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.

Biometric authentication of users through iris by using key binding and similarity preserving hash functions = Autenticación biométrica de usuarios a través del iris mediante la ocultación de claves y funciones resumen que preservan la similitud

El extraordinario auge de las nuevas tecnologías de la información, el desarrollo de la Internet de las Cosas, el comercio electrónico, las redes sociales, la telefonía móvil y la computación y almacenamiento en la nube, han proporcionado grandes beneficios en todos los ámbitos de la sociedad. Junto a éstos, se presentan nuevos retos para la protección y privacidad de la información y su contenido, como la suplantación de personalidad y la pérdida de la confidencialidad e integridad de los documentos o las comunicaciones electrónicas. Este hecho puede verse agravado por la falta de una frontera clara que delimite el mundo personal del mundo laboral en cuanto al acceso de la información. En todos estos campos de la actividad personal y laboral, la Criptografía ha jugado un papel fundamental aportando las herramientas necesarias para garantizar la confidencialidad, integridad y disponibilidad tanto de la privacidad de los datos personales como de la información. Por otro lado, la Biometría ha propuesto y ofrecido diferentes técnicas con el fin de garantizar la autentificación de individuos a través del uso de determinadas características personales como las huellas dáctilares, el iris, la geometría de la mano, la voz, la forma de caminar, etc. Cada una de estas dos ciencias, Criptografía y Biometría, aportan soluciones a campos específicos de la protección de datos y autentificación de usuarios, que se verían enormemente potenciados si determinadas características de ambas ciencias se unieran con vistas a objetivos comunes. Por ello es imperativo intensificar la investigación en estos ámbitos combinando los algoritmos y primitivas matemáticas de la Criptografía con la Biometría para dar respuesta a la demanda creciente de nuevas soluciones más técnicas, seguras y fáciles de usar que potencien de modo simultáneo la protección de datos y la identificacíón de usuarios. En esta combinación el concepto de biometría cancelable ha supuesto una piedra angular en el proceso de autentificación e identificación de usuarios al proporcionar propiedades de revocación y cancelación a los ragos biométricos. La contribución de esta tesis se basa en el principal aspecto de la Biometría, es decir, la autentificación segura y eficiente de usuarios a través de sus rasgos biométricos, utilizando tres aproximaciones distintas: 1. Diseño de un esquema criptobiométrico borroso que implemente los principios de la biometría cancelable para identificar usuarios lidiando con los problemas acaecidos de la variabilidad intra e inter-usuarios. 2. Diseño de una nueva función hash que preserva la similitud (SPHF por sus siglas en inglés). Actualmente estas funciones se usan en el campo del análisis forense digital con el objetivo de buscar similitudes en el contenido de archivos distintos pero similares de modo que se pueda precisar hasta qué punto estos archivos pudieran ser considerados iguales. La función definida en este trabajo de investigación, además de mejorar los resultados de las principales funciones desarrolladas hasta el momento, intenta extender su uso a la comparación entre patrones de iris. 3. Desarrollando un nuevo mecanismo de comparación de patrones de iris que considera tales patrones como si fueran señales para compararlos posteriormente utilizando la transformada de Walsh-Hadarmard. Los resultados obtenidos son excelentes teniendo en cuenta los requerimientos de seguridad y privacidad mencionados anteriormente. Cada uno de los tres esquemas diseñados han sido implementados para poder realizar experimentos y probar su eficacia operativa en escenarios que simulan situaciones reales: El esquema criptobiométrico borroso y la función SPHF han sido implementados en lenguaje Java mientras que el proceso basado en la transformada de Walsh-Hadamard en Matlab. En los experimentos se ha utilizado una base de datos de imágenes de iris (CASIA) para simular una población de usuarios del sistema. En el caso particular de la función de SPHF, además se han realizado experimentos para comprobar su utilidad en el campo de análisis forense comparando archivos e imágenes con contenido similar y distinto. En este sentido, para cada uno de los esquemas se han calculado los ratios de falso negativo y falso positivo. ABSTRACT The extraordinary increase of new information technologies, the development of Internet of Things, the electronic commerce, the social networks, mobile or smart telephony and cloud computing and storage, have provided great benefits in all areas of society. Besides this fact, there are new challenges for the protection and privacy of information and its content, such as the loss of confidentiality and integrity of electronic documents and communications. This is exarcebated by the lack of a clear boundary between the personal world and the business world as their differences are becoming narrower. In both worlds, i.e the personal and the business one, Cryptography has played a key role by providing the necessary tools to ensure the confidentiality, integrity and availability both of the privacy of the personal data and information. On the other hand, Biometrics has offered and proposed different techniques with the aim to assure the authentication of individuals through their biometric traits, such as fingerprints, iris, hand geometry, voice, gait, etc. Each of these sciences, Cryptography and Biometrics, provides tools to specific problems of the data protection and user authentication, which would be widely strengthen if determined characteristics of both sciences would be combined in order to achieve common objectives. Therefore, it is imperative to intensify the research in this area by combining the basics mathematical algorithms and primitives of Cryptography with Biometrics to meet the growing demand for more secure and usability techniques which would improve the data protection and the user authentication. In this combination, the use of cancelable biometrics makes a cornerstone in the user authentication and identification process since it provides revocable or cancelation properties to the biometric traits. The contributions in this thesis involve the main aspect of Biometrics, i.e. the secure and efficient authentication of users through their biometric templates, considered from three different approaches. The first one is designing a fuzzy crypto-biometric scheme using the cancelable biometric principles to take advantage of the fuzziness of the biometric templates at the same time that it deals with the intra- and inter-user variability among users without compromising the biometric templates extracted from the legitimate users. The second one is designing a new Similarity Preserving Hash Function (SPHF), currently widely used in the Digital Forensics field to find similarities among different files to calculate their similarity level. The function designed in this research work, besides the fact of improving the results of the two main functions of this field currently in place, it tries to expand its use to the iris template comparison. Finally, the last approach of this thesis is developing a new mechanism of handling the iris templates, considering them as signals, to use the Walsh-Hadamard transform (complemented with three other algorithms) to compare them. The results obtained are excellent taking into account the security and privacy requirements mentioned previously. Every one of the three schemes designed have been implemented to test their operational efficacy in situations that simulate real scenarios: The fuzzy crypto-biometric scheme and the SPHF have been implemented in Java language, while the process based on the Walsh-Hadamard transform in Matlab. The experiments have been performed using a database of iris templates (CASIA-IrisV2) to simulate a user population. The case of the new SPHF designed is special since previous to be applied i to the Biometrics field, it has been also tested to determine its applicability in the Digital Forensic field comparing similar and dissimilar files and images. The ratios of efficiency and effectiveness regarding user authentication, i.e. False Non Match and False Match Rate, for the schemes designed have been calculated with different parameters and cases to analyse their behaviour.

Improving Speech Interaction in Vehicles Using Context-Aware Information through A SCXML Framework

Speech Technologies can provide important benefits for the development of more usable and safe in-vehicle human-machine interactive systems (HMIs). However mainly due robustness issues, the use of spoken interaction can entail important distractions to the driver. In this challenging scenario, while speech technologies are evolving, further research is necessary to explore how they can be complemented with both other modalities (multimodality) and information from the increasing number of available sensors (context-awareness). The perceived quality of speech technologies can significantly be increased by implementing such policies, which simply try to make the best use of all the available resources; and the in vehicle scenario is an excellent test-bed for this kind of initiatives. In this contribution we propose an event-based HMI design framework which combines context modelling and multimodal interaction using a W3C XML language known as SCXML. SCXML provides a general process control mechanism that is being considered by W3C to improve both voice interaction (VoiceXML) and multimodal interaction (MMI). In our approach we try to anticipate and extend these initiatives presenting a flexible SCXML-based approach for the design of a wide range of multimodal context-aware HMI in-vehicle interfaces. The proposed framework for HMI design and specification has been implemented in an automotive OSGi service platform, and it is being used and tested in the Spanish research project MARTA for the development of several in-vehicle interactive applications.

An overview of the ciao multiparadigm language and program development environment and its design philosophy

We describe some of the novel aspects and motivations behind the design and implementation of the Ciao multiparadigm programming system. An important aspect of Ciao is that it provides the programmer with a large number of useful features from different programming paradigms and styles, and that the use of each of these features can be turned on and off at will for each program module. Thus, a given module may be using e.g. higher order functions and constraints, while another module may be using objects, predicates, and concurrency. Furthermore, the language is designed to be extensible in a simple and modular way. Another important aspect of Ciao is its programming environment, which provides a powerful preprocessor (with an associated assertion language) capable of statically finding non-trivial bugs, verifying that programs comply with specifications, and performing many types of program optimizations. Such optimizations produce code that is highly competitive with other dynamic languages or, when the highest levéis of optimization are used, even that of static languages, all while retaining the interactive development environment of a dynamic language. The environment also includes a powerful auto-documenter. The paper provides an informal overview of the language and program development environment. It aims at illustrating the design philosophy rather than at being exhaustive, which would be impossible in the format of a paper, pointing instead to the existing literature on the system.

Phonotactic language recognition using i-vectors and phoneme posteriogram counts

This paper describes a novel approach to phonotactic LID, where instead of using soft-counts based on phoneme lattices, we use posteriogram to obtain n-gram counts. The high-dimensional vectors of counts are reduced to low-dimensional units for which we adapted the commonly used term i-vectors. The reduction is based on multinomial subspace modeling and is designed to work in the total-variability space. The proposed technique was tested on the NIST 2009 LRE set with better results to a system based on using soft-counts (Cavg on 30s: 3.15% vs 3.43%), and with very good results when fused with an acoustic i-vector LID system (Cavg on 30s acoustic 2.4% vs 1.25%). The proposed technique is also compared with another low dimensional projection system based on PCA. In comparison with the original soft-counts, the proposed technique provides better results, reduces the problems due to sparse counts, and avoids the process of using pruning techniques when creating the lattices.

Electronic systems major in the context of integrated language learning lab (ILLLab) proyect = Sistemas electrónicos en el contexto del proyecto Integrated Language Learning Lab (ILLLab)

Este proyecto colabora con la plataforma Integrated Language Learning Lab (ILLLab) aportando una serie de ejercicios de gramática inglesa para una nueva sección de la web basada íntegramente en la especialidad de Sistemas Electrónicos. Complementariamente se adentra en una nueva oportunidad basada en dispositivos móviles inteligentes creando una aplicación para el repaso de los conceptos estudiados en la titulación de Ingeniería Técnica de Telecomunicación en lengua inglesa.

Low-resource language recognition using a fusion of phoneme posteriorgram counts, acoustic and glottal-based i-vectors

This paper presents a description of our system for the Albayzin 2012 LRE competition. One of the main characteristics of this evaluation was the reduced number of available files for training the system, especially for the empty condition where no training data set was provided but only a development set. In addition, the whole database was created from online videos and around one third of the training data was labeled as noisy files. Our primary system was the fusion of three different i-vector based systems: one acoustic system based on MFCCs, a phonotactic system using trigrams of phone-posteriorgram counts, and another acoustic system based on RPLPs that improved robustness against noise. A contrastive system that included new features based on the glottal source was also presented. Official and postevaluation results for all the conditions using the proposed metrics for the evaluation and the Cavg metric are presented in the paper.

Using Electronic Documents for Knowledge Acquisition and Model Maintenance

Knowledge acquisition and model maintenance are key problems in knowledge engineering to improve the productivity in the development of intelligent systems. Although historically a number of technical solutions have been proposed in this area, the recent experience shows that there is still an important gap between the way end-users describe their expertise and the way intelligent systems represent knowledge. In this paper we propose an original way to cope with this problem based on electronic documents. We propose the concept of intelligent document processor as a tool that allows the end-user to read/write a document explaining how an intelligent system operates in such a way that, if the user changes the content of the document, the intelligent system will react to these changes. The paper presents the structure of such a document based on knowledge categories derived from the modern knowledge modeling methodologies together with a number of requirements to be understandable by end-users and problem solvers.

Using Open Geographic Data to Generate Natural Language Descriptions for Hydrological Sensor Networks

Providing descriptions of isolated sensors and sensor networks in natural language, understandable by the general public, is useful to help users find relevant sensors and analyze sensor data. In this paper, we discuss the feasibility of using geographic knowledge from public databases available on the Web (such as OpenStreetMap, Geonames, or DBpedia) to automatically construct such descriptions. We present a general method that uses such information to generate sensor descriptions in natural language. The results of the evaluation of our method in a hydrologic national sensor network showed that this approach is feasible and capable of generating adequate sensor descriptions with a lower development effort compared to other approaches. In the paper we also analyze certain problems that we found in public databases (e.g., heterogeneity, non-standard use of labels, or rigid search methods) and their impact in the generation of sensor descriptions.

Enabling Language Resources to expose translations as linked data on the web

Language resources, such as multilingual lexica and multilingual electronic dictionaries, contain collections of lexical entries in several languages. Having access to the corresponding explicit or implicit translation relations between such entries might be of great interest for many NLP-based applications. By using Semantic Web-based techniques, translations can be available on the Web to be consumed by other (semantic enabled) resources in a direct manner, not relying on application-specific formats. To that end, in this paper we propose a model for representing translations as linked data, as an extension of the lemon model. Our translation module represents some core information associated to term translations and does not commit to specific views or translation theories. As a proof of concept, we have extracted the translations of the terms contained in Terminesp, a multilingual terminological database, and represented them as linked data. We have made them accessible on the Web both for humans (via a Web interface) and software agents (with a SPARQL endpoint).

Language recognition using phonotactic-based shifted delta coefficients and multiple phone recognizers

A new language recognition technique based on the application of the philosophy of the Shifted Delta Coefficients (SDC) to phone log-likelihood ratio features (PLLR) is described. The new methodology allows the incorporation of long-span phonetic information at a frame-by-frame level while dealing with the temporal length of each phone unit. The proposed features are used to train an i-vector based system and tested on the Albayzin LRE 2012 dataset. The results show a relative improvement of 33.3% in Cavg in comparison with different state-of-the-art acoustic i-vector based systems. On the other hand, the integration of parallel phone ASR systems where each one is used to generate multiple PLLR coefficients which are stacked together and then projected into a reduced dimension are also presented. Finally, the paper shows how the incorporation of state information from the phone ASR contributes to provide additional improvements and how the fusion with the other acoustic and phonotactic systems provides an important improvement of 25.8% over the system presented during the competition.