Developing European operational oceanography for Blue Growth, climate change adaptation and mitigation, and ecosystem-based management

Operational approaches have been more and more widely developed and used for providing marine data and information services for different socio-economic sectors of the Blue Growth and to advance knowledge about the marine environment. The objective of operational oceanographic research is to develop and improve the efficiency, timeliness, robustness and product quality of this approach. This white paper aims to address key scientific challenges and research priorities for the development of operational oceanography in Europe for the next 5-10 years. Knowledge gaps and deficiencies are identified in relation to common scientific challenges in four EuroGOOS knowledge areas: European Ocean Observations, Modelling and Forecasting Technology, Coastal Operational Oceanography and Operational Ecology. The areas "European Ocean Observations" and "Modelling and Forecasting Technology" focus on the further advancement of the basic instruments and capacities for European operational oceanography, while "Coastal Operational Oceanography" and "Operational Ecology" aim at developing new operational approaches for the corresponding knowledge areas.

Greening the city: an ecosystem-based framework to support planning towards urban sustainability and resilience

Cities are small-scale complex socio-ecological systems, that host around 60% of world population. Ecosystem Services (ES) provided by urban ecosystems offer multiple benefits necessary to cope with present and future urban challenges. These ES include microclimate regulation, runoff control, as well as opportunities for mental and physical recreation, affecting citizen’s health and wellbeing. Creating a balance between urban development, land take containment, climate adaptation and availability of Urban Green Areas and their related benefits, can improve the quality of the lives of the inhabitants, the economic performance of the city and the social justice and cohesion aspects. This work starts analysing current literature around the topic of Ecosystem Services (ES), Green and Blue Infrastructure (GBI) and Nature-based Solutions (NBS) and their integration within current European and International sustainability policies. Then, the thesis focuses on the role of ES, GBI and NBS towards urban sustainability and resilience setting the basis to build the core methodological and conceptual approach of this work. The developed ES-based conceptual approach provides guidance on how to map and assess ES, to better inform policy making and to give the proper value to ES within urban context. The proposed interdisciplinary approach navigates the topic of mapping and assessing ES benefits in terms of regulatory services, with a focus on climate mitigation and adaptation, and cultural services, to enhance wellbeing and justice in urban areas. Last, this thesis proposes a trans-disciplinary and participatory approach to build resilience over time around all relevant urban ES. The two case studies that will be presented in this dissertation, the city of Bologna and the city of Barcelona, have been used to implement, tailor and test the proposed conceptual framework, raising valuable inputs for planning, policies and science.

Predicted impact of the sea-level rise at VellareColeroon estuarine region of Tamil Nadu coast in India: Mainstreaming adaptation as a coastal zone management option

Low-lying coastal areas are more vulnerable to the impacts of climate change as they are highly prone for inundation to SLR (Sea-Level Rise). This study presents an appraisal of the impacts of SLR on the coastal natural resources and its dependent social communities in the low-lying area of VellareColeroon estuarine region of the Tamil Nadu coast, India. Digital Elevation Model (DEM) derived from SRTM 90M (Shuttle Radar Topographic Mission) data, along with GIS (Geographic Information System) techniques are used to identify an area of inundation in the study site. The vulnerability of coastal areas in Vellar-Coleroon estuarine region of Tamil Nadu coast to inundation was calculated based on the projected SLR scenarios of 0.5 m and 1 m. The results demonstrated that about 1570 ha of the LULC (Land use and Land cover) of the study area would be permanently inundated to 0.5 m and 2407 ha for 1 m SLR and has also resulted in the loss of three major coastal natural resources like coastal agriculture, mangroves and aquaculture. It has been identified that six hamlets of the social communities who depend on these resources are at high-risk and vulnerable to 0.5 m SLR and 12 hamlets for 1 m SLR. From the study, it has been emphasized that mainstreaming adaptation options to SLR should be embedded within a coastal zone management and planning effort, which includes all coastal natural resources (ecosystem-based adaptation), and its dependent social communities (community-based adaptation) involved through capacity building

Coastal Marine Mapping as an Ecosystem Based Management - the case study of the Baixada Santista Region - São Paulo, Brazil

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Dynamic topic-based adaptation of language models: a comparison between different approaches

This paper presents a dynamic LM adaptation based on the topic that has been identified on a speech segment. We use LSA and the given topic labels in the training dataset to obtain and use the topic models. We propose a dynamic language model adaptation to improve the recognition performance in "a two stages" AST system. The final stage makes use of the topic identification with two variants: the first on uses just the most probable topic and the other one depends on the relative distances of the topics that have been identified. We perform the adaptation of the LM as a linear interpolation between a background model and topic-based LM. The interpolation weight id dynamically adapted according to different parameters. The proposed method is evaluated on the Spanish partition of the EPPS speech database. We achieved a relative reduction in WER of 11.13% over the baseline system which uses a single blackground LM.

Understanding stakeholder preferences for flood adaptation alternatives with natural capital implications

Inland flood risks are defined by a range of environmental and social factors, including land use and floodplain management. Shifting patterns of storm intensity and precipitation, attributed to climate change, are exacerbating flood risk in regions across North America. Strategies for adapting to growing flood risks and climate change must account for a community’s specific vulnerabilities, and its local economic, environmental, and social conditions. Through a stakeholder-engaged methodology, we designed an interactive decision exercise to enable stakeholders to evaluate alternatives for addressing specific community flood vulnerabilities. We used a multicriteria framework to understand what drives stakeholder preferences for flood mitigation and adaptation alternatives, including ecosystem-based projects. Results indicated strong preferences for some ecosystem-based projects that utilize natural capital, generated a useful discussion on the role of individual values in driving decisions and a critique of local environmental and hazard planning procedure, and uncovered support for a river management alternative that had previously been considered socially infeasible. We conclude that a multicriteria decision framework may help ensure that the multiple benefit qualities of natural capital projects are considered by decision makers. Application of a utility function can demonstrate the role of individual decision-maker values in decision outcomes and help illustrate why one alternative may be a better choice than another. Although designing an efficient and accurate multicriteria exercise is quite challenging and often data intensive, we imagine that this method is applicable elsewhere. It may be especially suitable to group decisions that involve varying levels of expertise and competing values, as is often the case in planning for the ecological and human impacts of climate change.

How Have Institutional Barriers Impacted Implementation of Ecosystem Based Fishery Management in the US

Thesis (Master's)--University of Washington, 2016-08

Community-based climate change adaptation strategies for integrated prawn-fish-rice farming in Bangladesh to promote social-ecological resilience

Farming freshwater prawns with fish in rice fields is widespread in coastal regions of southwest Bangladesh because of favourable resources and ecological conditions. This article provides an overview of an ecosystem-based approach to integrated prawn-fish-rice farming in southwest Bangladesh. The practice of prawn and fish farming in rice fields is a form of integrated aquaculture-agriculture, which provides a wide range of social, economic and environmental benefits. Integrated prawn-fish-rice farming plays an important role in the economy of Bangladesh, earning foreign exchange and increasing food production. However, this unique farming system in coastal Bangladesh is particularly vulnerable to climatechange. We suggest that community-based adaptation strategies must be developed to cope with the challenges. We propose that integrated prawn-fish-rice farming could be relocated from the coastal region to less vulnerable upland areas, but caution that this will require appropriate adaptation strategies and an enabling institutional environment.

Nature-based solutions for urban heat island effect mitigation: the case study of Isla, Malta

Global population growth reflects how humans increasingly exploited Earth's resources. Urbanization develops along with anthropization. It is estimated that nearly 60% of the world's population lives in urban areas, which symbolize the denaturalized dimension of current modernity. Cities are artificial ecosystems that suffer most from environmental issues and climate change. The Urban Heat Island (UHI) effect is a common microclimatic phenomenon affecting cities, which causes considerable differences between urban and rural areas temperatures. Among the driving factors, the lack of vegetation in urban settlements can damage both humans and the environment (health diseases, heat waves caused deaths, biodiversity loss, and so on). As the world continues to urbanize, sustainable development increasingly depends on successful management of urban areas. To enhance cities’ resilience, Nature-based Solutions (NbSs), are defined as an umbrella concept that encompasses a wide range of ecosystem-based approaches and actions to climate change adaptation (CCA) and disaster risk reduction (DRR). This paper analyzes a 15-days study on air temperature trends carried out in Isla, a small locality in the Maltese archipelago, and proposes Nature-based Solutions-characterized scenarios to mitigate the Urban Heat Island effect the Mediterranean city is affected by. The results demonstrates how in some areas where vegetation is present, lower temperatures are recorded than in areas where vegetation is absent or scarce. It also appeared that in one location, the specific type of vegetation does not contribute to high temperature mitigation, whereas in another one, different environmental parameters can influence the measurements. Among the case-specific Nature-based Solutions proposed there are vertical greening (green wall, façades, ground based greening, etc.), tree lines, green canopy, and green roofs.

Value of Information Logistics Integration in Digital Business Ecosystem

Digital business ecosystems (DBE) are becoming an increasingly popular concept for modelling and building distributed systems in heterogeneous, decentralized and open environments. Information- and communication technology (ICT) enabled business solutions have created an opportunity for automated business relations and transactions. The deployment of ICT in business-to-business (B2B) integration seeks to improve competitiveness by establishing real-time information and offering better information visibility to business ecosystem actors. The products, components and raw material flows in supply chains are traditionally studied in logistics research. In this study, we expand the research to cover the processes parallel to the service and information flows as information logistics integration. In this thesis, we show how better integration and automation of information flows enhance the speed of processes and, thus, provide cost savings and other benefits for organizations. Investments in DBE are intended to add value through business automation and are key decisions in building up information logistics integration. Business solutions that build on automation are important sources of value in networks that promote and support business relations and transactions. Value is created through improved productivity and effectiveness when new, more efficient collaboration methods are discovered and integrated into DBE. Organizations, business networks and collaborations, even with competitors, form DBE in which information logistics integration has a significant role as a value driver. However, traditional economic and computing theories do not focus on digital business ecosystems as a separate form of organization, and they do not provide conceptual frameworks that can be used to explore digital business ecosystems as value drivers—combined internal management and external coordination mechanisms for information logistics integration are not the current practice of a company’s strategic process. In this thesis, we have developed and tested a framework to explore the digital business ecosystems developed and a coordination model for digital business ecosystem integration; moreover, we have analysed the value of information logistics integration. The research is based on a case study and on mixed methods, in which we use the Delphi method and Internetbased tools for idea generation and development. We conducted many interviews with key experts, which we recoded, transcribed and coded to find success factors. Qualitative analyses were based on a Monte Carlo simulation, which sought cost savings, and Real Option Valuation, which sought an optimal investment program for the ecosystem level. This study provides valuable knowledge regarding information logistics integration by utilizing a suitable business process information model for collaboration. An information model is based on the business process scenarios and on detailed transactions for the mapping and automation of product, service and information flows. The research results illustrate the current cap of understanding information logistics integration in a digital business ecosystem. Based on success factors, we were able to illustrate how specific coordination mechanisms related to network management and orchestration could be designed. We also pointed out the potential of information logistics integration in value creation. With the help of global standardization experts, we utilized the design of the core information model for B2B integration. We built this quantitative analysis by using the Monte Carlo-based simulation model and the Real Option Value model. This research covers relevant new research disciplines, such as information logistics integration and digital business ecosystems, in which the current literature needs to be improved. This research was executed by high-level experts and managers responsible for global business network B2B integration. However, the research was dominated by one industry domain, and therefore a more comprehensive exploration should be undertaken to cover a larger population of business sectors. Based on this research, the new quantitative survey could provide new possibilities to examine information logistics integration in digital business ecosystems. The value activities indicate that further studies should continue, especially with regard to the collaboration issues on integration, focusing on a user-centric approach. We should better understand how real-time information supports customer value creation by imbedding the information into the lifetime value of products and services. The aim of this research was to build competitive advantage through B2B integration to support a real-time economy. For practitioners, this research created several tools and concepts to improve value activities, information logistics integration design and management and orchestration models. Based on the results, the companies were able to better understand the formulation of the digital business ecosystem and the importance of joint efforts in collaboration. However, the challenge of incorporating this new knowledge into strategic processes in a multi-stakeholder environment remains. This challenge has been noted, and new projects have been established in pursuit of a real-time economy.

Metabolic theory predicts whole-ecosystem properties

Understanding the effects of individual organisms on material cycles and energy fluxes within ecosystems is central to predicting the impacts of human-caused changes on climate, land use, and biodiversity. Here we present a theory that integrates metabolic (organism-based bottom-up) and systems (ecosystem-based top-down) approaches to characterize how the metabolism of individuals affects the flows and stores of materials and energy in ecosystems. The theory predicts how the average residence time of carbon molecules, total system throughflow (TST), and amount of recycling vary with the body size and temperature of the organisms and with trophic organization. We evaluate the theory by comparing theoretical predictions with outputs of numerical models designed to simulate diverse ecosystem types and with empirical data for real ecosystems. Although residence times within different ecosystems vary by orders of magnitude—from weeks in warm pelagic oceans with minute phytoplankton producers to centuries in cold forests with large tree producers—as predicted, all ecosystems fall along a single line: residence time increases linearly with slope = 1.0 with the ratio of whole-ecosystem biomass to primary productivity (B/P). TST was affected predominantly by primary productivity and recycling by the transfer of energy from microbial decomposers to animal consumers. The theory provides a robust basis for estimating the flux and storage of energy, carbon, and other materials in terrestrial, marine, and freshwater ecosystems and for quantifying the roles of different kinds of organisms and environments at scales from local ecosystems to the biosphere.

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.