Evaluating retraining rules for semi-supervised learning in neural network based cursive word recognition

Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, including the generation of the ground truth, is tedious and costly. One way of reducing the high cost of labeled training data acquisition is to exploit unlabeled data, which can be gathered easily. Making use of both labeled and unlabeled data is known as semi-supervised learning. One of the most general versions of semi-supervised learning is self-training, where a recognizer iteratively retrains itself on its own output on new, unlabeled data. In this paper we propose to apply semi-supervised learning, and in particular self-training, to the problem of cursive, handwritten word recognition. The special focus of the paper is on retraining rules that define what data are actually being used in the retraining phase. In a series of experiments it is shown that the performance of a neural network based recognizer can be significantly improved through the use of unlabeled data and self-training if appropriate retraining rules are applied.

Emotion recognition: The role of featural and configural face information

Several studies investigated the role of featural and configural information when processing facial identity. A lot less is known about their contribution to emotion recognition. In this study, we addressed this issue by inducing either a featural or a configural processing strategy (Experiment 1) and by investigating the attentional strategies in response to emotional expressions (Experiment 2). In Experiment 1, participants identified emotional expressions in faces that were presented in three different versions (intact, blurred, and scrambled) and in two orientations (upright and inverted). Blurred faces contain mainly configural information, and scrambled faces contain mainly featural information. Inversion is known to selectively hinder configural processing. Analyses of the discriminability measure (A′) and response times (RTs) revealed that configural processing plays a more prominent role in expression recognition than featural processing, but their relative contribution varies depending on the emotion. In Experiment 2, we qualified these differences between emotions by investigating the relative importance of specific features by means of eye movements. Participants had to match intact expressions with the emotional cues that preceded the stimulus. The analysis of eye movements confirmed that the recognition of different emotions rely on different types of information. While the mouth is important for the detection of happiness and fear, the eyes are more relevant for anger, fear, and sadness.

Systemic Determinants of the Information Systems Outsourcing Decision: A Comparative Study of German and United States Firms

The practice of information systems (IS) outsourcing is widely established among organizations. Nonetheless, evidence suggests that organizations differ considerably in the extent to which they deploy IS outsourcing. This variation has motivated research into the determinants of the IS outsourcing decision. Most of this research is based on the assumption that a decision on the outsourcing of a particular IS function is made independently of other IS functions. This modular view ignores the systemic nature of the IS function, which posits that IS effectiveness depends on how the various IS functions work together effectively. This study proposes that systemic influences are important criteria in evaluating the outsourcing option. It further proposes that the recognition of systemic influences in outsourcing decisions is culturally sensitive. Specifically, we provide evidence that systemic effects are factored into the IS outsourcing decision differently in more individualist cultures than in collectivist ones. Our results of a survey of United States and German firms indicate that perceived in-house advantages in the systemic impact of an IS function are, indeed, a significant determinant of IS outsourcing in a moderately individualist country (i.e., Germany), whereas insignificant in a strongly individualist country (i.e., the United States). The country differences are even stronger with regard to perceived in-house advantages in the systemic view of IS professionals. In fact, the direction of this impact is reversed in the United States sample. Other IS outsourcing determinants that were included as controls, such as cost efficiency, did not show significant country differences.

Sparse representation based action and gesture recognition

In this paper we present a solution to the problem of action and gesture recognition using sparse representations. The dictionary is modelled as a simple concatenation of features computed for each action or gesture class from the training data, and test data is classified by finding sparse representation of the test video features over this dictionary. Our method does not impose any explicit training procedure on the dictionary. We experiment our model with two kinds of features, by projecting (i) Gait Energy Images (GEIs) and (ii) Motion-descriptors, to a lower dimension using Random projection. Experiments have shown 100% recognition rate on standard datasets and are compared to the results obtained with widely used SVM classifier.

Managing the risks of medical technology: Do hazard surveillance systems provide an early warning of medical device problems?

The Food and Drug Administration (FDA) is responsible for risk assessment and risk management in the post-market surveillance of the U.S. medical device industry. One of the FDA regulatory mechanisms, the Medical Device Reporting System (MDR) is an adverse event reporting system intended to provide the FDA with advance warning of device problems. It includes voluntary reporting for individuals, and mandatory reporting for device manufacturers. ^ In a study of alleged breast implant safety problems, this research examines the organizational processes by which the FDA gathers data on adverse events and uses adverse event reporting systems to assess and manage risk. The research reviews the literature on problem recognition, risk perception, and organizational learning to understand the influence highly publicized events may have on adverse event reporting. Understanding the influence of an environmental factor, such as publicity, on adverse event reporting can provide insight into the question of whether the FDA's adverse event reporting system operates as an early warning system for medical device problems. ^ The research focuses on two main questions. The first question addresses the relationship between publicity and the voluntary and mandatory reporting of adverse events. The second question examines whether government agencies make use of these adverse event reports. ^ Using quantitative and qualitative methods, a longitudinal study was conducted of the number and content of adverse event reports regarding breast implants filed with the FDA's medical device reporting system during 1985–1991. To assess variation in publicity over time, the print media were analyzed to identify articles related to breast implant failures. ^ The exploratory findings suggest that an increase in media activity is related to an increase in voluntary reporting, especially following periods of intense media coverage of the FDA. However, a similar relationship was not found between media activity and manufacturers' mandatory adverse event reporting. A review of government committee and agency reports on the FDA published during 1976–1996 produced little evidence to suggest that publicity or MDR information contributed to problem recognition, agenda setting, or the formulation of policy recommendations. ^ The research findings suggest that the reporting of breast implant problems to FDA may reflect the perceptions and concerns of the reporting groups, a barometer of the volume and content of media attention. ^

Recognition of activities of daily living in healthy subjects using two ad-hoc classifiers

Activities of daily living (ADL) are important for quality of life. They are indicators of cognitive health status and their assessment is a measure of independence in everyday living. ADL are difficult to reliably assess using questionnaires due to self-reporting biases. Various sensor-based (wearable, in-home, intrusive) systems have been proposed to successfully recognize and quantify ADL without relying on self-reporting. New classifiers required to classify sensor data are on the rise. We propose two ad-hoc classifiers that are based only on non-intrusive sensor data. METHODS: A wireless sensor system with ten sensor boxes was installed in the home of ten healthy subjects to collect ambient data over a duration of 20 consecutive days. A handheld protocol device and a paper logbook were also provided to the subjects. Eight ADL were selected for recognition. We developed two ad-hoc ADL classifiers, namely the rule based forward chaining inference engine (RBI) classifier and the circadian activity rhythm (CAR) classifier. The RBI classifier finds facts in data and matches them against the rules. The CAR classifier works within a framework to automatically rate routine activities to detect regular repeating patterns of behavior. For comparison, two state-of-the-art [Naïves Bayes (NB), Random Forest (RF)] classifiers have also been used. All classifiers were validated with the collected data sets for classification and recognition of the eight specific ADL. RESULTS: Out of a total of 1,373 ADL, the RBI classifier correctly determined 1,264, while missing 109 and the CAR determined 1,305 while missing 68 ADL. The RBI and CAR classifier recognized activities with an average sensitivity of 91.27 and 94.36%, respectively, outperforming both RF and NB. CONCLUSIONS: The performance of the classifiers varied significantly and shows that the classifier plays an important role in ADL recognition. Both RBI and CAR classifier performed better than existing state-of-the-art (NB, RF) on all ADL. Of the two ad-hoc classifiers, the CAR classifier was more accurate and is likely to be better suited than the RBI for distinguishing and recognizing complex ADL.

Food Recognition for Dietary Assessment Using Deep Convolutional Neural Networks

Diet management is a key factor for the prevention and treatment of diet-related chronic diseases. Computer vision systems aim to provide automated food intake assessment using meal images. We propose a method for the recognition of already segmented food items in meal images. The method uses a 6-layer deep convolutional neural network to classify food image patches. For each food item, overlapping patches are extracted and classified and the class with the majority of votes is assigned to it. Experiments on a manually annotated dataset with 573 food items justified the choice of the involved components and proved the effectiveness of the proposed system yielding an overall accuracy of 84.9%.

Implicit memory for the content but not the speaker of sleep-played messages

We presented 28 sentences uttered by 28 unfamiliar speakers to sleeping participants to investigate whether humans can encode new verbal messages, learn voices of unfamiliar speakers, and form associations between speakers and messages during EEG-defined deep sleep. After waking, participants performed three tests which assessed the unconscious recognition of sleep-played speakers, messages, and speaker-message associations. Recognition performance in all tests was at chance level. However, response latencies revealed implicit memory for sleep-played messages but neither for speakers nor for speaker-message combinations. Only participants with excellent implicit memory for sleep-played messages also displayed implicit memory for speakers but not speaker-message associations. Hence, deep sleep allows for the semantic encoding of novel verbal messages.

Cross -packing among retroviruses and characterization of the feline immunodeficiency virus (FIV) packaging signal: Implications for the development of FIV-based gene transfer systems

Feline immunodeficiency virus (FIV)-based gene transfer systems are being seriously considered for human gene therapy as an alternative to vectors based on primate lentiviruses, a genetically complex group of retroviruses capable of infecting non-dividing cells. The greater phylogenetic distance between the feline and primate lentiviruses is thought to reduce chances of the generation of recombinant viruses. However, safety of FIV-based vector systems has not been tested experimentally. Since primate lentiviruses such as human and simian immunodeficiency viruses (HIV/SIV) can cross-package each other's genomes, we tested this trait with respect to FIV. Unexpectedly, both feline and primate lentiviruses were reciprocally able to both cross-package and propagate each other's RNA genomes. This was largely due to the recognition of viral packaging signals by the heterologous proteins. However, a simple retrovirus such as Mason-Pfizer monkey virus (MPMV) was unable to package FIV RNA. Interestingly, FIV could package MPMV RNA, but not propagate it for further steps of replication. These findings suggest that upon co-infection of the same host, cross-packaging may allow distinct retroviruses to generate chimeric variants with unknown pathogenic potential. ^ In order to understand the packaging determinants in FIV, we conducted a detailed mutational analysis of the region thought to contain FIV packaging signal. We show that the first 90–120 nt of the 5′ untranslated region (UTR) and the first 90 nt of gag were simultaneously required for efficient FIV RNA packaging. These results suggest that the primary FIV packaging signal is multipartite and discontinuous, composed of two core elements separated by 150 nt of the 5 ′UTR. ^ The above studies are being used towards the development of safer FIV-based self-inactivating (SIN) vectors. These vectors are being designed to eliminate the ability of FIV transfer vector RNAs to be mobilized by primate lentiviral proteins that may be present in the target cells. Preliminary test of the first generation of these vectors has revealed that they are incapable of being propagated by feline proteins. The inability of FIV transfer vectors to express packageable vector RNA after integration should greatly increase the safety of FIV vectors for human gene therapy. ^

Semantic technologies in idea management systems: a model for interoperability, linking and filtering

Abstract Idea Management Systems are web applications that implement the notion of open innovation though crowdsourcing. Typically, organizations use those kind of systems to connect to large communities in order to gather ideas for improvement of products or services. Originating from simple suggestion boxes, Idea Management Systems advanced beyond collecting ideas and aspire to be a knowledge management solution capable to select best ideas via collaborative as well as expert assessment methods. In practice, however, the contemporary systems still face a number of problems usually related to information overflow and recognizing questionable quality of submissions with reasonable time and effort allocation. This thesis focuses on idea assessment problem area and contributes a number of solutions that allow to filter, compare and evaluate ideas submitted into an Idea Management System. With respect to Idea Management System interoperability the thesis proposes theoretical model of Idea Life Cycle and formalizes it as the Gi2MO ontology which enables to go beyond the boundaries of a single system to compare and assess innovation in an organization wide or market wide context. Furthermore, based on the ontology, the thesis builds a number of solutions for improving idea assessment via: community opinion analysis (MARL), annotation of idea characteristics (Gi2MO Types) and study of idea relationships (Gi2MO Links). The main achievements of the thesis are: application of theoretical innovation models for practice of Idea Management to successfully recognize the differentiation between communities, opinion metrics and their recognition as a new tool for idea assessment, discovery of new relationship types between ideas and their impact on idea clustering. Finally, the thesis outcome is establishment of Gi2MO Project that serves as an incubator for Idea Management solutions and mature open-source software alternatives for the widely available commercial suites. From the academic point of view the project delivers resources to undertake experiments in the Idea Management Systems area and managed to become a forum that gathered a number of academic and industrial partners. Resumen Los Sistemas de Gestión de Ideas son aplicaciones Web que implementan el concepto de innovación abierta con técnicas de crowdsourcing. Típicamente, las organizaciones utilizan ese tipo de sistemas para conectar con comunidades grandes y así recoger ideas sobre cómo mejorar productos o servicios. Los Sistemas de Gestión de Ideas lian avanzado más allá de recoger simplemente ideas de buzones de sugerencias y ahora aspiran ser una solución de gestión de conocimiento capaz de seleccionar las mejores ideas por medio de técnicas colaborativas, así como métodos de evaluación llevados a cabo por expertos. Sin embargo, en la práctica, los sistemas contemporáneos todavía se enfrentan a una serie de problemas, que, por lo general, están relacionados con la sobrecarga de información y el reconocimiento de las ideas de dudosa calidad con la asignación de un tiempo y un esfuerzo razonables. Esta tesis se centra en el área de la evaluación de ideas y aporta una serie de soluciones que permiten filtrar, comparar y evaluar las ideas publicadas en un Sistema de Gestión de Ideas. Con respecto a la interoperabilidad de los Sistemas de Gestión de Ideas, la tesis propone un modelo teórico del Ciclo de Vida de la Idea y lo formaliza como la ontología Gi2MO que permite ir más allá de los límites de un sistema único para comparar y evaluar la innovación en un contexto amplio dentro de cualquier organización o mercado. Por otra parte, basado en la ontología, la tesis desarrolla una serie de soluciones para mejorar la evaluación de las ideas a través de: análisis de las opiniones de la comunidad (MARL), la anotación de las características de las ideas (Gi2MO Types) y el estudio de las relaciones de las ideas (Gi2MO Links). Los logros principales de la tesis son: la aplicación de los modelos teóricos de innovación para la práctica de Sistemas de Gestión de Ideas para reconocer las diferenciasentre comu¬nidades, métricas de opiniones de comunidad y su reconocimiento como una nueva herramienta para la evaluación de ideas, el descubrimiento de nuevos tipos de relaciones entre ideas y su impacto en la agrupación de estas. Por último, el resultado de tesis es el establecimiento de proyecto Gi2MO que sirve como incubadora de soluciones para Gestión de Ideas y herramientas de código abierto ya maduras como alternativas a otros sistemas comerciales. Desde el punto de vista académico, el proyecto ha provisto de recursos a ciertos experimentos en el área de Sistemas de Gestión de Ideas y logró convertirse en un foro que reunión para un número de socios tanto académicos como industriales.

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.

Towards an unsupervised speaking style voice building framework: multi-style speaker diarization

Current text-to-speech systems are developed using studio-recorded speech in a neutral style or based on acted emotions. However, the proliferation of media sharing sites would allow developing a new generation of speech-based systems which could cope with spontaneous and styled speech. This paper proposes an architecture to deal with realistic recordings and carries out some experiments on unsupervised speaker diarization. In order to maximize the speaker purity of the clusters while keeping a high speaker coverage, the paper evaluates the F-measure of a diarization module, achieving high scores (>85%) especially when the clusters are longer than 30 seconds, even for the more spontaneous and expressive styles (such as talk shows or sports).

Data Fusion based on Game Theory for Speaker Diarization

A novel algorithm based on bimatrix game theory has been developed to improve the accuracy and reliability of a speaker diarization system. This algorithm fuses the output data of two open-source speaker diarization programs, LIUM and SHoUT, taking advantage of the best properties of each one. The performance of this new system has been tested by means of audio streams from several movies. From preliminary results on fragments of five movies, improvements of 63% in false alarms and missed speech mistakes have been achieved with respect to LIUM and SHoUT systems working alone. Moreover, we also improve in a 20% the number of recognized speakers, getting close to the real number of speakers in the audio stream

On the dynamic adaptation of language models based on dialogue information

We present an approach to adapt dynamically the language models (LMs) used by a speech recognizer that is part of a spoken dialogue system. We have developed a grammar generation strategy that automatically adapts the LMs using the semantic information that the user provides (represented as dialogue concepts), together with the information regarding the intentions of the speaker (inferred by the dialogue manager, and represented as dialogue goals). We carry out the adaptation as a linear interpolation between a background LM, and one or more of the LMs associated to the dialogue elements (concepts or goals) addressed by the user. The interpolation weights between those models are automatically estimated on each dialogue turn, using measures such as the posterior probabilities of concepts and goals, estimated as part of the inference procedure to determine the actions to be carried out. We propose two approaches to handle the LMs related to concepts and goals. Whereas in the first one we estimate a LM for each one of them, in the second one we apply several clustering strategies to group together those elements that share some common properties, and estimate a LM for each cluster. Our evaluation shows how the system can estimate a dynamic model adapted to each dialogue turn, which helps to improve the performance of the speech recognition (up to a 14.82% of relative improvement), which leads to an improvement in both the language understanding and the dialogue management tasks.