Statistical Machine Learning for Automatic Assessment of Physical Activity Intensity Using Multi-axial Accelerometry and Heart Rate

This work explores the automatic recognition of physical activity intensity patterns from multi-axial accelerometry and heart rate signals. Data collection was carried out in free-living conditions and in three controlled gymnasium circuits, for a total amount of 179.80 h of data divided into: sedentary situations (65.5%), light-to-moderate activity (17.6%) and vigorous exercise (16.9%). The proposed machine learning algorithms comprise the following steps: time-domain feature definition, standardization and PCA projection, unsupervised clustering (by k-means and GMM) and a HMM to account for long-term temporal trends. Performance was evaluated by 30 runs of a 10-fold cross-validation. Both k-means and GMM-based approaches yielded high overall accuracy (86.97% and 85.03%, respectively) and, given the imbalance of the dataset, meritorious F-measures (up to 77.88%) for non-sedentary cases. Classification errors tended to be concentrated around transients, what constrains their practical impact. Hence, we consider our proposal to be suitable for 24 h-based monitoring of physical activity in ambulatory scenarios and a first step towards intensity-specific energy expenditure estimators

Contributions to the contextualization of human-machine spoken interaction systems

The design and development of spoken interaction systems has been a thoroughly studied research scope for the last decades. The aim is to obtain systems with the ability to interact with human agents with a high degree of naturalness and efficiency, allowing them to carry out the actions they desire using speech, as it is the most natural means of communication between humans. To achieve that degree of naturalness, it is not enough to endow systems with the ability to accurately understand the user’s utterances and to properly react to them, even considering the information provided by the user in his or her previous interactions. The system has also to be aware of the evolution of the conditions under which the interaction takes place, in order to act the most coherent way as possible at each moment. Consequently, one of the most important features of the system is that it has to be context-aware. This context awareness of the system can be reflected in the modification of the behaviour of the system taking into account the current situation of the interaction. For instance, the system should decide which action it has to carry out, or the way to perform it, depending on the user that requests it, on the way that the user addresses the system, on the characteristics of the environment in which the interaction takes place, and so on. In other words, the system has to adapt its behaviour to these evolving elements of the interaction. Moreover that adaptation has to be carried out, if possible, in such a way that the user: i) does not perceive that the system has to make any additional effort, or to devote interaction time to perform tasks other than carrying out the requested actions, and ii) does not have to provide the system with any additional information to carry out the adaptation, which could imply a lesser efficiency of the interaction, since users should devote several interactions only to allow the system to become adapted. In the state-of-the-art spoken dialogue systems, researchers have proposed several disparate strategies to adapt the elements of the system to different conditions of the interaction (such as the acoustic characteristics of a specific user’s speech, the actions previously requested, and so on). Nevertheless, to our knowledge there is not any consensus on the procedures to carry out these adaptation. The approaches are to an extent unrelated from one another, in the sense that each one considers different pieces of information, and the treatment of that information is different taking into account the adaptation carried out. In this regard, the main contributions of this Thesis are the following ones: Definition of a contextualization framework. We propose a unified approach that can cover any strategy to adapt the behaviour of a dialogue system to the conditions of the interaction (i.e. the context). In our theoretical definition of the contextualization framework we consider the system’s context as all the sources of variability present at any time of the interaction, either those ones related to the environment in which the interaction takes place, or to the human agent that addresses the system at each moment. Our proposal relies on three aspects that any contextualization approach should fulfill: plasticity (i.e. the system has to be able to modify its behaviour in the most proactive way taking into account the conditions under which the interaction takes place), adaptivity (i.e. the system has also to be able to consider the most appropriate sources of information at each moment, both environmental and user- and dialogue-dependent, to effectively adapt to the conditions aforementioned), and transparency (i.e. the system has to carry out the contextualizaton-related tasks in such a way that the user neither perceives them nor has to do any effort in providing the system with any information that it needs to perform that contextualization). Additionally, we could include a generality aspect to our proposed framework: the main features of the framework should be easy to adopt in any dialogue system, regardless of the solution proposed to manage the dialogue. Once we define the theoretical basis of our contextualization framework, we propose two cases of study on its application in a spoken dialogue system. We focus on two aspects of the interaction: the contextualization of the speech recognition models, and the incorporation of user-specific information into the dialogue flow. One of the modules of a dialogue system that is more prone to be contextualized is the speech recognition system. This module makes use of several models to emit a recognition hypothesis from the user’s speech signal. Generally speaking, a recognition system considers two types of models: an acoustic one (that models each of the phonemes that the recognition system has to consider) and a linguistic one (that models the sequences of words that make sense for the system). In this work we contextualize the language model of the recognition system in such a way that it takes into account the information provided by the user in both his or her current utterance and in the previous ones. These utterances convey information useful to help the system in the recognition of the next utterance. The contextualization approach that we propose consists of a dynamic adaptation of the language model that is used by the recognition system. We carry out this adaptation by means of a linear interpolation between several models. Instead of training the best interpolation weights, we make them dependent on the conditions of the dialogue. In our approach, the system itself will obtain these weights as a function of the reliability of the different elements of information available, such as the semantic concepts extracted from the user’s utterance, the actions that he or she wants to carry out, the information provided in the previous interactions, and so on. One of the aspects more frequently addressed in Human-Computer Interaction research is the inclusion of user specific characteristics into the information structures managed by the system. The idea is to take into account the features that make each user different from the others in order to offer to each particular user different services (or the same service, but in a different way). We could consider this approach as a user-dependent contextualization of the system. In our work we propose the definition of a user model that contains all the information of each user that could be potentially useful to the system at a given moment of the interaction. In particular we will analyze the actions that each user carries out throughout his or her interaction. The objective is to determine which of these actions become the preferences of that user. We represent the specific information of each user as a feature vector. Each of the characteristics that the system will take into account has a confidence score associated. With these elements, we propose a probabilistic definition of a user preference, as the action whose likelihood of being addressed by the user is greater than the one for the rest of actions. To include the user dependent information into the dialogue flow, we modify the information structures on which the dialogue manager relies to retrieve information that could be needed to solve the actions addressed by the user. Usage preferences become another source of contextual information that will be considered by the system towards a more efficient interaction (since the new information source will help to decrease the need of the system to ask users for additional information, thus reducing the number of turns needed to carry out a specific action). To test the benefits of the contextualization framework that we propose, we carry out an evaluation of the two strategies aforementioned. We gather several performance metrics, both objective and subjective, that allow us to compare the improvements of a contextualized system against the baseline one. We will also gather the user’s opinions as regards their perceptions on the behaviour of the system, and its degree of adaptation to the specific features of each interaction. Resumen El diseño y el desarrollo de sistemas de interacción hablada ha sido objeto de profundo estudio durante las pasadas décadas. El propósito es la consecución de sistemas con la capacidad de interactuar con agentes humanos con un alto grado de eficiencia y naturalidad. De esta manera, los usuarios pueden desempeñar las tareas que deseen empleando la voz, que es el medio de comunicación más natural para los humanos. A fin de alcanzar el grado de naturalidad deseado, no basta con dotar a los sistemas de la abilidad de comprender las intervenciones de los usuarios y reaccionar a ellas de manera apropiada (teniendo en consideración, incluso, la información proporcionada en previas interacciones). Adicionalmente, el sistema ha de ser consciente de las condiciones bajo las cuales transcurre la interacción, así como de la evolución de las mismas, de tal manera que pueda actuar de la manera más coherente en cada instante de la interacción. En consecuencia, una de las características primordiales del sistema es que debe ser sensible al contexto. Esta capacidad del sistema de conocer y emplear el contexto de la interacción puede verse reflejada en la modificación de su comportamiento debida a las características actuales de la interacción. Por ejemplo, el sistema debería decidir cuál es la acción más apropiada, o la mejor manera de llevarla a término, dependiendo del usuario que la solicita, del modo en el que lo hace, etcétera. En otras palabras, el sistema ha de adaptar su comportamiento a tales elementos mutables (o dinámicos) de la interacción. Dos características adicionales son requeridas a dicha adaptación: i) el usuario no ha de percibir que el sistema dedica recursos (temporales o computacionales) a realizar tareas distintas a las que aquél le solicita, y ii) el usuario no ha de dedicar esfuerzo alguno a proporcionar al sistema información adicional para llevar a cabo la interacción. Esto último implicaría una menor eficiencia de la interacción, puesto que los usuarios deberían dedicar parte de la misma a proporcionar información al sistema para su adaptación, sin ningún beneficio inmediato. En los sistemas de diálogo hablado propuestos en la literatura, se han propuesto diferentes estrategias para llevar a cabo la adaptación de los elementos del sistema a las diferentes condiciones de la interacción (tales como las características acústicas del habla de un usuario particular, o a las acciones a las que se ha referido con anterioridad). Sin embargo, no existe una estrategia fija para proceder a dicha adaptación, sino que las mismas no suelen guardar una relación entre sí. En este sentido, cada una de ellas tiene en cuenta distintas fuentes de información, la cual es tratada de manera diferente en función de las características de la adaptación buscada. Teniendo en cuenta lo anterior, las contribuciones principales de esta Tesis son las siguientes: Definición de un marco de contextualización. Proponemos un criterio unificador que pueda cubrir cualquier estrategia de adaptación del comportamiento de un sistema de diálogo a las condiciones de la interacción (esto es, el contexto de la misma). En nuestra definición teórica del marco de contextualización consideramos el contexto del sistema como todas aquellas fuentes de variabilidad presentes en cualquier instante de la interacción, ya estén relacionadas con el entorno en el que tiene lugar la interacción, ya dependan del agente humano que se dirige al sistema en cada momento. Nuestra propuesta se basa en tres aspectos que cualquier estrategia de contextualización debería cumplir: plasticidad (es decir, el sistema ha de ser capaz de modificar su comportamiento de la manera más proactiva posible, teniendo en cuenta las condiciones en las que tiene lugar la interacción), adaptabilidad (esto es, el sistema ha de ser capaz de considerar la información oportuna en cada instante, ya dependa del entorno o del usuario, de tal manera que adecúe su comportamiento de manera eficaz a las condiciones mencionadas), y transparencia (que implica que el sistema ha de desarrollar las tareas relacionadas con la contextualización de tal manera que el usuario no perciba la manera en que dichas tareas se llevan a cabo, ni tampoco deba proporcionar al sistema con información adicional alguna). De manera adicional, incluiremos en el marco propuesto el aspecto de la generalidad: las características del marco de contextualización han de ser portables a cualquier sistema de diálogo, con independencia de la solución propuesta en los mismos para gestionar el diálogo. Una vez hemos definido las características de alto nivel de nuestro marco de contextualización, proponemos dos estrategias de aplicación del mismo a un sistema de diálogo hablado. Nos centraremos en dos aspectos de la interacción a adaptar: los modelos empleados en el reconocimiento de habla, y la incorporación de información específica de cada usuario en el flujo de diálogo. Uno de los módulos de un sistema de diálogo más susceptible de ser contextualizado es el sistema de reconocimiento de habla. Este módulo hace uso de varios modelos para generar una hipótesis de reconocimiento a partir de la señal de habla. En general, un sistema de reconocimiento emplea dos tipos de modelos: uno acústico (que modela cada uno de los fonemas considerados por el reconocedor) y uno lingüístico (que modela las secuencias de palabras que tienen sentido desde el punto de vista de la interacción). En este trabajo contextualizamos el modelo lingüístico del reconocedor de habla, de tal manera que tenga en cuenta la información proporcionada por el usuario, tanto en su intervención actual como en las previas. Estas intervenciones contienen información (semántica y/o discursiva) que puede contribuir a un mejor reconocimiento de las subsiguientes intervenciones del usuario. La estrategia de contextualización propuesta consiste en una adaptación dinámica del modelo de lenguaje empleado en el reconocedor de habla. Dicha adaptación se lleva a cabo mediante una interpolación lineal entre diferentes modelos. En lugar de entrenar los mejores pesos de interpolación, proponemos hacer los mismos dependientes de las condiciones actuales de cada diálogo. El propio sistema obtendrá estos pesos como función de la disponibilidad y relevancia de las diferentes fuentes de información disponibles, tales como los conceptos semánticos extraídos a partir de la intervención del usuario, o las acciones que el mismo desea ejecutar. Uno de los aspectos más comúnmente analizados en la investigación de la Interacción Persona-Máquina es la inclusión de las características específicas de cada usuario en las estructuras de información empleadas por el sistema. El objetivo es tener en cuenta los aspectos que diferencian a cada usuario, de tal manera que el sistema pueda ofrecer a cada uno de ellos el servicio más apropiado (o un mismo servicio, pero de la manera más adecuada a cada usuario). Podemos considerar esta estrategia como una contextualización dependiente del usuario. En este trabajo proponemos la definición de un modelo de usuario que contenga toda la información relativa a cada usuario, que pueda ser potencialmente utilizada por el sistema en un momento determinado de la interacción. En particular, analizaremos aquellas acciones que cada usuario decide ejecutar a lo largo de sus diálogos con el sistema. Nuestro objetivo es determinar cuáles de dichas acciones se convierten en las preferencias de cada usuario. La información de cada usuario quedará representada mediante un vector de características, cada una de las cuales tendrá asociado un valor de confianza. Con ambos elementos proponemos una definición probabilística de una preferencia de uso, como aquella acción cuya verosimilitud es mayor que la del resto de acciones solicitadas por el usuario. A fin de incluir la información dependiente de usuario en el flujo de diálogo, llevamos a cabo una modificación de las estructuras de información en las que se apoya el gestor de diálogo para recuperar información necesaria para resolver ciertos diálogos. En dicha modificación las preferencias de cada usuario pasarán a ser una fuente adicional de información contextual, que será tenida en cuenta por el sistema en aras de una interacción más eficiente (puesto que la nueva fuente de información contribuirá a reducir la necesidad del sistema de solicitar al usuario información adicional, dando lugar en consecuencia a una reducción del número de intervenciones necesarias para llevar a cabo una acción determinada). Para determinar los beneficios de las aplicaciones del marco de contextualización propuesto, llevamos a cabo una evaluación de un sistema de diálogo que incluye las estrategias mencionadas. Hemos recogido diversas métricas, tanto objetivas como subjetivas, que nos permiten determinar las mejoras aportadas por un sistema contextualizado en comparación con el sistema sin contextualizar. De igual manera, hemos recogido las opiniones de los participantes en la evaluación acerca de su percepción del comportamiento del sistema, y de su capacidad de adaptación a las condiciones concretas de cada interacción.

A Satisfaction-based Model for Affect Recognition from Conversational Features in Spoken Dialog Systems

Detecting user affect automatically during real-time conversation is the main challenge towards our greater aim of infusing social intelligence into a natural-language mixed-initiative High-Fidelity (Hi-Fi) audio control spoken dialog agent. In recent years, studies on affect detection from voice have moved on to using realistic, non-acted data, which is subtler. However, it is more challenging to perceive subtler emotions and this is demonstrated in tasks such as labelling and machine prediction. This paper attempts to address part of this challenge by considering the role of user satisfaction ratings and also conversational/dialog features in discriminating contentment and frustration, two types of emotions that are known to be prevalent within spoken human-computer interaction. However, given the laboratory constraints, users might be positively biased when rating the system, indirectly making the reliability of the satisfaction data questionable. Machine learning experiments were conducted on two datasets, users and annotators, which were then compared in order to assess the reliability of these datasets. Our results indicated that standard classifiers were significantly more successful in discriminating the abovementioned emotions and their intensities (reflected by user satisfaction ratings) from annotator data than from user data. These results corroborated that: first, satisfaction data could be used directly as an alternative target variable to model affect, and that they could be predicted exclusively by dialog features. Second, these were only true when trying to predict the abovementioned emotions using annotator?s data, suggesting that user bias does exist in a laboratory-led evaluation.

Analysis of pattern recognition and dimensionality reduction techniques for odor biometrics

In this paper, we analyze the performance of several well-known pattern recognition and dimensionality reduction techniques when applied to mass-spectrometry data for odor biometric identification. Motivated by the successful results of previous works capturing the odor from other parts of the body, this work attempts to evaluate the feasibility of identifying people by the odor emanated from the hands. By formulating this task according to a machine learning scheme, the problem is identified with a small-sample-size supervised classification problem in which the input data is formed by mass spectrograms from the hand odor of 13 subjects captured in different sessions. The high dimensionality of the data makes it necessary to apply feature selection and extraction techniques together with a simple classifier in order to improve the generalization capabilities of the model. Our experimental results achieve recognition rates over 85% which reveals that there exists discriminatory information in the hand odor and points at body odor as a promising biometric identifier.

Depth-based face recognition using local quantized patterns adapted for range data

A depth-based face recognition algorithm specially adapted to high range resolution data acquired by the new Microsoft Kinect 2 sensor is presented. A novel descriptor called Depth Local Quantized Pattern descriptor has been designed to make use of the extended range resolution of the new sensor. This descriptor is a substantial modification of the popular Local Binary Pattern algorithm. One of the main contributions is the introduction of a quantification step, increasing its capacity to distinguish different depth patterns. The proposed descriptor has been used to train and test a Support Vector Machine classifier, which has proven to be able to accurately recognize different people faces from a wide range of poses. In addition, a new depth-based face database acquired by the new Kinect 2 sensor have been created and made public to evaluate the proposed face recognition system.

Automatic physical activity pattern recognition and meal intake modelling in type 1 diabetes for their inclusion in artificial pancreas systems

La diabetes comprende un conjunto de enfermedades metabólicas que se caracterizan por concentraciones de glucosa en sangre anormalmente altas. En el caso de la diabetes tipo 1 (T1D, por sus siglas en inglés), esta situación es debida a una ausencia total de secreción endógena de insulina, lo que impide a la mayoría de tejidos usar la glucosa. En tales circunstancias, se hace necesario el suministro exógeno de insulina para preservar la vida del paciente; no obstante, siempre con la precaución de evitar caídas agudas de la glucemia por debajo de los niveles recomendados de seguridad. Además de la administración de insulina, las ingestas y la actividad física son factores fundamentales que influyen en la homeostasis de la glucosa. En consecuencia, una gestión apropiada de la T1D debería incorporar estos dos fenómenos fisiológicos, en base a una identificación y un modelado apropiado de los mismos y de sus sorrespondientes efectos en el balance glucosa-insulina. En particular, los sistemas de páncreas artificial –ideados para llevar a cabo un control automático de los niveles de glucemia del paciente– podrían beneficiarse de la integración de esta clase de información. La primera parte de esta tesis doctoral cubre la caracterización del efecto agudo de la actividad física en los perfiles de glucosa. Con este objetivo se ha llevado a cabo una revisión sistemática de la literatura y meta-análisis que determinen las respuestas ante varias modalidades de ejercicio para pacientes con T1D, abordando esta caracterización mediante unas magnitudes que cuantifican las tasas de cambio en la glucemia a lo largo del tiempo. Por otro lado, una identificación fiable de los periodos con actividad física es un requisito imprescindible para poder proveer de esa información a los sistemas de páncreas artificial en condiciones libres y ambulatorias. Por esta razón, la segunda parte de esta tesis está enfocada a la propuesta y evaluación de un sistema automático diseñado para reconocer periodos de actividad física, clasificando su nivel de intensidad (ligera, moderada o vigorosa); así como, en el caso de periodos vigorosos, identificando también la modalidad de ejercicio (aeróbica, mixta o de fuerza). En este sentido, ambos aspectos tienen una influencia específica en el mecanismo metabólico que suministra la energía para llevar a cabo el ejercicio y, por tanto, en las respuestas glucémicas en T1D. En este trabajo se aplican varias combinaciones de técnicas de aprendizaje máquina y reconocimiento de patrones sobre la fusión multimodal de señales de acelerometría y ritmo cardíaco, las cuales describen tanto aspectos mecánicos del movimiento como la respuesta fisiológica del sistema cardiovascular ante el ejercicio. Después del reconocimiento de patrones se incorpora también un módulo de filtrado temporal para sacar partido a la considerable coherencia temporal presente en los datos, una redundancia que se origina en el hecho de que en la práctica, las tendencias en cuanto a actividad física suelen mantenerse estables a lo largo de cierto tiempo, sin fluctuaciones rápidas y repetitivas. El tercer bloque de esta tesis doctoral aborda el tema de las ingestas en el ámbito de la T1D. En concreto, se propone una serie de modelos compartimentales y se evalúan éstos en función de su capacidad para describir matemáticamente el efecto remoto de las concetraciones plasmáticas de insulina exógena sobre las tasas de eleiminación de la glucosa atribuible a la ingesta; un aspecto hasta ahora no incorporado en los principales modelos de paciente para T1D existentes en la literatura. Los datos aquí utilizados se obtuvieron gracias a un experimento realizado por el Institute of Metabolic Science (Universidad de Cambridge, Reino Unido) con 16 pacientes jóvenes. En el experimento, de tipo ‘clamp’ con objetivo variable, se replicaron los perfiles individuales de glucosa, según lo observado durante una visita preliminar tras la ingesta de una cena con o bien alta carga glucémica, o bien baja. Los seis modelos mecanísticos evaluados constaban de: a) submodelos de doble compartimento para las masas de trazadores de glucosa, b) un submodelo de único compartimento para reflejar el efecto remoto de la insulina, c) dos tipos de activación de este mismo efecto remoto (bien lineal, bien con un punto de corte), y d) diversas condiciones iniciales. ABSTRACT Diabetes encompasses a series of metabolic diseases characterized by abnormally high blood glucose concentrations. In the case of type 1 diabetes (T1D), this situation is caused by a total absence of endogenous insulin secretion, which impedes the use of glucose by most tissues. In these circumstances, exogenous insulin supplies are necessary to maintain patient’s life; although caution is always needed to avoid acute decays in glycaemia below safe levels. In addition to insulin administrations, meal intakes and physical activity are fundamental factors influencing glucose homoeostasis. Consequently, a successful management of T1D should incorporate these two physiological phenomena, based on an appropriate identification and modelling of these events and their corresponding effect on the glucose-insulin balance. In particular, artificial pancreas systems –designed to perform an automated control of patient’s glycaemia levels– may benefit from the integration of this type of information. The first part of this PhD thesis covers the characterization of the acute effect of physical activity on glucose profiles. With this aim, a systematic review of literature and metaanalyses are conduced to determine responses to various exercise modalities in patients with T1D, assessed via rates-of-change magnitudes to quantify temporal variations in glycaemia. On the other hand, a reliable identification of physical activity periods is an essential prerequisite to feed artificial pancreas systems with information concerning exercise in ambulatory, free-living conditions. For this reason, the second part of this thesis focuses on the proposal and evaluation of an automatic system devised to recognize physical activity, classifying its intensity level (light, moderate or vigorous) and for vigorous periods, identifying also its exercise modality (aerobic, mixed or resistance); since both aspects have a distinctive influence on the predominant metabolic pathway involved in fuelling exercise, and therefore, in the glycaemic responses in T1D. Various combinations of machine learning and pattern recognition techniques are applied on the fusion of multi-modal signal sources, namely: accelerometry and heart rate measurements, which describe both mechanical aspects of movement and the physiological response of the cardiovascular system to exercise. An additional temporal filtering module is incorporated after recognition in order to exploit the considerable temporal coherence (i.e. redundancy) present in data, which stems from the fact that in practice, physical activity trends are often maintained stable along time, instead of fluctuating rapid and repeatedly. The third block of this PhD thesis addresses meal intakes in the context of T1D. In particular, a number of compartmental models are proposed and compared in terms of their ability to describe mathematically the remote effect of exogenous plasma insulin concentrations on the disposal rates of meal-attributable glucose, an aspect which had not yet been incorporated to the prevailing T1D patient models in literature. Data were acquired in an experiment conduced at the Institute of Metabolic Science (University of Cambridge, UK) on 16 young patients. A variable-target glucose clamp replicated their individual glucose profiles, observed during a preliminary visit after ingesting either a high glycaemic-load or a low glycaemic-load evening meal. The six mechanistic models under evaluation here comprised: a) two-compartmental submodels for glucose tracer masses, b) a single-compartmental submodel for insulin’s remote effect, c) two types of activations for this remote effect (either linear or with a ‘cut-off’ point), and d) diverse forms of initial conditions.

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.

Human-computer interaction based on visual hand-gesture recognition using volumetric spatiograms of local binary patterns

A more natural, intuitive, user-friendly, and less intrusive Human–Computer interface for controlling an application by executing hand gestures is presented. For this purpose, a robust vision-based hand-gesture recognition system has been developed, and a new database has been created to test it. The system is divided into three stages: detection, tracking, and recognition. The detection stage searches in every frame of a video sequence potential hand poses using a binary Support Vector Machine classifier and Local Binary Patterns as feature vectors. These detections are employed as input of a tracker to generate a spatio-temporal trajectory of hand poses. Finally, the recognition stage segments a spatio-temporal volume of data using the obtained trajectories, and compute a video descriptor called Volumetric Spatiograms of Local Binary Patterns (VS-LBP), which is delivered to a bank of SVM classifiers to perform the gesture recognition. The VS-LBP is a novel video descriptor that constitutes one of the most important contributions of the paper, which is able to provide much richer spatio-temporal information than other existing approaches in the state of the art with a manageable computational cost. Excellent results have been obtained outperforming other approaches of the state of the art.

Development of a hand-gesture recognition system for human-computer interaction

The aim of this Master Thesis is the analysis, design and development of a robust and reliable Human-Computer Interaction interface, based on visual hand-gesture recognition. The implementation of the required functions is oriented to the simulation of a classical hardware interaction device: the mouse, by recognizing a specific hand-gesture vocabulary in color video sequences. For this purpose, a prototype of a hand-gesture recognition system has been designed and implemented, which is composed of three stages: detection, tracking and recognition. This system is based on machine learning methods and pattern recognition techniques, which have been integrated together with other image processing approaches to get a high recognition accuracy and a low computational cost. Regarding pattern recongition techniques, several algorithms and strategies have been designed and implemented, which are applicable to color images and video sequences. The design of these algorithms has the purpose of extracting spatial and spatio-temporal features from static and dynamic hand gestures, in order to identify them in a robust and reliable way. Finally, a visual database containing the necessary vocabulary of gestures for interacting with the computer has been created.

Reciprocal secretion of proteins by the bacterial type III machines of plant and animal pathogens suggests universal recognition of mRNA targeting signals

Bacterial pathogens of both animals and plants use type III secretion machines to inject virulence proteins into host cells. Although many components of the secretion machinery are conserved among different bacterial species, the substrates for their type III pathways are not. The Yersinia type III machinery recognizes some secretion substrates via a signal that is encoded within the first 15 codons of yop mRNA. These signals can be altered by frameshift mutations without affecting secretion of the encoded polypeptides, suggesting a mechanism whereby translation of yop mRNA is coupled to the translocation of newly synthesized polypeptide. We report that the type III machinery of Erwinia chrysanthemi cloned in Escherichia coli recognizes the secretion signals of yopE and yopQ. Pseudomonas syringae AvrB and AvrPto, two proteins exported by the recombinant Erwinia machine, can also be secreted by the Yersinia type III pathway. Mapping AvrPto sequences sufficient for the secretion of reporter fusions in Yersinia revealed the presence of an mRNA secretion signal. We propose that 11 conserved components of type III secretion machines may recognize signals that couple mRNA translation to polypeptide secretion.

Scientific bases of human-machine communication by voice.

The scientific bases for human-machine communication by voice are in the fields of psychology, linguistics, acoustics, signal processing, computer science, and integrated circuit technology. The purpose of this paper is to highlight the basic scientific and technological issues in human-machine communication by voice and to point out areas of future research opportunity. The discussion is organized around the following major issues in implementing human-machine voice communication systems: (i) hardware/software implementation of the system, (ii) speech synthesis for voice output, (iii) speech recognition and understanding for voice input, and (iv) usability factors related to how humans interact with machines.

The role of voice input for human-machine communication.

Optimism is growing that the near future will witness rapid growth in human-computer interaction using voice. System prototypes have recently been built that demonstrate speaker-independent real-time speech recognition, and understanding of naturally spoken utterances with vocabularies of 1000 to 2000 words, and larger. Already, computer manufacturers are building speech recognition subsystems into their new product lines. However, before this technology can be broadly useful, a substantial knowledge base is needed about human spoken language and performance during computer-based spoken interaction. This paper reviews application areas in which spoken interaction can play a significant role, assesses potential benefits of spoken interaction with machines, and compares voice with other modalities of human-computer interaction. It also discusses information that will be needed to build a firm empirical foundation for the design of future spoken and multimodal interfaces. Finally, it argues for a more systematic and scientific approach to investigating spoken input and performance with future language technology.

State of the art in continuous speech recognition.

In the past decade, tremendous advances in the state of the art of automatic speech recognition by machine have taken place. A reduction in the word error rate by more than a factor of 5 and an increase in recognition speeds by several orders of magnitude (brought about by a combination of faster recognition search algorithms and more powerful computers), have combined to make high-accuracy, speaker-independent, continuous speech recognition for large vocabularies possible in real time, on off-the-shelf workstations, without the aid of special hardware. These advances promise to make speech recognition technology readily available to the general public. This paper focuses on the speech recognition advances made through better speech modeling techniques, chiefly through more accurate mathematical modeling of speech sounds.

Military and government applications of human-machine communication by voice.

This paper describes a range of opportunities for military and government applications of human-machine communication by voice, based on visits and contacts with numerous user organizations in the United States. The applications include some that appear to be feasible by careful integration of current state-of-the-art technology and others that will require a varying mix of advances in speech technology and in integration of the technology into applications environments. Applications that are described include (1) speech recognition and synthesis for mobile command and control; (2) speech processing for a portable multifunction soldier's computer; (3) speech- and language-based technology for naval combat team tactical training; (4) speech technology for command and control on a carrier flight deck; (5) control of auxiliary systems, and alert and warning generation, in fighter aircraft and helicopters; and (6) voice check-in, report entry, and communication for law enforcement agents or special forces. A phased approach for transfer of the technology into applications is advocated, where integration of applications systems is pursued in parallel with advanced research to meet future needs.

Deployment of human-machine dialogue systems.

The deployment of systems for human-to-machine communication by voice requires overcoming a variety of obstacles that affect the speech-processing technologies. Problems encountered in the field might include variation in speaking style, acoustic noise, ambiguity of language, or confusion on the part of the speaker. The diversity of these practical problems encountered in the "real world" leads to the perceived gap between laboratory and "real-world" performance. To answer the question "What applications can speech technology support today?" the concept of the "degree of difficulty" of an application is introduced. The degree of difficulty depends not only on the demands placed on the speech recognition and speech synthesis technologies but also on the expectations of the user of the system. Experience has shown that deployment of effective speech communication systems requires an iterative process. This paper discusses general deployment principles, which are illustrated by several examples of human-machine communication systems.