are adjusted to a particular domain and their efficacy depends significantly, among many other aspects, on the similarity between the language model used and the task that is being addressed. This dependence is even more important in scenarios where the statistical properties of the language fluctuates throughout the time, for example, in application domains involving spontaneous and multitopic speech. Over the last years there has been an increasing effort in enhancing the speech recognition systems for such domains. This has been done, among other approaches, by means of techniques of automatic adaptation. These techniques are applied to the existing systems, specially since exporting the system to a new task or domain may be both time-consuming and expensive. Adaptation techniques require additional sources of information, and the spoken language could provide some of them. It must be considered that speech not only conveys a message, it also provides information on the context in which the spoken communication takes place (e.g. on the subject on which it is being talked about). Therefore, when we communicate through speech, it could be feasible to identify the elements of the language that characterize the context, and at the same time, to track the changes that occur in those elements over time. This information can be extracted and exploited through techniques of information retrieval and machine learning. This allows us, within the development of more robust speech recognition systems, to enhance the adaptation of language models to the conditions of the context, thus strengthening the recognition system for domains under changing conditions (such as potential variations in vocabulary, style and topic). In this sense, the main contribution of this Thesis is the proposal and evaluation of a framework of topic-motivated contextualization based on the dynamic and non-supervised adaptation of language models for the enhancement of an automatic speech recognition system. This adaptation is based on an combined approach (from the perspective of both information retrieval and machine learning fields) whereby we identify the topics that are being discussed in an audio recording. The topic identification, therefore, enables the system to perform an adaptation of the language model according to the contextual conditions. The proposed framework can be divided in two major systems: a topic identification system and a dynamic language model adaptation system. This Thesis can be outlined from the perspective of the particular contributions made in each of the fields that composes the proposed framework: _ Regarding the topic identification system, we have focused on the enhancement of the document preprocessing techniques in addition to contributing in the definition of more robust criteria for the selection of index-terms. – Within both information retrieval and machine learning based approaches, the efficiency of topic identification systems, depends, to a large extent, on the mechanisms of preprocessing applied to the documents. Among the many operations that encloses the preprocessing procedures, an adequate selection of index-terms is critical to establish conceptual and semantic relationships between terms and documents. This process might also be weakened by a poor choice of stopwords or lack of precision in defining stemming rules. In this regard we compare and evaluate different criteria for preprocessing the documents, as well as for improving the selection of the index-terms. This allows us to not only reduce the size of the indexing structure but also to strengthen the topic identification process. – One of the most crucial aspects, in relation to the performance of topic identification systems, is to assign different weights to different terms depending on their contribution to the content of the document. In this sense we evaluate and propose alternative approaches to traditional weighting schemes (such as tf-idf ) that allow us to improve the specificity of terms, and to better identify the topics that are related to documents. _ Regarding the dynamic language model adaptation, we divide the contextualization process into different steps. – We propose supervised and unsupervised approaches for the generation of topic-based language models. The first of them is intended to generate topic-based language models by grouping the documents, in the training set, according to the original topic labels of the corpus. Nevertheless, a goal of this Thesis is to evaluate whether or not the use of these labels to generate language models is optimal in terms of recognition accuracy. For this reason, we propose a second approach, an unsupervised one, in which the objective is to group the data in the training set into automatic topic clusters based on the semantic similarity between the documents. By means of clustering approaches we expect to obtain a more cohesive association of the documents that are related by similar concepts, thus improving the coverage of the topic-based language models and enhancing the performance of the recognition system. – We develop various strategies in order to create a context-dependent language model. Our aim is that this model reflects the semantic context of the current utterance, i.e. the most relevant topics that are being discussed. This model is generated by means of a linear interpolation between the topic-based language models related to the most relevant topics. The estimation of the interpolation weights is based mainly on the outcome of the topic identification process. – Finally, we propose a methodology for the dynamic adaptation of a background language model. The adaptation process takes into account the context-dependent model as well as the information provided by the topic identification process. The scheme used for the adaptation is a linear interpolation between the background model and the context-dependent one. We also study different approaches to determine the interpolation weights used in this adaptation scheme. Once we defined the basis of our topic-motivated contextualization framework, we propose its application into an automatic speech recognition system. We focus on two aspects: the contextualization of the language models used by the system, and the incorporation of semantic-related information into a topic-based adaptation process. To achieve this, we propose an experimental framework based in ‘a two stages’ recognition architecture. In the first stage of the architecture, Information Retrieval and Machine Learning techniques are used to identify the topics in a transcription of an audio segment. This transcription is generated by the recognition system using a background language model. According to the confidence on the topics that have been identified, the dynamic language model adaptation is carried out. In the second stage of the recognition architecture, an adapted language model is used to re-decode the utterance. To test the benefits of the proposed framework, we carry out the evaluation of each of the major systems aforementioned. The evaluation is conducted on speeches of political domain using the EPPS (European Parliamentary Plenary Sessions) database from the European TC-STAR project. We analyse several performance metrics that allow us to compare the improvements of the proposed systems against the baseline ones.