As patologias que afetam a laringe estão aumentando consideravelmente nos últimos anos devido à condição da sociedade atual onde há hábitos não saudáveis como fumo, álcool e tabaco e um abuso vocal cada vez maior, talvez por conta do aumento da poluição sonora, principalmente nos grandes centros urbanos. Atualmente o exame utilizado pela endoscopia per-oral, direcionado a identificar patologias de laringe, são a videolaringoscopia e videoestroboscopia, ambos invasivos e por muitas vezes desconfortável ao paciente. Buscando melhorar o bem estar e minimizar o desconforto dos pacientes que necessitam submeter-se a estes procedimentos, este estudo tem como objetivo reconhecer padrões que possam ser aplicados à identificação de patologias de laringe de modo a auxiliar na criação de um novo método não invasivo em substituição ao método atual. Este trabalho utilizará várias configurações diferentes de redes neurais. A primeira rede neural foi gerada a partir de 524.287 resultados obtidos através das configurações k-k das 19 medidas acústicas disponíveis neste trabalho. Esta configuração atingiu uma acurácia de 99,5% (média de 96,99±2,08%) ao utilizar uma configuração com 11 e com 12 medidas acústicas dentre as 19 disponíveis. Utilizando-se 3 medidas rotacionadas (obtidas através do método de componentes principais), foi obtido uma acurácia de 93,98±0,24%. Com 6 medidas rotacionadas, o resultado obtido foi de acurácia foi de 94,07±0,29%. Para 6 medidas rotacionadas com entrada normalizada, a acurácia encontrada foi de 97,88±1,53%. A rede neural que fez 23 diferentes classificações, voz normal mais 22 patologias, mostrou que as melhores classificações, de acordo com a acurácia, são a da patologia hiperfunção com 58,23±18,98% e a voz normal com 52,15±18,31%. Já para a pior patologia a ser classificada, encontrou-se a fadiga vocal com 0,57±1,99%. Excluindo-se a voz normal, ou seja, utilizando uma rede neural composta somente por vozes patológicas, a hiperfunção continua sendo a mais facilmente identificável com uma acurácia de 57,3±19,55%, a segunda patologia mais facilmente identificável é a constrição ântero-posterior com 18,14±11,45%. Nesta configuração, a patologia mais difícil de se classificar continua sendo a fadiga vocal com 0,7±2,14%. A rede com re-amostragem obteve uma acurácia de 25,88±10,15% enquanto que a rede com re-amostragem e alteração de neurônios na camada intermediária obteve uma acurácia de 21,47±7,58% para 30 neurônios e uma acurácia de 18,44±6,57% para 40 neurônios. Por fim foi feita uma máquina de vetores suporte que encontrou um resultado de 67±6,2%. Assim, mostrou-se que as medidas acústicas precisam ser aprimoradas para a obtenção de melhores resultados de classificação dentre as patologias de laringe estudadas. Ainda assim, verificou-se que é possível discriminar locutores normais daqueles pacientes disfônicos. / Diseases that affect the larynx have been considerably increased in recent years due to the condition of nowadays society where there have been unhealthy habits like smoking, alcohol and tobacco and an increased vocal abuse, perhaps due to the increase in noise pollution, especially in large urban cities. Currently the exam performed by per-oral endoscopy (aimed to identify laryngeal pathologies) have been videolaryngoscopy and videostroboscopy, both invasive and often uncomfortable to the patient. Seeking to improve the comfort of the patients who need to undergo through these procedures, this study aims to identify acoustic patterns that can be applied to the identification of laryngeal pathologies in order to creating a new non-invasive larynx assessment method. Here two different configurations of neural networks were used. The first one was generated from 524.287 combinations of 19 acoustic measurements to classify voices into normal or from a diseased larynx, and achieved an max accuracy of 99.5% (96.99±2.08%). Using 3 and 6 rotated measurements (obtained from the principal components analysis method), the accuracy was 93.98±0.24% and 94.07±0.29%, respectively. With 6 rotated measurements from a previouly standardization of the 19 acoustic measurements, the accuracy was 97.88±1.53%. The second one, to classify 23 different voice types (including normal voices), showed better accuracy in identifying hiperfunctioned larynxes and normal voices, with 58.23±18.98% and 52.15±18.31%, respectively. The worst accuracy was obtained from vocal fatigues, with 0.57±1.99%. Excluding normal voices of the analysis, hyperfunctioned voices remained the most easily identifiable (with an accuracy of 57.3±19.55%) followed by anterior-posterior constriction (with 18.14±11.45%), and the most difficult condition to be identified remained vocal fatigue (with 0.7±2.14%). Re-sampling the neural networks input vectors, it was obtained accuracies of 25.88±10.15%, 21.47±7.58%, and 18.44±6.57% from such networks with 20, 30, and 40 hidden layer neurons, respectively. For comparison, classification using support vector machine produced an accuracy of 67±6.2%. Thus, it was shown that the acoustic measurements need to be improved to achieve better results of classification among the studied laryngeal pathologies. Even so, it was found that is possible to discriminate normal from dysphonic speakers.

L'une des difficultés d'une langue peu dotée est l'inexistence des services liés aux technologies du traitement de l'écrit et de l'oral. Dans cette thèse, nous avons affronté la problématique de l'étude acoustique de la parole isolée et de la parole continue en Fongbe dans le cadre de la reconnaissance automatique de la parole. La complexité tonale de l'oral et la récente convention de l'écriture du Fongbe nous ont conduit à étudier le Fongbe sur toute la chaîne de la reconnaissance automatique de la parole. En plus des ressources linguistiques collectées (vocabulaires, grands corpus de texte, grands corpus de parole, dictionnaires de prononciation) pour permettre la construction des algorithmes, nous avons proposé une recette complète d'algorithmes (incluant des algorithmes de classification et de reconnaissance de phonèmes isolés et de segmentation de la parole continue en syllabe), basés sur une étude acoustique des différents sons, pour le traitement automatique du Fongbe. Dans ce manuscrit, nous avons aussi présenté une méthodologie de développement de modèles accoustiques et de modèles du langage pour faciliter la reconnaissance automatique de la parole en Fongbe. Dans cette étude, il a été proposé et évalué une modélisation acoustique à base de graphèmes (vu que le Fongbe ne dispose pas encore de dictionnaire phonétique) et aussi l'impact de la prononciation tonale sur la performance d'un système RAP en Fongbe. Enfin, les ressources écrites et orales collectées pour le Fongbe ainsi que les résultats expérimentaux obtenus pour chaque aspect de la chaîne de RAP en Fongbe valident le potentiel des méthodes et algorithmes que nous avons proposés. / One of the difficulties of an unresourced language is the lack of technology services in the speech and text processing. In this thesis, we faced the problematic of an acoustical study of the isolated and continous speech in Fongbe as part of the speech recognition. Tonal complexity of the oral and the recent agreement of writing the Fongbe led us to study the Fongbe throughout the chain of an automatic speech recognition. In addition to the collected linguistic resources (vocabularies, large text and speech corpus, pronunciation dictionaries) for building the algorithms, we proposed a complete recipe of algorithms (including algorithms of classification and recognition of isolated phonemes and segmentation of continuous speech into syllable), based on an acoustic study of the different sounds, for Fongbe automatic processing. In this manuscript, we also presented a methodology for developing acoustic models and language models to facilitate speech recognition in Fongbe. In this study, it was proposed and evaluated an acoustic modeling based on grapheme (since the Fongbe don't have phonetic dictionary) and also the impact of tonal pronunciation on the performance of a Fongbe ASR system. Finally, the written and oral resources collected for Fongbe and experimental results obtained for each aspect of an ASR chain in Fongbe validate the potential of the methods and algorithms that we proposed.

South Africa has eleven official languages, ten of which are considered “resource-scarce”. For these languages, even basic linguistic resources required for the development of speech technology systems can be difficult or impossible to obtain. In this thesis, the process of developing Spoken Language Identification (S-LID) systems in resource-scarce environments is investigated. A Parallel Phoneme Recognition followed by Language Modeling (PPR-LM) architecture is utilized and three specific scenarios are investigated: (1) incomplete resources, including the lack of audio transcriptions and/or pronunciation dictionaries; (2) inconsistent resources, including the use of speech corpora that are unmatched with regard to domain or channel characteristics; and (3) poor quality resources, such as wrongly labeled or poorly transcribed data. Each situation is analysed, techniques defined to mitigate the effect of limited or poor quality resources, and the effectiveness of these techniques evaluated experimentally. Techniques evaluated include the development of orthographic tokenizers, bootstrapping of transcriptions, filtering of low quality audio, diarization and channel normalization techniques, and the human verification of miss-classified utterances. The knowledge gained from this research is used to develop the first S-LID system able to distinguish between all South African languages. The system performs well, able to differentiate among the eleven languages with an accuracy of above 67%, and among the six primary South African language families with an accuracy of higher than 80%, on segments of speech of between 2s and 10s in length. AFRIKAANS : Suid-Afrika het elf amptelike tale waarvan tien as hulpbron-skaars beskou word. Vir die tien tale kan selfs die basiese hulpbronne wat benodig word om spraak tegnologie stelsels te ontwikkel moeilik wees om te bekom. Die proses om ‘n Gesproke Taal Identifisering stelsel vir hulpbron-skaars omgewings te ontwikkel, word in hierdie tesis ondersoek. ‘n Parallelle Foneem Herkenning gevolg deur Taal Modellering argitektuur word ingespan om drie spesifieke moontlikhede word ondersoek: (1) Onvolledige Hulpbronne, byvoorbeeld vermiste transkripsies en uitspraak woordeboeke; (2) Teenstrydige Hulpbronne, byvoorbeeld die gebruik van spraak data-versamelings wat teenstrydig is in terme van kanaal kenmerke; en (3) Hulpbronne van swak kwaliteit, byvoorbeeld foutief geklasifiseerde data en klank opnames wat swak getranskribeer is. Elke situasie word geanaliseer, tegnieke om die negatiewe effekte van min of swak hulpbronne te verminder word ontwikkel, en die bruikbaarheid van hierdie tegnieke word deur middel van eksperimente bepaal. Tegnieke wat ontwikkel word sluit die ontwikkeling van ortografiese ontleders, die outomatiese ontwikkeling van nuwe transkripsies, die filtrering van swak kwaliteit klank-data, klank-verdeling en kanaal normalisering tegnieke, en menslike verifikasie van verkeerd geklassifiseerde uitsprake in. Die kennis wat deur hierdie navorsing bekom word, word gebruik om die eerste Gesproke Taal Identifisering stelsel wat tussen al die tale van Suid-Afrika kan onderskei, te ontwikkel. Hierdie stelsel vaar relatief goed, en kan die elf tale met ‘n akkuraatheid van meer as 67% identifiseer. Indien daar op die ses taal families gefokus word, verbeter die persentasie tot meer as 80% vir segmente wat tussen 2 en 10 sekondes lank. Copyright / Dissertation (MEng)--University of Pretoria, 2010. / Electrical, Electronic and Computer Engineering / unrestricted

Indiana University-Purdue University Indianapolis (IUPUI) / A Brain Computer Interface (BCI) is a hardware and software system that establishes direct communication between human brain and the environment. In a BCI system, brain messages pass through wires and external computers instead of the normal pathway of nerves and muscles. General work ow in all BCIs is to measure brain activities, process and then convert them into an output readable for a computer. The measurement of electrical activities in different parts of the brain is called electroencephalography (EEG). There are lots of sensor technologies with different number of electrodes to record brain activities along the scalp. Each of these electrodes captures a weighted sum of activities of all neurons in the area around that electrode. In order to establish a BCI system, it is needed to set a bunch of electrodes on scalp, and a tool to send the signals to a computer for training a system that can find the important information, extract them from the raw signal, and use them to recognize the user's intention. After all, a control signal should be generated based on the application. This thesis describes the step by step training and testing a BCI system that can be used for a person who has lost speaking skills through an accident or surgery, but still has healthy brain tissues. The goal is to establish an algorithm, which recognizes different vowels from EEG signals. It considers a bandpass filter to remove signals' noise and artifacts, periodogram for feature extraction, and Support Vector Machine (SVM) for classification.

本論文は第二言語話者の発話を高精度で認識するための音素セットの構成方法に関する研究結果を述べている．本論文では，第二言語話者の発話をネイティブ話者の発話とは異なる音響特徴量の頻度分布を持つ情報源とみなし，これを表現する適切な音素セットを構築する手法を提案している．具体的には，対象とする第二言語と母語との調音位置や調音様式などの類似性に加え，同音異義語の発生による単語識別性能の低下を総合した基準に基づき，最適な音素セットを決定する．提案手法を日本人学生の英語発話の音声認識に適用し，種々の条件下で認識精度の向上を検証した． / This dissertation focuses on the problem caused by confused mispronunciation to improve the recognition performance of second language speech. A novel method considering integrated acoustic and linguistic features is proposed to derive a reduced phoneme set for L2 speech recognition. The customized phoneme set is created with a phonetic decision tree (PDT)-based top-down sequential splitting method that utilizes the phonological knowledge between L1 and L2. The dissertation verifies the efficacy of the proposed method for Japanese English and shows that the feasibility of building a speech recognizer with the proposed method is able to alleviate the problem caused by confused mispronunciation by second language speakers. / 博士(工学) / Doctor of Philosophy in Engineering / 同志社大学 / Doshisha University

Advances in technologies of voice profiling shed new light on questions of listening and its entanglement with antiblackness as a structuring paradigm of modernity. To contest current conceptions of listening with regards to the question of race and antiblackness while also shining light on the potentials offered by blackness, this dissertation engages listening at three distinct sites that are entangled with this modern question of voice profiling AI. In the process, this dissertation elaborates on the ethical stakes involved in listening itself. Chapter 1 excavates the way in which the ears of enslaved Black lives were ritualized. It centers an analysis of the role of the punishment of ear cropping and how this performed both a claim over slaves’ belonging and an inhibition on their freedom. Scholarship from Hebrew law aids in uncovering the meaning of the specific form of punishment. The chapter concludes by comparing the conception of slaves’ ears to Black artistic expressions such as Harriet Jacobs’s various methods of narration in Incidents of a Slave Girl and Blind Tom Wiggins’ unique use of clusters and graphic notation in Battle of Manassas, so as to demonstrate their methods of resistance and refusal to a claimed all-encompassing regime of listening. Chapter 2 engages modern notions of sound and listening. The way in which sound is theorized and engaged in modern digital technologies is entangled with the conception of what listening is and what it entails. Hermann von Helmholtz provides an axis after which sound and listening, as well as the relation between an inner world of perceptions and an outer world of sensations, has to be engaged as a question of listening as entangled in societal questions. The chapter critically elaborates alongside questions of categorical distinction in sound, such as the use of skull shapes as referents for AI listening, instrument classification systems, and the general question of the form of sound, or sound as object. The concluding Chapter 3 discusses, alongside Sylvia Wynter’s work and Roscoe Mitchell’s piece S II Examples (date) the kinds of questions we must pose in the development of modern AI listening technologies to move past antiblackness. Immanuel Kant’s theorizing of race and his influence on Johann Friedrich Blumenbach’s classification of skulls relate tomodern voice profiling AI technology directly through the question of using cranial shapes. Wynter’s work challenges both a turn to varieties that do not allow the addressing of structural antiblackness, and a continuation of claims to proper knowledge on the basis of antiblackness. Ultimately, Wynter aids us in hearing Mitchell’s continual shapeshifting practice on the saxophone as a proposal towards a refiguring of our conception of sound, listening, and us.

[EN] This thesis work contributes to the field of the {Automatic Speech Recognition} (ASR). And particularly to the {Interactive Speech Transcription} and {Confidence Measures} (CM) for ASR. The main goals of this thesis work can be summarised as follows: 1. To design IST methods and tools to tackle the problem of improving automatically generated transcripts. 2. To assess the designed IST methods and tools on real-life tasks of transcription in large educational repositories of video lectures. 3. To improve the reliability of the IST by improving the underlying (CM). Abstracts: The {Automatic Speech Recognition} (ASR) is a crucial task in a broad range of important applications which could not accomplished by means of manual transcription. The ASR can provide cost-effective transcripts in scenarios of increasing social impact such as the {Massive Open Online Courses} (MOOC), for which the availability of accurate enough is crucial even if they are not flawless. The transcripts enable search-ability, summarisation, recommendation, translation; they make the contents accessible to non-native speakers and users with impairments, etc. The usefulness is such that students improve their academic performance when learning from subtitled video lectures even when transcript is not perfect. Unfortunately, the current ASR technology is still far from the necessary accuracy. The imperfect transcripts resulting from ASR can be manually supervised and corrected, but the effort can be even higher than manual transcription. For the purpose of alleviating this issue, a novel {Interactive Transcription of Speech} (IST) system is presented in this thesis. This IST succeeded in reducing the effort if a small quantity of errors can be allowed; and also in improving the underlying ASR models in a cost-effective way. In other to adequate the proposed framework into real-life MOOCs, another intelligent interaction methods involving limited user effort were investigated. And also, it was introduced a new method which benefit from the user interactions to improve automatically the unsupervised parts ({Constrained Search} for ASR). The conducted research was deployed into a web-based IST platform with which it was possible to produce a massive number of semi-supervised lectures from two different well-known repositories, videoLectures.net and poliMedia. Finally, the performance of the IST and ASR systems can be easily increased by improving the computation of the {Confidence Measure} (CM) of transcribed words. As so, two contributions were developed: a new particular {Logistic Regresion} (LR) model; and the speaker adaption of the CM for cases in which it is possible, such with MOOCs. / [ES] Este trabajo contribuye en el campo del {reconocimiento automático del habla} (RAH). Y en especial, en el de la {transcripción interactiva del habla} (TIH) y el de las {medidas de confianza} (MC) para RAH. Los objetivos principales son los siguientes: 1. Diseño de métodos y herramientas TIH para mejorar las transcripciones automáticas. 2. Evaluar los métodos y herramientas TIH empleando tareas de transcripción realistas extraídas de grandes repositorios de vídeos educacionales. 3. Mejorar la fiabilidad del TIH mediante la mejora de las MC. Resumen: El {reconocimiento automático del habla} (RAH) es una tarea crucial en una amplia gama de aplicaciones importantes que no podrían realizarse mediante transcripción manual. El RAH puede proporcionar transcripciones rentables en escenarios de creciente impacto social como el de los {cursos abiertos en linea masivos} (MOOC), para el que la disponibilidad de transcripciones es crucial, incluso cuando no son completamente perfectas. Las transcripciones permiten la automatización de procesos como buscar, resumir, recomendar, traducir; hacen que los contenidos sean más accesibles para hablantes no nativos y usuarios con discapacidades, etc. Incluso se ha comprobado que mejora el rendimiento de los estudiantes que aprenden de videos con subtítulos incluso cuando estos no son completamente perfectos. Desafortunadamente, la tecnología RAH actual aún está lejos de la precisión necesaria. Las transcripciones imperfectas resultantes del RAH pueden ser supervisadas y corregidas manualmente, pero el esfuerzo puede ser incluso superior al de la transcripción manual. Con el fin de aliviar este problema, esta tesis presenta un novedoso sistema de {transcripción interactiva del habla} (TIH). Este método TIH consigue reducir el esfuerzo de semi-supervisión siempre que sea aceptable una pequeña cantidad de errores; además mejora a la par los modelos RAH subyacentes. Con objeto de transportar el marco propuesto para MOOCs, también se investigaron otros métodos de interacción inteligentes que involucran esfuerzo limitado por parte del usuario. Además, se introdujo un nuevo método que aprovecha las interacciones para mejorar aún más las partes no supervisadas (ASR con {búsqueda restringida}). La investigación en TIH llevada a cabo se desplegó en una plataforma web con el que fue posible producir un número masivo de transcripciones de videos de dos conocidos repositorios, videoLectures.net y poliMedia. Por último, el rendimiento de la TIH y los sistemas de RAH se puede aumentar directamente mediante la mejora de la estimación de la {medida de confianza} (MC) de las palabras transcritas. Por este motivo se desarrollaron dos contribuciones: un nuevo modelo discriminativo {logístico} (LR); y la adaptación al locutor de la MC para los casos en que es posible, como por ejemplo en MOOCs. / [CA] Aquest treball hi contribueix al camp del {reconeixment automàtic de la parla} (RAP). I en especial, al de la {transcripció interactiva de la parla} i el de {mesures de confiança} (MC) per a RAP. Els objectius principals són els següents: 1. Dissenyar mètodes i eines per a TIP per tal de millorar les transcripcions automàtiques. 2. Avaluar els mètodes i eines TIP per a tasques de transcripció realistes extretes de grans repositoris de vídeos educacionals. 3. Millorar la fiabilitat del TIP, mitjançant la millora de les MC. Resum: El {reconeixment automàtic de la parla} (RAP) és una tasca crucial per una àmplia gamma d'aplicacions importants que no es poden dur a terme per mitjà de la transcripció manual. El RAP pot proporcionar transcripcions en escenaris de creixent impacte social com els {cursos online oberts massius} (MOOC). Les transcripcions permeten automatitzar tasques com ara cercar, resumir, recomanar, traduir; a més a més, fa accessibles els continguts als parlants no nadius i els usuaris amb discapacitat, etc. Fins i tot, pot millorar el rendiment acadèmic de estudiants que aprenen de xerrades amb subtítols, encara que aquests subtítols no siguen perfectes. Malauradament, la tecnologia RAP actual encara està lluny de la precisió necessària. Les transcripcions imperfectes resultants de RAP poden ser supervisades i corregides manualment, però aquest l'esforç pot acabar sent superior a la transcripció manual. Per tal de resoldre aquest problema, en aquest treball es presenta un sistema nou per a {transcripció interactiva de la parla} (TIP). Aquest sistema TIP va ser reeixit en la reducció de l'esforç per quan es pot permetre una certa quantitat d'errors; així com també en en la millora dels models RAP subjacents. Per tal d'adequar el marc proposat per a MOOCs, també es van investigar altres mètodes d'interacció intel·ligents amb esforç d''usuari limitat. A més a més, es va introduir un nou mètode que aprofita les interaccions per tal de millorar encara més les parts no supervisades (RAP amb {cerca restringida}). La investigació en TIP duta a terme es va desplegar en una plataforma web amb la qual va ser possible produir un nombre massiu de transcripcions semi-supervisades de xerrades de repositoris ben coneguts, videoLectures.net i poliMedia. Finalment, el rendiment de la TIP i els sistemes de RAP es pot augmentar directament mitjançant la millora de l'estimació de la {Confiança Mesura} (MC) de les paraules transcrites. Per tant, es van desenvolupar dues contribucions: un nou model discriminatiu logístic (LR); i l'adaptació al locutor de la MC per casos en que és possible, per exemple amb MOOCs. / Sánchez Cortina, I. (2016). Confidence Measures for Automatic and Interactive Speech Recognition [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/61473

[ES] En la última década, el reconocimiento automático del habla (RAH) y la traducción automática (TA) han mejorado enormemente mediante el uso de modelos de redes neuronales profundas (RNP) en constante evolución. Si a principios de los 2010 los sistemas de RAH y TA previos a las RNP llegaron a afrontar con éxito algunas aplicaciones reales como la transcripción y traducción de vídeos docentes pregrabados, ahora en los 2020 son abordables aplicaciones que suponen un reto mucho mayor, como la subtitulación de retransmisiones audiovisuales en directo. En este mismo período, se están invirtiendo cada vez mayores esfuerzos en la accesibilidad a los medios audiovisuales para todos, incluidas las personas sordas. El RAH y la TA, en su estado actual, son grandes herramientas para aumentar la disponibilidad de medidas de accesibilidad como subtítulos, transcripciones y traducciones, y también para proporcionar acceso multilingüe a todo tipo de contenidos. En esta tesis doctoral presentamos resultados de investigación sobre RAH y TA basadas en RNP en tres campos muy activos: los recursos educativos abiertos, los contenidos parlamentarios y los medios audiovisuales. En el área de los recursos educativos abiertos (REA), presentamos primeramente trabajos sobre la evaluación y postedición de RAH y TA con métodos de interacción inteligente, en el marco del proyecto de investigación europeo "transLectures: Transcripción y Traducción de Vídeos Docentes". Los resultados obtenidos confirman que la interacción inteligente puede reducir aún más el esfuerzo de postedición de transcripciones y traducciones automáticas. Seguidamente, en el contexto del posterior proyecto europeo X5gon, presentamos una investigación sobre el desarrollo de sistemas de TA neuronal basados en RNP, y sobre sacar el máximo partido de corpus de TA masivos mediante filtrado automático de datos. Este trabajo dio como resultado sistemas de TA neuronal clasificados entre los mejores en una competición internacional de TA, y mostramos cómo estos nuevos sistemas mejoraron la calidad de los subtítulos multilingües en casos reales de REA. En el ámbito también en crecimiento de las tecnologías del lenguaje para contenidos parlamentarios, describimos una investigación sobre técnicas de filtrado de datos de habla para el RAH en tiempo real en el contexto de debates del Parlamento Europeo. Esta investigación permitió la publicación de Europarl-ASR, un nuevo y amplio corpus de habla para entrenamiento y evaluación de sistemas de RAH en continuo, así como para la evaluación comparativa de técnicas de filtrado de datos de habla. Finalmente, presentamos un trabajo en un ámbito en la vanguardia tecnológica del RAH y de la TA: la subtitulación de retransmisiones audiovisuales en directo, en el marco del Convenio de colaboración I+D+i 2020-2023 entre la radiotelevisión pública valenciana À Punt y la Universitat Politècnica de València para la subtitulación asistida por ordenador de contenidos audiovisuales en tiempo real. Esta investigación ha resultado en la implantación de sistemas de RAH en tiempo real, de alta precisión y baja latencia, para una lengua no mayoritaria en el mundo (el catalán) y una de las lenguas más habladas del mundo (el castellano) en un medio audiovisual real. / [CA] En l'última dècada, el reconeixement automàtic de la parla (RAP) i la traducció automàtica (TA) han millorat enormement mitjançant l'ús de models de xarxes neuronals profundes (XNP) en constant evolució. Si a principis dels 2010 els sistemes de RAP i TA previs a les XNP van arribar a afrontar amb èxit algunes aplicacions reals com la transcripció i traducció de vídeos docents pregravats, ara en els 2020 són abordables aplicacions que suposen un repte molt major, com la subtitulació de retransmissions audiovisuals en directe. En aquest mateix període, s'estan invertint cada vegada majors esforços en l'accessibilitat als mitjans audiovisuals per a tots, incloses les persones sordes. El RAP i la TA, en el seu estat actual, són grans eines per a incrementar la disponibilitat de mesures d'accessibilitat com subtítols, transcripcions i traduccions, també com una manera de proporcionar accés multilingüe a tota classe de continguts. En aquesta tesi doctoral presentem resultats d'investigació sobre RAP i TA basades en XNP en tres camps molt actius: els recursos educatius oberts, els continguts parlamentaris i els mitjans audiovisuals. En l'àrea dels recursos educatius oberts (REO), presentem primerament treballs sobre l'avaluació i postedició de RAP i TA amb mètodes d'interacció intel·ligent, en el marc del projecte d'investigació europeu "transLectures: Transcripció i traducció de vídeos docents". Els resultats obtinguts confirmen que la interacció intel·ligent pot reduir encara més l'esforç de postedició de transcripcions i traduccions automàtiques. Seguidament, en el context del posterior projecte europeu X5gon, presentem una investigació sobre el desenvolupament de sistemes de TA neuronal basats en XNP, i sobre traure el màxim partit de corpus de TA massius mitjançant filtratge automàtic de dades. Aquest treball va donar com a resultat sistemes de TA neuronal classificats entre els millors en una competició internacional de TA, i mostrem com aquests nous sistemes milloren la qualitat dels subtítols multilingües en casos reals de REO. En l'àmbit també en creixement de les tecnologies del llenguatge per a continguts parlamentaris, descrivim una investigació sobre tècniques de filtratge de dades de parla per al RAP en temps real en el context de debats del Parlament Europeu. Aquesta investigació va permetre la publicació d'Europarl-ASR, un corpus de parla nou i ampli per a l'entrenament i l'avaluació de sistemes de RAP en continu, així com per a l'avaluació comparativa de tècniques de filtratge de dades de parla. Finalment, presentem un treball en un àmbit en l'avantguarda tecnològica del RAP i de la TA: la subtitulació de retransmissions audiovisuals en directe, en el context del Conveni de col·laboració R+D+i 2020-2023 entre la radiotelevisió pública valenciana À Punt i la Universitat Politècnica de València per a la subtitulació assistida per ordinador de continguts audiovisuals en temps real. Aquesta investigació ha donat com a resultat la implantació de sistemes de RAP en temps real, amb alta precisió i baixa latència, per a una llengua no majoritària en el món (el català) i una de les llengües més parlades del món (el castellà) en un mitjà audiovisual real. / [EN] In the last decade, automatic speech recognition (ASR) and machine translation (MT) have improved enormously through the use of constantly evolving deep neural network (DNN) models. If at the beginning of the 2010s the then pre-DNN ASR and MT systems were ready to tackle with success some real-life applications such as offline video lecture transcription and translation, now in the 2020s much more challenging applications are within grasp, such as live broadcast media subtitling. At the same time in this period, media accessibility for everyone, including deaf and hard-of-hearing people, is being given more and more importance. ASR and MT, in their current state, are powerful tools to increase the coverage of accessibility measures such as subtitles, transcriptions and translations, also as a way of providing multilingual access to all types of content. In this PhD thesis, we present research results on automatic speech recognition and machine translation based on deep neural networks in three very active domains: open educational resources, parliamentary contents and broadcast media. Regarding open educational resources (OER), we first present work on the evaluation and post-editing of ASR and MT with intelligent interaction approaches, as carried out in the framework of EU project transLectures: Transcription and Translation of Video Lectures. The results obtained confirm that the intelligent interaction approach can make post-editing automatic transcriptions and translations even more cost-effective. Then, in the context of subsequent EU project X5gon, we present research on developing DNN-based neural MT systems, and making the most of larger MT corpora through automatic data filtering. This work resulted in a first-rank classification in an international evaluation campaign on MT, and we show how these new NMT systems improved the quality of multilingual subtitles in real OER scenarios. In the also growing domain of language technologies for parliamentary contents, we describe research on speech data curation techniques for streaming ASR in the context of European Parliament debates. This research resulted in the release of Europarl-ASR, a new, large speech corpus for streaming ASR system training and evaluation, as well as for the benchmarking of speech data curation techniques. Finally, we present work in a domain on the edge of the state of the art for ASR and MT: the live subtitling of broadcast media, in the context of the 2020-2023 R&D collaboration agreement between the Valencian public broadcaster À Punt and the Universitat Politècnica de València for real-time computer assisted subtitling of media contents. This research has resulted in the deployment of high-quality, low-latency, real-time streaming ASR systems for a less-spoken language (Catalan) and a widely spoken language (Spanish) in a real broadcast use case. / The research leading to these results has received funding from the European Union’s Seventh Framework Programme (FP7/2007-2013) under grant agreement no. 287755 (transLectures), Competitiveness and Innovation Framework Programme (CIP) under grant agreement no. 621030 (EMMA), Horizon 2020 research and innovation programme under grant agreements no. 761758 (X5gon) and no. 952215 (TAILOR), and EU4Health Programme 2021–2027 as part of Europe’s Beating Cancer Plan under grant agreements no. 101056995 (INTERACT-EUROPE) and no. 101129375 (INTERACT-EUROPE 100); from the Government of Spain’s research projects iTrans2 (ref. TIN2009-14511, MICINN/ERDF EU), MORE (ref. TIN2015-68326-R,MINECO/ERDF EU), Multisub (ref. RTI2018-094879-B-I00, MCIN/AEI/10.13039/501100011033 ERDF “A way of making Europe”), and XLinDub (ref. PID2021-122443OB-I00, MCIN/AEI/10.13039/501100011033 ERDF “A way of making Europe”); from the Generalitat Valenciana’s “R&D collaboration agreement between the Corporació Valenciana de Mitjans de Comunicació (À Punt Mèdia) and the Universitat Politècnica de València (UPV) for real-time computer assisted subtitling of audiovisual contents based on artificial intelligence”, and research project Classroom Activity Recognition (PROMETEO/2019/111); and from the Universitat Politècnica de València’s PAID-01-17 R&D support programme. This work uses data from the RTVE 2018 and 2020 Databases. This set of data has been provided by RTVE Corporation to help develop Spanish-language speech technologies. / Garcés Díaz-Munío, GV. (2024). Automatic Speech Recognition and Machine Translation with Deep Neural Networks for Open Educational Resources, Parliamentary Contents and Broadcast Media [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/212454