Evaluación de la contribución y el impacto de las tecnologías del habla en la detección automática del Síndrome de la Apnea Obstructiva del Sueño = Contributions and impact assessment of speech technologies on the automatic detection of severe Obstructive Sleep Apnea syndrome

La presente Tesis analiza las posibilidades que ofrecen en la actualidad las tecnologías del habla para la detección de patologías clínicas asociadas a la vía aérea superior. El estudio del habla que tradicionalmente cubre tanto la producción como el proceso de transformación del mensaje y las señales involucradas, desde el emisor hasta alcanzar al receptor, ofrece una vía de estudio alternativa para estas patologías. El hecho de que la señal emitida no solo contiene este mensaje, sino también información acerca del locutor, ha motivado el desarrollo de sistemas orientados a la identificación y verificación de la identidad de los locutores. Estos trabajos han recibido recientemente un nuevo impulso, orientándose tanto hacia la caracterización de rasgos que son comunes a varios locutores, como a las diferencias existentes entre grabaciones de un mismo locutor. Los primeros resultan especialmente relevantes para esta Tesis dado que estos rasgos podrían evidenciar la presencia de características relacionadas con una cierta condición común a varios locutores, independiente de su identidad. Tal es el caso que se enfrenta en esta Tesis, donde los rasgos identificados se relacionarían con una de la patología particular y directamente vinculada con el sistema de físico de conformación del habla. El caso del Síndrome de Apneas Hipopneas durante el Sueno (SAHS) resulta paradigmático. Se trata de una patología con una elevada prevalencia mundo, que aumenta con la edad. Los pacientes de esta patología experimentan episodios de cese involuntario de la respiración durante el sueño, que se prolongan durante varios segundos y que se reproducen a lo largo de la noche impidiendo el correcto descanso. En el caso de la apnea obstructiva, estos episodios se deben a la imposibilidad de mantener un camino abierto a través de la vía aérea, de forma que el flujo de aire se ve interrumpido. En la actualidad, el diagnostico de estos pacientes se realiza a través de un estudio polisomnográfico, que se centra en el análisis de los episodios de apnea durante el sueño, requiriendo que el paciente permanezca en el hospital durante una noche. La complejidad y el elevado coste de estos procedimientos, unidos a las crecientes listas de espera, han evidenciado la necesidad de contar con técnicas rápidas de detección, que si bien podrían no obtener tasas tan elevadas, permitirían reorganizar las listas de espera en función del grado de severidad de la patología en cada paciente. Entre otros, los sistemas de diagnostico por imagen, así como la caracterización antropométrica de los pacientes, han evidenciado la existencia de patrones anatómicos que tendrían influencia directa sobre el habla. Los trabajos dedicados al estudio del SAHS en lo relativo a como esta afecta al habla han sido escasos y algunos de ellos incluso contradictorios. Sin embargo, desde finales de la década de 1980 se conoce la existencia de patrones específicos relativos a la articulación, la fonación y la resonancia. Sin embargo, su descripción resultaba difícilmente aprovechable a través de un sistema de reconocimiento automático, pero apuntaba la existencia de un nexo entre voz y SAHS. En los últimos anos las técnicas de procesado automático han permitido el desarrollo de sistemas automáticos que ya son capaces de identificar diferencias significativas en el habla de los pacientes del SAHS, y que los distinguen de los locutores sanos. Por contra, poco se conoce acerca de la conexión entre estos nuevos resultados, los sé que habían obtenido en el pasado y la patogénesis del SAHS. Esta Tesis continua la labor desarrollada en este ámbito considerando específicamente: el estudio de la forma en que el SAHS afecta el habla de los pacientes, la mejora en las tasas de clasificación automática y la combinación de la información obtenida con los predictores utilizados por los especialistas clínicos en sus evaluaciones preliminares. Las dos primeras tareas plantean problemas simbióticos, pero diferentes. Mientras el estudio de la conexión entre el SAHS y el habla requiere de modelos acotados que puedan ser interpretados con facilidad, los sistemas de reconocimiento se sirven de un elevado número de dimensiones para la caracterización y posterior identificación de patrones. Así, la primera tarea debe permitirnos avanzar en la segunda, al igual que la incorporación de los predictores utilizados por los especialistas clínicos. La Tesis aborda el estudio tanto del habla continua como del habla sostenida, con el fin de aprovechar las sinergias y diferencias existentes entre ambas. En el análisis del habla continua se tomo como punto de partida un esquema que ya fue evaluado con anterioridad, y sobre el cual se ha tratado la evaluación y optimización de la representación del habla, así como la caracterización de los patrones específicos asociados al SAHS. Ello ha evidenciado la conexión entre el SAHS y los elementos fundamentales de la señal de voz: los formantes. Los resultados obtenidos demuestran que el éxito de estos sistemas se debe, fundamentalmente, a la capacidad de estas representaciones para describir dichas componentes, obviando las dimensiones ruidosas o con poca capacidad discriminativa. El esquema resultante ofrece una tasa de error por debajo del 18%, sirviéndose de clasificadores notablemente menos complejos que los descritos en el estado del arte y de una única grabación de voz de corta duración. En relación a la conexión entre el SAHS y los patrones observados, fue necesario considerar las diferencias inter- e intra-grupo, centrándonos en la articulación característica del locutor, sustituyendo los complejos modelos de clasificación por el estudio de los promedios espectrales. El resultado apunta con claridad hacia ciertas regiones del eje de frecuencias, sugiriendo la existencia de un estrechamiento sistemático en la sección del tracto en la región de la orofaringe, ya prevista en la patogénesis de este síndrome. En cuanto al habla sostenida, se han reproducido los estudios realizados sobre el habla continua en grabaciones de la vocal /a/ sostenida. Los resultados son cualitativamente análogos a los anteriores, si bien en este caso las tasas de clasificación resultan ser más bajas. Con el objetivo de identificar el sentido de este resultado se reprodujo el estudio de los promedios espectrales y de la variabilidad inter e intra-grupo. Ambos estudios mostraron importantes diferencias con los anteriores que podrían explicar estos resultados. Sin embargo, el habla sostenida ofrece otras oportunidades al establecer un entorno controlado para el estudio de la fonación, que también había sido identificada como una fuente de información para la detección del SAHS. De su estudio se pudo observar que, en el conjunto de datos disponibles, no existen variaciones que pudieran asociarse fácilmente con la fonación. Únicamente aquellas dimensiones que describen la distribución de energía a lo largo del eje de frecuencia evidenciaron diferencias significativas, apuntando, una vez más, en la dirección de las resonancias espectrales. Analizados los resultados anteriores, la Tesis afronta la fusión de ambas fuentes de información en un único sistema de clasificación. Con ello es posible mejorar las tasas de clasificación, bajo la hipótesis de que la información presente en el habla continua y el habla sostenida es fundamentalmente distinta. Esta tarea se realizo a través de un sencillo esquema de fusión que obtuvo un 88.6% de aciertos en clasificación (tasa de error del 11.4%), lo que representa una mejora significativa respecto al estado del arte. Finalmente, la combinación de este clasificador con los predictores utilizados por los especialistas clínicos ofreció una tasa del 91.3% (tasa de error de 8.7%), que se encuentra dentro del margen ofrecido por esquemas más costosos e intrusivos, y que a diferencia del propuesto, no pueden ser utilizados en la evaluación previa de los pacientes. Con todo, la Tesis ofrece una visión clara sobre la relación entre el SAHS y el habla, evidenciando el grado de madurez alcanzado por la tecnología del habla en la caracterización y detección del SAHS, poniendo de manifiesto que su uso para la evaluación de los pacientes ya sería posible, y dejando la puerta abierta a futuras investigaciones que continúen el trabajo aquí iniciado. ABSTRACT This Thesis explores the potential of speech technologies for the detection of clinical disorders connected to the upper airway. The study of speech traditionally covers both the production process and post processing of the signals involved, from the speaker up to the listener, offering an alternative path to study these pathologies. The fact that utterances embed not just the encoded message but also information about the speaker, has motivated the development of automatic systems oriented to the identification and verificaton the speaker’s identity. These have recently been boosted and reoriented either towards the characterization of traits that are common to several speakers, or to the differences between records of the same speaker collected under different conditions. The first are particularly relevant to this Thesis as these patterns could reveal the presence of features that are related to a common condition shared among different speakers, regardless of their identity. Such is the case faced in this Thesis, where the traits identified would relate to a particular pathology, directly connected to the speech production system. The Obstructive Sleep Apnea syndrome (OSA) is a paradigmatic case for analysis. It is a disorder with high prevalence among adults and affecting a larger number of them as they grow older. Patients suffering from this disorder experience episodes of involuntary cessation of breath during sleep that may last a few seconds and reproduce throughout the night, preventing proper rest. In the case of obstructive apnea, these episodes are related to the collapse of the pharynx, which interrupts the air flow. Currently, OSA diagnosis is done through a polysomnographic study, which focuses on the analysis of apnea episodes during sleep, requiring the patient to stay at the hospital for the whole night. The complexity and high cost of the procedures involved, combined with the waiting lists, have evidenced the need for screening techniques, which perhaps would not achieve outstanding performance rates but would allow clinicians to reorganize these lists ranking patients according to the severity of their condition. Among others, imaging diagnosis and anthropometric characterization of patients have evidenced the existence of anatomical patterns related to OSA that have direct influence on speech. Contributions devoted to the study of how this disorder affects scpeech are scarce and somehow contradictory. However, since the late 1980s the existence of specific patterns related to articulation, phonation and resonance is known. By that time these descriptions were virtually useless when coming to the development of an automatic system, but pointed out the existence of a link between speech and OSA. In recent years automatic processing techniques have evolved and are now able to identify significant differences in the speech of OSAS patients when compared to records from healthy subjects. Nevertheless, little is known about the connection between these new results with those published in the past and the pathogenesis of the OSA syndrome. This Thesis is aimed to progress beyond the previous research done in this area by addressing: the study of how OSA affects patients’ speech, the enhancement of automatic OSA classification based on speech analysis, and its integration with the information embedded in the predictors generally used by clinicians in preliminary patients’ examination. The first two tasks, though may appear symbiotic at first, are quite different. While studying the connection between speech and OSA requires simple narrow models that can be easily interpreted, classification requires larger models including a large number dimensions for the characterization and posterior identification of the observed patterns. Anyhow, it is clear that any progress made in the first task should allow us to improve our performance on the second one, and that the incorporation of the predictors used by clinicians shall contribute in this same direction. The Thesis considers both continuous and sustained speech analysis, to exploit the synergies and differences between them. On continuous speech analysis, a conventional speech processing scheme, designed and evaluated before this Thesis, was taken as a baseline. Over this initial system several alternative representations of the speech information were proposed, optimized and tested to select those more suitable for the characterization of OSA-specific patterns. Evidences were found on the existence of a connection between OSA and the fundamental constituents of the speech: the formants. Experimental results proved that the success of the proposed solution is well explained by the ability of speech representations to describe these specific OSA-related components, ignoring the noisy ones as well those presenting low discrimination capabilities. The resulting scheme obtained a 18% error rate, on a classification scheme significantly less complex than those described in the literature and operating on a single speech record. Regarding the connection between OSA and the observed patterns, it was necessary to consider inter-and intra-group differences for this analysis, and to focus on the articulation, replacing the complex classification models by the long-term average spectra. Results clearly point to certain regions on the frequency axis, suggesting the existence of a systematic narrowing in the vocal tract section at the oropharynx. This was already described in the pathogenesis of this syndrome. Regarding sustained speech, similar experiments as those conducted on continuous speech were reproduced on sustained phonations of vowel / a /. Results were qualitatively similar to the previous ones, though in this case perfomance rates were found to be noticeably lower. Trying to derive further knowledge from this result, experiments on the long-term average spectra and intraand inter-group variability ratios were also reproduced on sustained speech records. Results on both experiments showed significant differences from the previous ones obtained from continuous speech which could explain the differences observed on peformance. However, sustained speech also provided the opportunity to study phonation within the controlled framework it provides. This was also identified in the literature as a source of information for the detection of OSA. In this study it was found that, for the available dataset, no sistematic differences related to phonation could be found between the two groups of speakers. Only those dimensions which relate energy distribution along the frequency axis provided significant differences, pointing once again towards the direction of resonant components. Once classification schemes on both continuous and sustained speech were developed, the Thesis addressed their combination into a single classification system. Under the assumption that the information in continuous and sustained speech is fundamentally different, it should be possible to successfully merge the two of them. This was tested through a simple fusion scheme which obtained a 88.6% correct classification (11.4% error rate), which represents a significant improvement over the state of the art. Finally, the combination of this classifier with the variables used by clinicians obtained a 91.3% accuracy (8.7% error rate). This is within the range of alternative, but costly and intrusive schemes, which unlike the one proposed can not be used in the preliminary assessment of patients’ condition. In the end, this Thesis has shed new light on the underlying connection between OSA and speech, and evidenced the degree of maturity reached by speech technology on OSA characterization and detection, leaving the door open for future research which shall continue in the multiple directions that have been pointed out and left as future work.

Reporting experiments to satisfy professionals information needs

Although the aim of empirical software engineering is to provide evidence for selecting the appropriate technology, it appears that there is a lack of recognition of this work in industry. Results from empirical research only rarely seem to find their way to company decision makers. If information relevant for software managers is provided in reports on experiments, such reports can be considered as a source of information for them when they are faced with making decisions about the selection of software engineering technologies. To bridge this communication gap between researchers and professionals, we propose characterizing the information needs of software managers in order to show empirical software engineering researchers which information is relevant for decision-making and thus enable them to make this information available. We empirically investigated decision makers? information needs to identify which information they need to judge the appropriateness and impact of a software technology. We empirically developed a model that characterizes these needs. To ensure that researchers provide relevant information when reporting results from experiments, we extended existing reporting guidelines accordingly.We performed an experiment to evaluate our model with regard to its effectiveness. Software managers who read an experiment report according to the proposed model judged the technology?s appropriateness significantly better than those reading a report about the same experiment that did not explicitly address their information needs. Our research shows that information regarding a technology, the context in which it is supposed to work, and most importantly, the impact of this technology on development costs and schedule as well as on product quality is crucial for decision makers.

Reporting experiments to satisfy professionals’information needs

Although the aim of empirical software engineering is to provide evidence for selecting the appropriate technology, it appears that there is a lack of recognition of this work in industry. Results from empirical research only rarely seem to find their way to company decision makers. If information relevant for software managers is provided in reports on experiments, such reports can be considered as a source of information for them when they are faced with making decisions about the selection of software engineering technologies. To bridge this communication gap between researchers and professionals, we propose characterizing the information needs of software managers in order to show empirical software engineering researchers which information is relevant for decision-making and thus enable them to make this information available. We empirically investigated decision makers? information needs to identify which information they need to judge the appropriateness and impact of a software technology. We empirically developed a model that characterizes these needs. To ensure that researchers provide relevant information when reporting results from experiments, we extended existing reporting guidelines accordingly. We performed an experiment to evaluate our model with regard to its effectiveness. Software managers who read an experiment report according to the proposed model judged the technology?s appropriateness significantly better than those reading a report about the same experiment that did not explicitly address their information needs. Our research shows that information regarding a technology, the context in which it is supposed to work, and most importantly, the impact of this technology on development costs and schedule as well as on product quality is crucial for decision makers.

Drying Increases Intracellular Partitioning of Amphiphilic Substances into the Lipid Phase1 : Impact on Membrane Permeability and Significance for Desiccation Tolerance

Previously we proposed that endogenous amphiphilic substances may partition from the aqueous cytoplasm into the lipid phase during dehydration of desiccation-tolerant organ(ism)s and vice versa during rehydration. Their perturbing presence in membranes could thus explain the transient leakage from imbibing organisms. To study the mechanism of this phenomenon, amphiphilic nitroxide spin probes were introduced into the pollen of a model organism, Typha latifolia, and their partitioning behavior during dehydration and rehydration was analyzed by electron paramagnetic resonance spectroscopy. In hydrated pollen the spin probes mainly occurred in the aqueous phase; during dehydration, however, the amphiphilic spin probes partitioned into the lipid phase and had disappeared from the aqueous phase below 0.4 g water g−1 dry weight. During rehydration the probes reappeared in the aqueous phase above 0.4 g water g−1 dry weight. The partitioning back into the cytoplasm coincided with the decrease of the initially high plasma membrane permeability. A charged polar spin probe was trapped in the cytoplasm during drying. Liposome experiments showed that partitioning of an amphiphilic spin probe into the bilayer during dehydration caused transient leakage during rehydration. This was also observed with endogenous amphipaths that were extracted from pollen, implying similar partitioning behavior. In view of the fluidizing effect on membranes and the antioxidant properties of many endogenous amphipaths, we suggest that partitioning with drying may be pivotal to desiccation tolerance, despite the risk of imbibitional leakage.

The impact of a future solar minimum on climate change projections in the Northern Hemisphere

Solar variability represents a source of uncertainty in the future forcings used in climate model simulations. Current knowledge indicates that a descent of solar activity into an extended minimum state is a possible scenario. With aid of experiments from a state-of-the-art Earth system model, we investigate the impact of a future solar minimum on Northern Hemisphere climate change projections. This scenario is constructed from recent 11 year solar-cycle minima of the solar spectral irradiance, and is therefore more conservative than the 'grand' minima employed in some previous modeling studies. Despite the small reduction in total solar irradiance (0.36 W m^-2), relatively large responses emerge in the winter Northern Hemisphere, with a reduction in regional-scale projected warming by up to 40%. To identify the origin of the enhanced regional signals, we assess the role of the different mechanisms by performing additional experiments forced only by irradiance changes at different wavelengths of the solar spectrum. We find that a reduction in visible irradiance drives changes in the stationary wave pattern of the North Pacific and sea-ice cover. A decrease in UV irradiance leads to smaller surface signals, although its regional effects are not negligible. These results point to a distinct but additive role of UV and visible irradiance in the Earth's climate, and stress the need to account for solar forcing as a source of uncertainty in regional scale projections.

Impact characteristics of glass fiber-reinforced composite materials for use in roadside safety barriers. Final report.

Federal Highway Administration, McLean Va.

The Impact of Tropical Teleconnections on Antarctic Sea Ice and Climate

Thesis (Master's)--University of Washington, 2016-06

A conformationally sensitive GHR [growth hormone (GH) receptor] antibody: Impact on GH signaling and GHR proteolysis

The GH receptor (GHR) mediates metabolic and somatogenic actions of GH. Its extracellular domain (ECD; residues 1-246) has two subdomains, each with seven beta strands organized into two antiparallel beta sheets, connected by a short hinge region. Most of the ECD residues involved in GH binding reside in subdomain 1, whereas subdomain 2 harbors a dimerization interface between GHR dimers that alters conformation in response to GH. A regulated GHR metalloprotease cleavage site is in the membrane-proximal stem region of subdomain 2. We have identified a monoclonal anti-ECD antibody, anti-GHR(ext-mAb), which recognizes the rabbit and human GHRs by immunoprecipitation, but less so after GH treatment. By immunoblotting and immunoprecipitation, anti-GHR(ext-mAb) recognized a glutathione-S-transferase (GST) fusion incorporating subdomain 2, but not one including subdomain 1. In transient transfection experiments, anti-GHR(ext-mAb) failed to recognize by immunoprecipitation a previously characterized dimerization interface mutant GHR that is incompetent for signaling. In signaling experiments, brief pretreatment of GH-responsive human fibrosarcoma cells with anti-GHR(ext-mAb) dramatically inhibited GH-induced Janus kinase 2 and signal transducer and activator of transcription 5 tyrosine phosphorylation and prevented GH-induced GHR disulfide linkage (a reflection of GH-induced conformational changes). In contrast, anti-GHR(ext-mAb) only partially inhibited radiolabeled GH binding, suggesting its effects on signaling were not simply via inhibition of binding. Furthermore, anti-GHR(ext-mAb) prevented phorbol ester-stimulated GHR proteolysis, but GHR cleavage site mutants were normally recognized by the antibody, indicating that the stem region cleavage site is not a direct epitope. A Fab fragment of anti-GHR(ext-mAb) inhibited GH-induced GHR disulfide linkage and signaling, as well as phorbol ester-induced GHR proteolysis, in a fashion similar to the intact antibody. Thus, our findings suggest that anti-GHR(ext-mAb) has promise as a GH antagonist and as a tool in studies of conformational changes required for GHR activation.

Segmented polyurethane nanocomposites: Impact of controlled particle size nanofillers on the morphological response to uniaxial deformation

A series of TPU nanocomposites were prepared by incorporating organically modified layered silicates with controlled particle size. To our knowledge, this is the first study into the effects of layered silicate diameter in polymer nanocomposites utilizing the same mineral for each size fraction. The tensile properties of these materials were found to be highly dependent upon the size of the layered silicates. A decrease in disk diameter was associated with a sharp upturn in the stress-strain curve and a pronounced increase in tensile strength. Results from SAXS/SANS experiments showed that the layered silicates did not affect the bulk TPU microphase structure and the morphological response of the host TPU to deformation or promote/hinder strain-induced soft segment crystallization. The improved tensile properties of the nanocomposites containing the smaller nanofillers resulted from the layered silicates aligning in the direction of strain and interacting with the TPU sequences via secondary bonding. This phenomenon contributes predominantly above 400% strain once the microdomain architecture has largely been disassembled. Large tactoids that are unable to align in the strain direction lead to concentrated tensile stresses between the polymer and filler, instead of desirable shear stresses, resulting in void formation and reduced tensile properties. In severe cases, such as that observed for the composite containing the largest silicate, these voids manifest visually as stress whitening.