The Spanish variety of Malaga: From real to mental to virtual speech

Internet has affected our lives and society in manifold ways, and partly, in fundamental ways. Therefore, it is no surprise that one of the affected areas is language and communication itself. Over the last few years, online social networks have become a widespread and continuously expanding medium of communication. Being a new medium of social interaction, online social networks produce their own communication style, which in many cases differs considerably from real speech and is also perceived differently. The focus of analysis of my PhD thesis is how social network users from the city of Malaga create this virtual style by means of phonic features typical of the Andalusian variety of Spanish and how the users’ language attitude has an influence on the use of these phonic features. The data collection was fourfold: 1) a main corpus was compiled from 240 informants’ utterances on Facebook and Tuenti; 2) a corpus constituted of broad transcriptions of recordings with 120 people from Malaga served as a comparison; 3) a survey in which 240 participants rated the use of said phonetic variants on the following axes: “good–bad”, “correct–incorrect” and “beautiful–ugly” was carried out; 4) a survey with 240 participants who estimated with which frequency the analysed features are used in Malaga was conducted. For the analysis, which is quantitative and qualitative, ten variables were chosen. Results show that the studied variants are employed differently in virtual and real speech depending on how people perceive these variants. In addition, the use of the features is constrained by social factors. In general, people from Malaga have a more positive attitude towards non-­‐standard features if they are used in virtual speech than in real speech. Thus, virtual communication is seen as a style serving to create social meaning and to express linguistic identity. These stylistic practices reflect an amalgam of social presuppositions about usage conventions and individual strategies for handling a new medium. In sum, the virtual style is an initiative deliberately taken by the users, to create their, real and virtual, identities, and to define their language attitudes towards the features of their variety of speech.

Facebook style: The use of non-standard features in virtual speech conditioned by the medium Facebook

Over the last few years Facebook has become a widespread and continuously expanding medium of communication. Being a new medium of social interaction, Facebook produces its own communication style. My focus of analysis is how Facebook users from the city of Malaga create this style by means of phonic features typical of the Andalusian variety and how the users reflect on the use of these phonic features. This project is based on a theoretical framework which combines variationist sociolinguistics with CMC to study the emergence of a style peculiar of the online social networks. In a corpus of Facebook users from three zones of Malaga, I have analysed the use of non-standard phonic features and then compared them with the same features in a reference corpus collected on three beaches of Malaga. From this comparison it can be deduced that the analysed social and linguistic factors work differently in real and virtual speech. Due to these different uses we can consider the peculiar electronic communication of Facebook as a style constrained by the electronic medium. It is a style which serves the users to create social meaning and to express their linguistic identities.

Perception of co-speech gestures in aphasic patients: A visual exploration study during the observation of dyadic conversations.

BACKGROUND Co-speech gestures are part of nonverbal communication during conversations. They either support the verbal message or provide the interlocutor with additional information. Furthermore, they prompt as nonverbal cues the cooperative process of turn taking. In the present study, we investigated the influence of co-speech gestures on the perception of dyadic dialogue in aphasic patients. In particular, we analysed the impact of co-speech gestures on gaze direction (towards speaker or listener) and fixation of body parts. We hypothesized that aphasic patients, who are restricted in verbal comprehension, adapt their visual exploration strategies. METHODS Sixteen aphasic patients and 23 healthy control subjects participated in the study. Visual exploration behaviour was measured by means of a contact-free infrared eye-tracker while subjects were watching videos depicting spontaneous dialogues between two individuals. Cumulative fixation duration and mean fixation duration were calculated for the factors co-speech gesture (present and absent), gaze direction (to the speaker or to the listener), and region of interest (ROI), including hands, face, and body. RESULTS Both aphasic patients and healthy controls mainly fixated the speaker's face. We found a significant co-speech gesture × ROI interaction, indicating that the presence of a co-speech gesture encouraged subjects to look at the speaker. Further, there was a significant gaze direction × ROI × group interaction revealing that aphasic patients showed reduced cumulative fixation duration on the speaker's face compared to healthy controls. CONCLUSION Co-speech gestures guide the observer's attention towards the speaker, the source of semantic input. It is discussed whether an underlying semantic processing deficit or a deficit to integrate audio-visual information may cause aphasic patients to explore less the speaker's face.

Perception of co-speech gestures in aphasic patients: A visual exploration study during the observation of dyadic conversations

Background: Co-speech gestures are part of nonverbal communication during conversations. They either support the verbal message or provide the interlocutor with additional information. Furthermore, they prompt as nonverbal cues the cooperative process of turn taking. In the present study, we investigated the influence of co-speech gestures on the perception of dyadic dialogue in aphasic patients. In particular, we analysed the impact of co-speech gestures on gaze direction (towards speaker or listener) and fixation of body parts. We hypothesized that aphasic patients, who are restricted in verbal comprehension, adapt their visual exploration strategies. Methods: Sixteen aphasic patients and 23 healthy control subjects participated in the study. Visual exploration behaviour was measured by means of a contact-free infrared eye-tracker while subjects were watching videos depicting spontaneous dialogues between two individuals. Cumulative fixation duration and mean fixation duration were calculated for the factors co-speech gesture (present and absent), gaze direction (to the speaker or to the listener), and region of interest (ROI), including hands, face, and body. Results: Both aphasic patients and healthy controls mainly fixated the speaker’s face. We found a significant co-speech gesture x ROI interaction, indicating that the presence of a co-speech gesture encouraged subjects to look at the speaker. Further, there was a significant gaze direction x ROI x group interaction revealing that aphasic patients showed reduced cumulative fixation duration on the speaker’s face compared to healthy controls. Conclusion: Co-speech gestures guide the observer’s attention towards the speaker, the source of semantic input. It is discussed whether an underlying semantic processing deficit or a deficit to integrate audio-visual information may cause aphasic patients to explore less the speaker’s face. Keywords: Gestures, visual exploration, dialogue, aphasia, apraxia, eye movements

Assessment of English Language Learners Seeking a Graduate Degree in Speech Language Pathology

A shortage of bilingual/bicultural speech language pathologists may reflect a problem with recruitment and retention of bilingual/bicultural students. The purpose of the present study was to survey graduate training programs in speech language pathology to determine typical policies and practices concerning students who apply and are admitted as ELLs. With a growing number of ELL children needing services from a bilingual SLP, it seems that little is being done to address the issue. The problem may be with the reluctance of programs to not only accept ELL students, but there also seems to be a disinclination for any sort of training program to be established for these ELL students. Clinic directors were asked to complete a survey about ELLs seeking clinical training in speech language pathology. In particular, we were interested in obtaining information about whether clinical training programs a) provided opportunities for ELL to participate in clinic, b) assessed the English skills of these students, and c) provided remediation if these students English skills were judged to be less than proficient.

User Experience in Human-Technology Interaction. Communication, context and evaluation methodology

En esta Tesis se presentan dos líneas de investigación relacionadas y que contribuyen a las áreas de Interacción Hombre-Tecnología (o Máquina; siglas en inglés: HTI o HMI), lingüística computacional y evaluación de la experiencia del usuario. Las dos líneas en cuestión son el diseño y la evaluación centrada en el usuario de sistemas de Interacción Hombre-Máquina avanzados. En la primera parte de la Tesis (Capítulos 2 a 4) se abordan cuestiones fundamentales del diseño de sistemas HMI avanzados. El Capítulo 2 presenta una panorámica del estado del arte de la investigación en el ámbito de los sistemas conversacionales multimodales, con la que se enmarca el trabajo de investigación presentado en el resto de la Tesis. Los Capítulos 3 y 4 se centran en dos grandes aspectos del diseño de sistemas HMI: un gestor del diálogo generalizado para tratar la Interacción Hombre-Máquina multimodal y sensible al contexto, y el uso de agentes animados personificados (ECAs) para mejorar la robustez del diálogo, respectivamente. El Capítulo 3, sobre gestión del diálogo, aborda el tratamiento de la heterogeneidad de la información proveniente de las modalidades comunicativas y de los sensores externos. En este capítulo se propone, en un nivel de abstracción alto, una arquitectura para la gestión del diálogo con influjos heterogéneos de información, apoyándose en el uso de State Chart XML. En el Capítulo 4 se presenta una contribución a la representación interna de intenciones comunicativas, y su traducción a secuencias de gestos a ejecutar por parte de un ECA, diseñados específicamente para mejorar la robustez en situaciones de diálogo críticas que pueden surgir, por ejemplo, cuando se producen errores de entendimiento en la comunicación entre el usuario humano y la máquina. Se propone, en estas páginas, una extensión del Functional Mark-up Language definido en el marco conceptual SAIBA. Esta extensión permite representar actos comunicativos que realizan intenciones del emisor (la máquina) que no se pretende sean captadas conscientemente por el receptor (el usuario humano), pero con las que se pretende influirle a éste e influir el curso del diálogo. Esto se consigue mediante un objeto llamado Base de Intenciones Comunicativas (en inglés, Communication Intention Base, o CIB). La representación en el CIB de intenciones “no claradas” además de las explícitas permite la construcción de actos comunicativos que realizan simultáneamente varias intenciones comunicativas. En el Capítulo 4 también se describe un sistema experimental para el control remoto (simulado) de un asistente domótico, con autenticación de locutor para dar acceso, y con un ECA en el interfaz de cada una de estas tareas. Se incluye una descripción de las secuencias de comportamiento verbal y no verbal de los ECAs, que fueron diseñados específicamente para determinadas situaciones con objeto de mejorar la robustez del diálogo. Los Capítulos 5 a 7 conforman la parte de la Tesis dedicada a la evaluación. El Capítulo 5 repasa antecedentes relevantes en la literatura de tecnologías de la información en general, y de sistemas de interacción hablada en particular. Los principales antecedentes en el ámbito de la evaluación de la interacción sobre los cuales se ha desarrollado el trabajo presentado en esta Tesis son el Technology Acceptance Model (TAM), la herramienta Subjective Assessment of Speech System Interfaces (SASSI), y la Recomendación P.851 de la ITU-T. En el Capítulo 6 se describen un marco y una metodología de evaluación aplicados a la experiencia del usuario con sistemas HMI multimodales. Se desarrolló con este propósito un novedoso marco de evaluación subjetiva de la calidad de la experiencia del usuario y su relación con la aceptación por parte del mismo de la tecnología HMI (el nombre dado en inglés a este marco es Subjective Quality Evaluation Framework). En este marco se articula una estructura de clases de factores subjetivos relacionados con la satisfacción y aceptación por parte del usuario de la tecnología HMI propuesta. Esta estructura, tal y como se propone en la presente tesis, tiene dos dimensiones ortogonales. Primero se identifican tres grandes clases de parámetros relacionados con la aceptación por parte del usuario: “agradabilidad ” (likeability: aquellos que tienen que ver con la experiencia de uso, sin entrar en valoraciones de utilidad), rechazo (los cuales sólo pueden tener una valencia negativa) y percepción de utilidad. En segundo lugar, este conjunto clases se reproduce para distintos “niveles, o focos, percepción del usuario”. Éstos incluyen, como mínimo, un nivel de valoración global del sistema, niveles correspondientes a las tareas a realizar y objetivos a alcanzar, y un nivel de interfaz (en los casos propuestos en esta tesis, el interfaz es un sistema de diálogo con o sin un ECA). En el Capítulo 7 se presenta una evaluación empírica del sistema descrito en el Capítulo 4. El estudio se apoya en los mencionados antecedentes en la literatura, ampliados con parámetros para el estudio específico de los agentes animados (los ECAs), la auto-evaluación de las emociones de los usuarios, así como determinados factores de rechazo (concretamente, la preocupación por la privacidad y la seguridad). También se evalúa el marco de evaluación subjetiva de la calidad propuesto en el capítulo anterior. Los análisis de factores efectuados revelan una estructura de parámetros muy cercana conceptualmente a la división de clases en utilidad-agradabilidad-rechazo propuesta en dicho marco, resultado que da cierta validez empírica al marco. Análisis basados en regresiones lineales revelan estructuras de dependencias e interrelación entre los parámetros subjetivos y objetivos considerados. El efecto central de mediación, descrito en el Technology Acceptance Model, de la utilidad percibida sobre la relación de dependencia entre la intención de uso y la facilidad de uso percibida, se confirma en el estudio presentado en la presente Tesis. Además, se ha encontrado que esta estructura de relaciones se fortalece, en el estudio concreto presentado en estas páginas, si las variables consideradas se generalizan para cubrir más ampliamente las categorías de agradabilidad y utilidad contempladas en el marco de evaluación subjetiva de calidad. Se ha observado, asimismo, que los factores de rechazo aparecen como un componente propio en los análisis de factores, y además se distinguen por su comportamiento: moderan la relación entre la intención de uso (que es el principal indicador de la aceptación del usuario) y su predictor más fuerte, la utilidad percibida. Se presentan también resultados de menor importancia referentes a los efectos de los ECAs sobre los interfaces de los sistemas de diálogo y sobre los parámetros de percepción y las valoraciones de los usuarios que juegan un papel en conformar su aceptación de la tecnología. A pesar de que se observa un rendimiento de la interacción dialogada ligeramente mejor con ECAs, las opiniones subjetivas son muy similares entre los dos grupos experimentales (uno interactuando con un sistema de diálogo con ECA, y el otro sin ECA). Entre las pequeñas diferencias encontradas entre los dos grupos destacan las siguientes: en el grupo experimental sin ECA (es decir, con interfaz sólo de voz) se observó un efecto más directo de los problemas de diálogo (por ejemplo, errores de reconocimiento) sobre la percepción de robustez, mientras que el grupo con ECA tuvo una respuesta emocional más positiva cuando se producían problemas. Los ECAs parecen generar inicialmente expectativas más elevadas en cuanto a las capacidades del sistema, y los usuarios de este grupo se declaran más seguros de sí mismos en su interacción. Por último, se observan algunos indicios de efectos sociales de los ECAs: la “amigabilidad ” percibida los ECAs estaba correlada con un incremento la preocupación por la seguridad. Asimismo, los usuarios del sistema con ECAs tendían más a culparse a sí mismos, en lugar de culpar al sistema, de los problemas de diálogo que pudieran surgir, mientras que se observó una ligera tendencia opuesta en el caso de los usuarios del sistema con interacción sólo de voz. ABSTRACT This Thesis presents two related lines of research work contributing to the general fields of Human-Technology (or Machine) Interaction (HTI, or HMI), computational linguistics, and user experience evaluation. These two lines are the design and user-focused evaluation of advanced Human-Machine (or Technology) Interaction systems. The first part of the Thesis (Chapters 2 to 4) is centred on advanced HMI system design. Chapter 2 provides a background overview of the state of research in multimodal conversational systems. This sets the stage for the research work presented in the rest of the Thesis. Chapers 3 and 4 focus on two major aspects of HMI design in detail: a generalised dialogue manager for context-aware multimodal HMI, and embodied conversational agents (ECAs, or animated agents) to improve dialogue robustness, respectively. Chapter 3, on dialogue management, deals with how to handle information heterogeneity, both from the communication modalities or from external sensors. A highly abstracted architectural contribution based on State Chart XML is proposed. Chapter 4 presents a contribution for the internal representation of communication intentions and their translation into gestural sequences for an ECA, especially designed to improve robustness in critical dialogue situations such as when miscommunication occurs. We propose an extension of the functionality of Functional Mark-up Language, as envisaged in much of the work in the SAIBA framework. Our extension allows the representation of communication acts that carry intentions that are not for the interlocutor to know of, but which are made to influence him or her as well as the flow of the dialogue itself. This is achieved through a design element we have called the Communication Intention Base. Such r pr s ntation of “non- clar ” int ntions allows th construction of communication acts that carry several communication intentions simultaneously. Also in Chapter 4, an experimental system is described which allows (simulated) remote control to a home automation assistant, with biometric (speaker) authentication to grant access, featuring embodied conversation agents for each of the tasks. The discussion includes a description of the behavioural sequences for the ECAs, which were designed for specific dialogue situations with particular attention given to the objective of improving dialogue robustness. Chapters 5 to 7 form the evaluation part of the Thesis. Chapter 5 reviews evaluation approaches in the literature for information technologies, as well as in particular for speech-based interaction systems, that are useful precedents to the contributions of the present Thesis. The main evaluation precedents on which the work in this Thesis has built are the Technology Acceptance Model (TAM), the Subjective Assessment of Speech System Interfaces (SASSI) tool, and ITU-T Recommendation P.851. Chapter 6 presents the author’s work in establishing an valuation framework and methodology applied to the users’ experience with multimodal HMI systems. A novel user-acceptance Subjective Quality Evaluation Framework was developed by the author specifically for this purpose. A class structure arises from two orthogonal sets of dimensions. First we identify three broad classes of parameters related with user acceptance: likeability factors (those that have to do with the experience of using the system), rejection factors (which can only have a negative valence) and perception of usefulness. Secondly, the class structure is further broken down into several “user perception levels”; at the very least: an overall system-assessment level, task and goal-related levels, and an interface level (e.g., a dialogue system with or without an ECA). An empirical evaluation of the system described in Chapter 4 is presented in Chapter 7. The study was based on the abovementioned precedents in the literature, expanded with categories covering the inclusion of an ECA, the users’ s lf-assessed emotions, and particular rejection factors (privacy and security concerns). The Subjective Quality Evaluation Framework proposed in the previous chapter was also scrutinised. Factor analyses revealed an item structure very much related conceptually to the usefulness-likeability-rejection class division introduced above, thus giving it some empirical weight. Regression-based analysis revealed structures of dependencies, paths of interrelations, between the subjective and objective parameters considered. The central mediation effect, in the Technology Acceptance Model, of perceived usefulness on the dependency relationship of intention-to-use with perceived ease of use was confirmed in this study. Furthermore, the pattern of relationships was stronger for variables covering more broadly the likeability and usefulness categories in the Subjective Quality Evaluation Framework. Rejection factors were found to have a distinct presence as components in factor analyses, as well as distinct behaviour: they were found to moderate the relationship between intention-to-use (the main measure of user acceptance) and its strongest predictor, perceived usefulness. Insights of secondary importance are also given regarding the effect of ECAs on the interface of spoken dialogue systems and the dimensions of user perception and judgement attitude that may have a role in determining user acceptance of the technology. Despite observing slightly better performance values in the case of the system with the ECA, subjective opinions regarding both systems were, overall, very similar. Minor differences between two experimental groups (one interacting with an ECA, the other only through speech) include a more direct effect of dialogue problems (e.g., non-understandings) on perceived dialogue robustness for the voice-only interface test group, and a more positive emotional response for the ECA test group. Our findings further suggest that the ECA generates higher initial expectations, and users seem slightly more confident in their interaction with the ECA than do those without it. Finally, mild evidence of social effects of ECAs was also found: the perceived friendliness of the ECA increased security concerns, and ECA users may tend to blame themselves rather than the system when dialogue problems are encountered, while the opposite may be true for voice-only users.

Speech features of the domain of the word in heterosexual twins during the second yeard of life

Speech is the major function, emergence and which development radically changes all course of formation of the identity of the child already in the early childhood. If language and speech development in solitary born children is investigated today quite well, at twin children this process practically is not studied. Our research was carried out for the purpose of studying of an originality of mastering by speech by heterosexual children of pair of twins within communicative and pragmatist approach (T.N. Ushakov,G. V. Chirkina). Application of this approach to the analysis of process of communication at twin children allowed us to allocate those peculiar receptions and means of communication which they functionally develop in a situation of pair of twins, as allows them to show the phenomena of the speech which are not meeting at solitary born contemporaries. In this work results of supervision and research of pair of heterosexual twins of the second year of the life, carried out by a technique developed by us under the scientific guide of G. V. Chirkina

Contributions to Speech Analytics based on Speech Recognition and Topic Identification

La última década ha sido testigo de importantes avances en el campo de la tecnología de reconocimiento de voz. Los sistemas comerciales existentes actualmente poseen la capacidad de reconocer habla continua de múltiples locutores, consiguiendo valores aceptables de error, y sin la necesidad de realizar procedimientos explícitos de adaptación. A pesar del buen momento que vive esta tecnología, el reconocimiento de voz dista de ser un problema resuelto. La mayoría de estos sistemas de reconocimiento se ajustan a dominios particulares y su eficacia depende de manera significativa, entre otros muchos aspectos, de la similitud que exista entre el modelo de lenguaje utilizado y la tarea específica para la cual se está empleando. Esta dependencia cobra aún más importancia en aquellos escenarios en los cuales las propiedades estadísticas del lenguaje varían a lo largo del tiempo, como por ejemplo, en dominios de aplicación que involucren habla espontánea y múltiples temáticas. En los últimos años se ha evidenciado un constante esfuerzo por mejorar los sistemas de reconocimiento para tales dominios. Esto se ha hecho, entre otros muchos enfoques, a través de técnicas automáticas de adaptación. Estas técnicas son aplicadas a sistemas ya existentes, dado que exportar el sistema a una nueva tarea o dominio puede requerir tiempo a la vez que resultar costoso. Las técnicas de adaptación requieren fuentes adicionales de información, y en este sentido, el lenguaje hablado puede aportar algunas de ellas. El habla no sólo transmite un mensaje, también transmite información acerca del contexto en el cual se desarrolla la comunicación hablada (e.g. acerca del tema sobre el cual se está hablando). Por tanto, cuando nos comunicamos a través del habla, es posible identificar los elementos del lenguaje que caracterizan el contexto, y al mismo tiempo, rastrear los cambios que ocurren en estos elementos a lo largo del tiempo. Esta información podría ser capturada y aprovechada por medio de técnicas de recuperación de información (information retrieval) y de aprendizaje de máquina (machine learning). Esto podría permitirnos, dentro del desarrollo de mejores sistemas automáticos de reconocimiento de voz, mejorar la adaptación de modelos del lenguaje a las condiciones del contexto, y por tanto, robustecer al sistema de reconocimiento en dominios con condiciones variables (tales como variaciones potenciales en el vocabulario, el estilo y la temática). En este sentido, la principal contribución de esta Tesis es la propuesta y evaluación de un marco de contextualización motivado por el análisis temático y basado en la adaptación dinámica y no supervisada de modelos de lenguaje para el robustecimiento de un sistema automático de reconocimiento de voz. Esta adaptación toma como base distintos enfoque de los sistemas mencionados (de recuperación de información y aprendizaje de máquina) mediante los cuales buscamos identificar las temáticas sobre las cuales se está hablando en una grabación de audio. Dicha identificación, por lo tanto, permite realizar una adaptación del modelo de lenguaje de acuerdo a las condiciones del contexto. El marco de contextualización propuesto se puede dividir en dos sistemas principales: un sistema de identificación de temática y un sistema de adaptación dinámica de modelos de lenguaje. Esta Tesis puede describirse en detalle desde la perspectiva de las contribuciones particulares realizadas en cada uno de los campos que componen el marco propuesto: _ En lo referente al sistema de identificación de temática, nos hemos enfocado en aportar mejoras a las técnicas de pre-procesamiento de documentos, asimismo en contribuir a la definición de criterios más robustos para la selección de index-terms. – La eficiencia de los sistemas basados tanto en técnicas de recuperación de información como en técnicas de aprendizaje de máquina, y específicamente de aquellos sistemas que particularizan en la tarea de identificación de temática, depende, en gran medida, de los mecanismos de preprocesamiento que se aplican a los documentos. Entre las múltiples operaciones que hacen parte de un esquema de preprocesamiento, la selección adecuada de los términos de indexado (index-terms) es crucial para establecer relaciones semánticas y conceptuales entre los términos y los documentos. Este proceso también puede verse afectado, o bien por una mala elección de stopwords, o bien por la falta de precisión en la definición de reglas de lematización. En este sentido, en este trabajo comparamos y evaluamos diferentes criterios para el preprocesamiento de los documentos, así como también distintas estrategias para la selección de los index-terms. Esto nos permite no sólo reducir el tamaño de la estructura de indexación, sino también mejorar el proceso de identificación de temática. – Uno de los aspectos más importantes en cuanto al rendimiento de los sistemas de identificación de temática es la asignación de diferentes pesos a los términos de acuerdo a su contribución al contenido del documento. En este trabajo evaluamos y proponemos enfoques alternativos a los esquemas tradicionales de ponderado de términos (tales como tf-idf ) que nos permitan mejorar la especificidad de los términos, así como también discriminar mejor las temáticas de los documentos. _ Respecto a la adaptación dinámica de modelos de lenguaje, hemos dividimos el proceso de contextualización en varios pasos. – Para la generación de modelos de lenguaje basados en temática, proponemos dos tipos de enfoques: un enfoque supervisado y un enfoque no supervisado. En el primero de ellos nos basamos en las etiquetas de temática que originalmente acompañan a los documentos del corpus que empleamos. A partir de estas, agrupamos los documentos que forman parte de la misma temática y generamos modelos de lenguaje a partir de dichos grupos. Sin embargo, uno de los objetivos que se persigue en esta Tesis es evaluar si el uso de estas etiquetas para la generación de modelos es óptimo en términos del rendimiento del reconocedor. Por esta razón, nosotros proponemos un segundo enfoque, un enfoque no supervisado, en el cual el objetivo es agrupar, automáticamente, los documentos en clusters temáticos, basándonos en la similaridad semántica existente entre los documentos. Por medio de enfoques de agrupamiento conseguimos mejorar la cohesión conceptual y semántica en cada uno de los clusters, lo que a su vez nos permitió refinar los modelos de lenguaje basados en temática y mejorar el rendimiento del sistema de reconocimiento. – Desarrollamos diversas estrategias para generar un modelo de lenguaje dependiente del contexto. Nuestro objetivo es que este modelo refleje el contexto semántico del habla, i.e. las temáticas más relevantes que se están discutiendo. Este modelo es generado por medio de la interpolación lineal entre aquellos modelos de lenguaje basados en temática que estén relacionados con las temáticas más relevantes. La estimación de los pesos de interpolación está basada principalmente en el resultado del proceso de identificación de temática. – Finalmente, proponemos una metodología para la adaptación dinámica de un modelo de lenguaje general. El proceso de adaptación tiene en cuenta no sólo al modelo dependiente del contexto sino también a la información entregada por el proceso de identificación de temática. El esquema usado para la adaptación es una interpolación lineal entre el modelo general y el modelo dependiente de contexto. Estudiamos también diferentes enfoques para determinar los pesos de interpolación entre ambos modelos. Una vez definida la base teórica de nuestro marco de contextualización, proponemos su aplicación dentro de un sistema automático de reconocimiento de voz. Para esto, nos enfocamos en dos aspectos: la contextualización de los modelos de lenguaje empleados por el sistema y la incorporación de información semántica en el proceso de adaptación basado en temática. En esta Tesis proponemos un marco experimental basado en una arquitectura de reconocimiento en ‘dos etapas’. En la primera etapa, empleamos sistemas basados en técnicas de recuperación de información y aprendizaje de máquina para identificar las temáticas sobre las cuales se habla en una transcripción de un segmento de audio. Esta transcripción es generada por el sistema de reconocimiento empleando un modelo de lenguaje general. De acuerdo con la relevancia de las temáticas que han sido identificadas, se lleva a cabo la adaptación dinámica del modelo de lenguaje. En la segunda etapa de la arquitectura de reconocimiento, usamos este modelo adaptado para realizar de nuevo el reconocimiento del segmento de audio. Para determinar los beneficios del marco de trabajo propuesto, llevamos a cabo la evaluación de cada uno de los sistemas principales previamente mencionados. Esta evaluación es realizada sobre discursos en el dominio de la política usando la base de datos EPPS (European Parliamentary Plenary Sessions - Sesiones Plenarias del Parlamento Europeo) del proyecto europeo TC-STAR. Analizamos distintas métricas acerca del rendimiento de los sistemas y evaluamos las mejoras propuestas con respecto a los sistemas de referencia. ABSTRACT The last decade has witnessed major advances in speech recognition technology. Today’s commercial systems are able to recognize continuous speech from numerous speakers, with acceptable levels of error and without the need for an explicit adaptation procedure. Despite this progress, speech recognition is far from being a solved problem. Most of these systems are adjusted to a particular domain and their efficacy depends significantly, among many other aspects, on the similarity between the language model used and the task that is being addressed. This dependence is even more important in scenarios where the statistical properties of the language fluctuates throughout the time, for example, in application domains involving spontaneous and multitopic speech. Over the last years there has been an increasing effort in enhancing the speech recognition systems for such domains. This has been done, among other approaches, by means of techniques of automatic adaptation. These techniques are applied to the existing systems, specially since exporting the system to a new task or domain may be both time-consuming and expensive. Adaptation techniques require additional sources of information, and the spoken language could provide some of them. It must be considered that speech not only conveys a message, it also provides information on the context in which the spoken communication takes place (e.g. on the subject on which it is being talked about). Therefore, when we communicate through speech, it could be feasible to identify the elements of the language that characterize the context, and at the same time, to track the changes that occur in those elements over time. This information can be extracted and exploited through techniques of information retrieval and machine learning. This allows us, within the development of more robust speech recognition systems, to enhance the adaptation of language models to the conditions of the context, thus strengthening the recognition system for domains under changing conditions (such as potential variations in vocabulary, style and topic). In this sense, the main contribution of this Thesis is the proposal and evaluation of a framework of topic-motivated contextualization based on the dynamic and non-supervised adaptation of language models for the enhancement of an automatic speech recognition system. This adaptation is based on an combined approach (from the perspective of both information retrieval and machine learning fields) whereby we identify the topics that are being discussed in an audio recording. The topic identification, therefore, enables the system to perform an adaptation of the language model according to the contextual conditions. The proposed framework can be divided in two major systems: a topic identification system and a dynamic language model adaptation system. This Thesis can be outlined from the perspective of the particular contributions made in each of the fields that composes the proposed framework: _ Regarding the topic identification system, we have focused on the enhancement of the document preprocessing techniques in addition to contributing in the definition of more robust criteria for the selection of index-terms. – Within both information retrieval and machine learning based approaches, the efficiency of topic identification systems, depends, to a large extent, on the mechanisms of preprocessing applied to the documents. Among the many operations that encloses the preprocessing procedures, an adequate selection of index-terms is critical to establish conceptual and semantic relationships between terms and documents. This process might also be weakened by a poor choice of stopwords or lack of precision in defining stemming rules. In this regard we compare and evaluate different criteria for preprocessing the documents, as well as for improving the selection of the index-terms. This allows us to not only reduce the size of the indexing structure but also to strengthen the topic identification process. – One of the most crucial aspects, in relation to the performance of topic identification systems, is to assign different weights to different terms depending on their contribution to the content of the document. In this sense we evaluate and propose alternative approaches to traditional weighting schemes (such as tf-idf ) that allow us to improve the specificity of terms, and to better identify the topics that are related to documents. _ Regarding the dynamic language model adaptation, we divide the contextualization process into different steps. – We propose supervised and unsupervised approaches for the generation of topic-based language models. The first of them is intended to generate topic-based language models by grouping the documents, in the training set, according to the original topic labels of the corpus. Nevertheless, a goal of this Thesis is to evaluate whether or not the use of these labels to generate language models is optimal in terms of recognition accuracy. For this reason, we propose a second approach, an unsupervised one, in which the objective is to group the data in the training set into automatic topic clusters based on the semantic similarity between the documents. By means of clustering approaches we expect to obtain a more cohesive association of the documents that are related by similar concepts, thus improving the coverage of the topic-based language models and enhancing the performance of the recognition system. – We develop various strategies in order to create a context-dependent language model. Our aim is that this model reflects the semantic context of the current utterance, i.e. the most relevant topics that are being discussed. This model is generated by means of a linear interpolation between the topic-based language models related to the most relevant topics. The estimation of the interpolation weights is based mainly on the outcome of the topic identification process. – Finally, we propose a methodology for the dynamic adaptation of a background language model. The adaptation process takes into account the context-dependent model as well as the information provided by the topic identification process. The scheme used for the adaptation is a linear interpolation between the background model and the context-dependent one. We also study different approaches to determine the interpolation weights used in this adaptation scheme. Once we defined the basis of our topic-motivated contextualization framework, we propose its application into an automatic speech recognition system. We focus on two aspects: the contextualization of the language models used by the system, and the incorporation of semantic-related information into a topic-based adaptation process. To achieve this, we propose an experimental framework based in ‘a two stages’ recognition architecture. In the first stage of the architecture, Information Retrieval and Machine Learning techniques are used to identify the topics in a transcription of an audio segment. This transcription is generated by the recognition system using a background language model. According to the confidence on the topics that have been identified, the dynamic language model adaptation is carried out. In the second stage of the recognition architecture, an adapted language model is used to re-decode the utterance. To test the benefits of the proposed framework, we carry out the evaluation of each of the major systems aforementioned. The evaluation is conducted on speeches of political domain using the EPPS (European Parliamentary Plenary Sessions) database from the European TC-STAR project. We analyse several performance metrics that allow us to compare the improvements of the proposed systems against the baseline ones.

On cortical coding of vocal communication sounds in primates

Understanding how the brain processes vocal communication sounds is one of the most challenging problems in neuroscience. Our understanding of how the cortex accomplishes this unique task should greatly facilitate our understanding of cortical mechanisms in general. Perception of species-specific communication sounds is an important aspect of the auditory behavior of many animal species and is crucial for their social interactions, reproductive success, and survival. The principles of neural representations of these behaviorally important sounds in the cerebral cortex have direct implications for the neural mechanisms underlying human speech perception. Our progress in this area has been relatively slow, compared with our understanding of other auditory functions such as echolocation and sound localization. This article discusses previous and current studies in this field, with emphasis on nonhuman primates, and proposes a conceptual platform to further our exploration of this frontier. It is argued that the prerequisite condition for understanding cortical mechanisms underlying communication sound perception and production is an appropriate animal model. Three issues are central to this work: (i) neural encoding of statistical structure of communication sounds, (ii) the role of behavioral relevance in shaping cortical representations, and (iii) sensory–motor interactions between vocal production and perception systems.

Scientific bases of human-machine communication by voice.

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

The role of voice input for human-machine communication.

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

Processing of speech signals for physical and sensory disabilities.

Assistive technology involving voice communication is used primarily by people who are deaf, hard of hearing, or who have speech and/or language disabilities. It is also used to a lesser extent by people with visual or motor disabilities. A very wide range of devices has been developed for people with hearing loss. These devices can be categorized not only by the modality of stimulation [i.e., auditory, visual, tactile, or direct electrical stimulation of the auditory nerve (auditory-neural)] but also in terms of the degree of speech processing that is used. At least four such categories can be distinguished: assistive devices (a) that are not designed specifically for speech, (b) that take the average characteristics of speech into account, (c) that process articulatory or phonetic characteristics of speech, and (d) that embody some degree of automatic speech recognition. Assistive devices for people with speech and/or language disabilities typically involve some form of speech synthesis or symbol generation for severe forms of language disability. Speech synthesis is also used in text-to-speech systems for sightless persons. Other applications of assistive technology involving voice communication include voice control of wheelchairs and other devices for people with mobility disabilities.

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

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

Speech technology in the year 2001.

This paper introduces the session "Technology in the Year 2001" and is the first of four papers dealing with the future of human-machine communication by voice. In looking to the future it is important to recognize both the difficulties of technological forecasting and the frailties of the technology as it exists today--frailties that are manifestations of our limited scientific understanding of human cognition. The technology to realize truly advanced applications does not yet exist and cannot be supported by our presently incomplete science of speech. To achieve this long-term goal, the authors advocate a fundamental research program using a cybernetic approach substantially different from more conventional synthetic approaches. In a cybernetic approach, feedback control systems will allow a machine to adapt to a linguistically rich environment using reinforcement learning.

Speech technology in 2001: new research directions.

Research in speech recognition and synthesis over the past several decades has brought speech technology to a point where it is being used in "real-world" applications. However, despite the progress, the perception remains that the current technology is not flexible enough to allow easy voice communication with machines. The focus of speech research is now on producing systems that are accurate and robust but that do not impose unnecessary constraints on the user. This chapter takes a critical look at the shortcomings of the current speech recognition and synthesis algorithms, discusses the technical challenges facing research, and examines the new directions that research in speech recognition and synthesis must take in order to form the basis of new solutions suitable for supporting a wide range of applications.