Automatic Understanding of ATC Speech: Study of Prospectives and Field Experiments for Several Controller Positions

Although there has been a lot of interest in recognizing and understanding air traffic control (ATC) speech, none of the published works have obtained detailed field data results. We have developed a system able to identify the language spoken and recognize and understand sentences in both Spanish and English. We also present field results for several in-tower controller positions. To the best of our knowledge, this is the first time that field ATC speech (not simulated) is captured, processed, and analyzed. The use of stochastic grammars allows variations in the standard phraseology that appear in field data. The robust understanding algorithm developed has 95% concept accuracy from ATC text input. It also allows changes in the presentation order of the concepts and the correction of errors created by the speech recognition engine improving it by 17% and 25%, respectively, absolute in the percentage of fully correctly understood sentences for English and Spanish in relation to the percentages of fully correctly recognized sentences. The analysis of errors due to the spontaneity of the speech and its comparison to read speech is also carried out. A 96% word accuracy for read speech is reduced to 86% word accuracy for field ATC data for Spanish for the "clearances" task confirming that field data is needed to estimate the performance of a system. A literature review and a critical discussion on the possibilities of speech recognition and understanding technology applied to ATC speech are also given.

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.

Review of Research on Speech Technology: Main Contributions From Spanish Research Groups

In the last two decades, there has been an important increase in research on speech technology in Spain, mainly due to a higher level of funding from European, Spanish and local institutions and also due to a growing interest in these technologies for developing new services and applications. This paper provides a review of the main areas of speech technology addressed by research groups in Spain, their main contributions in the recent years and the main focus of interest these days. This description is classified in five main areas: audio processing including speech, speaker characterization, speech and language processing, text to speech conversion and spoken language applications. This paper also introduces the Spanish Network of Speech Technologies (RTTH. Red Temática en Tecnologías del Habla) as the research network that includes almost all the researchers working in this area, presenting some figures, its objectives and its main activities developed in the last years.

MIRACLE’s Hybrid Approach to Bilingual and Monolingual Information Retrieval

The main goal of the bilingual and monolingual participation of the MIRACLE team in CLEF 2004 was to test the effect of combination approaches on information retrieval. The starting point was a set of basic components: stemming, transformation, filtering, generation of n-grams, weighting and relevance feedback. Some of these basic components were used in different combinations and order of application for document indexing and for query processing. A second order combination was also tested, mainly by averaging or selective combination of the documents retrieved by different approaches for a particular query.

Introducing non-linear analysis into sustained speech characterization to improve sleep apnea detection

We present a novel approach for detecting severe obstructive sleep apnea (OSA) cases by introducing non-linear analysis into sustained speech characterization. The proposed scheme was designed for providing additional information into our baseline system, built on top of state-of-the-art cepstral domain modeling techniques, aiming to improve accuracy rates. This new information is lightly correlated with our previous MFCC modeling of sustained speech and uncorrelated with the information in our continuous speech modeling scheme. Tests have been performed to evaluate the improvement for our detection task, based on sustained speech as well as combined with a continuous speech classifier, resulting in a 10% relative reduction in classification for the first and a 33% relative reduction for the fused scheme. Results encourage us to consider the existence of non-linear effects on OSA patients' voices, and to think about tools which could be used to improve short-time analysis.

Source Language Categorization for improving a Speech into Sign Language Translation System

This paper describes a categorization module for improving the performance of a Spanish into Spanish Sign Language (LSE) translation system. This categorization module replaces Spanish words with associated tags. When implementing this module, several alternatives for dealing with non-relevant words have been studied. Non-relevant words are Spanish words not relevant in the translation process. The categorization module has been incorporated into a phrase-based system and a Statistical Finite State Transducer (SFST). The evaluation results reveal that the BLEU has increased from 69.11% to 78.79% for the phrase-based system and from 69.84% to 75.59% for the SFST.

Mutual Information and Perplexity based Clustering of Dialogue Information for Dynamic Adaptation of Language Models

We present two approaches to cluster dialogue-based information obtained by the speech understanding module and the dialogue manager of a spoken dialogue system. The purpose is to estimate a language model related to each cluster, and use them to dynamically modify the model of the speech recognizer at each dialogue turn. In the first approach we build the cluster tree using local decisions based on a Maximum Normalized Mutual Information criterion. In the second one we take global decisions, based on the optimization of the global perplexity of the combination of the cluster-related LMs. Our experiments show a relative reduction of the word error rate of 15.17%, which helps to improve the performance of the understanding and the dialogue manager modules.

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

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

Evaluation of a transplantation algorithm for expressive speech synthesis

When designing human-machine interfaces it is important to consider not only the bare bones functionality but also the ease of use and accessibility it provides. When talking about voice-based inter- faces, it has been proven that imbuing expressiveness into the synthetic voices increases signi?cantly its perceived naturalness, which in the end is very helpful when building user friendly interfaces. This paper proposes an adaptation based expressiveness transplantation system capable of copying the emotions of a source speaker into any desired target speaker with just a few minutes of read speech and without requiring the record- ing of additional expressive data. This system was evaluated through a perceptual test for 3 speakers showing up to an average of 52% emotion recognition rates relative to the natural voice recognition rates, while at the same time keeping good scores in similarity and naturality.

Synthesis of Nature Sounds for Speech Masking

The introduction of open-plan offices in the 1960s with the intent of making the workplace more flexible, efficient, and team-oriented resulted in a higher noise floor level, which not only made concentrated work more difficult, but also caused physiological problems, such as increased stress, in addition to a loss of speech privacy. Irrelevant background human speech, in particular, has proven to be a major factor in disrupting concentration and lowering performance. Therefore, reducing the intelligibility of speech and has been a goal of increasing importance in recent years. One method employed to do so is the use of masking noises, which consists in emitting a continuous noise signal over a loudspeaker system that conceals the perturbing speech. Studies have shown that while effective, the maskers employed to date – normally filtered pink noise – are generally poorly accepted by users. The collaborative "Private Workspace" project, within the scope of which this thesis was carried out, attempts to develop a coupled, adaptive noise masking system along with a physical structure to be used for open-plan offices so as to combat these issues. There is evidence to suggest that nature sounds might be more accepted as masker, in part because they can have a visual object that acts as the source for the sound. Direct audio recordings are not recommended for various reasons, and thus the nature sounds must be synthesized. This work done consists of the synthesis of a sound texture to be used as a masker as well as its evaluation. The sound texture is composed of two parts: a wind-like noise synthesized with subtractive synthesis, and a leaf-like noise synthesized through granular synthesis. Different combinations of these two noises produced five variations of the masker, which were evaluated at different levels along with white noise and pink noise using a modified version of an Oldenburger Satztest to test for an affect on speech intelligibility and a questionnaire to asses its subjective acceptance. The goal was to find which of the synthesized noises works best as a speech masker. This thesis first uses a theoretical introduction to establish the basics of sound perception, psychoacoustic masking, and sound texture synthesis. The design of each of the noises, as well as their respective implementations in MATLAB, is explained, followed by the procedures used to evaluate the maskers. The results obtained in the evaluation are analyzed. Lastly, conclusions are drawn and future work is and modifications to the masker are proposed. RESUMEN. La introducción de las oficinas abiertas en los años 60 tenía como objeto flexibilizar el ambiente laboral, hacerlo más eficiente y que estuviera más orientado al trabajo en equipo. Como consecuencia, subió el nivel de ruido de fondo, que no sólo dificulta la concentración, sino que causa problemas fisiológicos, como el aumento del estrés, además de reducir la privacidad. Hay estudios que prueban que las conversaciones de fondo en particular tienen un efecto negativo en el nivel de concentración y disminuyen el rendimiento de los trabajadores. Por lo tanto, reducir la inteligibilidad del habla es uno de los principales objetivos en la actualidad. Un método empleado para hacerlo ha sido el uso de ruido enmascarante, que consiste en reproducir señales continuas de ruido a través de un sistema de altavoces que enmascare el habla. Aunque diversos estudios demuestran que es un método eficaz, los ruidos utilizados hasta la fecha (normalmente ruido rosa filtrado), no son muy bien aceptados por los usuarios. El proyecto colaborativo "Private Workspace", dentro del cual se engloba el trabajo realizado en este Proyecto Fin de Grado, tiene por objeto desarrollar un sistema de ruido enmascarador acoplado y adaptativo, además de una estructura física, para su uso en oficinas abiertas con el fin de combatir los problemas descritos anteriormente. Existen indicios de que los sonidos naturales son mejor aceptados, en parte porque pueden tener una estructura física que simule ser la fuente de los mismos. La utilización de grabaciones directas de estos sonidos no está recomendada por varios motivos, y por lo tanto los sonidos naturales deben ser sintetizados. El presente trabajo consiste en la síntesis de una textura de sonido (en inglés sound texture) para ser usada como ruido enmascarador, además de su evaluación. La textura está compuesta de dos partes: un sonido de viento sintetizado mediante síntesis sustractiva y un sonido de hojas sintetizado mediante síntesis granular. Diferentes combinaciones de estos dos sonidos producen cinco variaciones de ruido enmascarador. Estos cinco ruidos han sido evaluados a diferentes niveles, junto con ruido blanco y ruido rosa, mediante una versión modificada de un Oldenburger Satztest para comprobar cómo afectan a la inteligibilidad del habla, y mediante un cuestionario para una evaluación subjetiva de su aceptación. El objetivo era encontrar qué ruido de los que se han sintetizado funciona mejor como enmascarador del habla. El proyecto consiste en una introducción teórica que establece las bases de la percepción del sonido, el enmascaramiento psicoacústico, y la síntesis de texturas de sonido. Se explica a continuación el diseño de cada uno de los ruidos, así como su implementación en MATLAB. Posteriormente se detallan los procedimientos empleados para evaluarlos. Los resultados obtenidos se analizan y se extraen conclusiones. Por último, se propone un posible trabajo futuro y mejoras al ruido sintetizado.

Extended phone log-likelihood ratio features and acoustic-based I-vectors for language recognition

This paper presents new techniques with relevant improvements added to the primary system presented by our group to the Albayzin 2012 LRE competition, where the use of any additional corpora for training or optimizing the models was forbidden. In this work, we present the incorporation of an additional phonotactic subsystem based on the use of phone log-likelihood ratio features (PLLR) extracted from different phonotactic recognizers that contributes to improve the accuracy of the system in a 21.4% in terms of Cavg (we also present results for the official metric during the evaluation, Fact). We will present how using these features at the phone state level provides significant improvements, when used together with dimensionality reduction techniques, especially PCA. We have also experimented with applying alternative SDC-like configurations on these PLLR features with additional improvements. Also, we will describe some modifications to the MFCC-based acoustic i-vector system which have also contributed to additional improvements. The final fused system outperformed the baseline in 27.4% in Cavg.