[pt] Spoken Dialogue Systems (SDS s) são sistemas baseados em computadores desenvolvidos para fornecerem informações e realizar tarefas utilizando o diálogo como forma de interação. Eles são capazes de reconhecimento de voz, interpretação, gerenciamento de diálogo e são capazes de ter uma voz como saída de dados, tentando reproduzir uma interação natural falada entre um usuário humano e um sistema. SDS s provém diferentes serviços, todos através de linguagem falada com um sistema. Mesmo com todo o desenvolvimento nesta área, há escassez de informações sobre como avaliar a qualidade de tais sistemas com o propósito de otimização do mesmo. Com dois destes sistemas, BoRIS e INSPIRE, usados para reservas de restaurantes e gerenciamento de casas inteligentes, diversos experimentos foram conduzidos no passado, onde tais sistemas foram utilizados para resolver tarefas específicas. Os participantes avaliaram a qualidade do sistema em uma série de questões. Além disso, todas as interações foram gravadas e anotadas por um especialista.O desenvolvimento de métodos para avaliação de performance é um tópico aberto de pesquisa na área de SDS s. Seguindo a idéia do modelo PARADISE (PARAdigm for DIalogue System Evaluation – desenvolvido pro Walker e colaboradores na AT&T em 1998), diversos experimentos foram conduzidos para desenvolver modelos de previsão de performance de sistemas de reconhecimento de voz e linguagem falada. O objetivo desta dissertação de mestrado é desenvolver modelos que permitam a previsão de dimensões de qualidade percebidas por um usuário humano, baseado em parâmetros instrumentalmente mensuráveis utilizando dados coletados nos experimentos realizados com os sistemas BoRIS e INSPIRE , dois sistemas de reconhecimento de voz (o primeiro para busca de restaurantes e o segundo para Smart Homes). Diferentes algoritmos serão utilizados para análise (Regressão linear, Árvores de Regressão, Árvores de Classificação e Redes Neurais) e para cada um dos algoritmos, uma ferramenta diferente será programada em MATLAB, para poder servir de base para análise de experimentos futuros, sendo facilmente modificado para sistemas e parâmetros novos em estudos subsequentes.A idéia principal é desenvolver ferramentas que possam ajudar na otimização de um SDS sem o envolvimento direto de um usuário humano ou servir de ferramenta para estudos futuros na área. / [en] Spoken Dialogue Systems (SDS s) are computer-based systems developed to provide information and carry out tasks using speech as the interaction mode. They are capable of speech recognition, interpretation, management of dialogue and have speech output capabilities, trying to reproduce a more or less natural spoken interaction between a human user and the system. SDS s provide several different services, all through spoken language. Even with all this development, there is scarcity of information on ways to assess and evaluate the quality of such systems with the purpose of optimization. With two of these SDS s ,BoRIS and INSPIRE, (used for Restaurant Booking Services and Smart Home Systems), extensive experiments were conducted in the past, where the systems were used to resolve specific tasks. The evaluators rated the quality of the system on a multitude of scales. In addition to that, the interactions were recorded and annotated by an expert. The development of methods for performance evaluation is an open research issue in this area of SDS s. Following the idea of the PARADISE model (PARAdigm for DIalogue System Evaluation model, the most well-known model for this purpose (developed by Walker and co-workers at AT&T in 1998), several experiments were conducted to develop predictive models of spoken dialogue performance. The objective of this dissertation is to develop and assess models which allow the prediction of quality dimensions as perceived by the human user, based on instrumentally measurable variables using all the collected data from the BoRIS and INSPIRE systems. Different types of algorithms will be compared to their prediction performance and to how generic they are. Four different approaches will be used for these analyses: Linear regression, Regression Trees, Classification Trees and Neural Networks. For each of these methods, a different tool will be programmed using MATLAB, that can carry out all experiments from this work and be easily modified for new experiments with data from new systems or new variables on future studies. All the used MATLAB programs will be made available on the attached CD with an operation manual for future users as well as a guide to modify the existing programs to work on new data. The main idea is to develop tools that would help on the optimization of a spoken dialogue system without a direct involvement of the human user or serve as tools for future studies in this area.

This thesis aims to explore an aspect of the history of vernacular speech through analysis of some eighteenth century verse texts. These satirical anti-Jesuit pamphlets by Nicolas Jouin, known as the 'Sarcelades', were collected posthumously in 'Le Vrai Recueil des Sarcelles' of 1764. The texts purport to be in the patois of the peasants of Sarcelles and show features which may be paralleled in the vernacular speech of Paris and elsewhere, and even correspond with features of contemporary colloquial French. The study may appeal to French historical sociolinguists interested in reconstructing spoken language of the past, and particularly in the history of vernacular speech of Paris since the Middle Ages through to the eighteenth century, in the context of the development of urban dialects. In order to set the scene for a linguistic description of Jouin’s work the limited biographical information available was collated. Then a period of bibliographical research led to acquisition of copies of the texts which were to be studied in order to identify and examine their non-standard linguistic features. Firstly the process of growth of urban dialects was discussed, and then the development of the Paris vernacular in particular. Then attention was turned to direct written evidence in the form of commentary and to a number of texts from the sixteenth to eighteenth centuries containing features of the Paris vernacular. These had already been analysed by certain historical linguists, although the texts in the 'Sarcelades' had hitherto only been briefly mentioned. However, here they are considered to be of sufficient interest to be examined more closely, although it had to be established whether Jouin’s texts containing a selection of non-standard features could be regarded as an accurate depiction of the Paris vernacular at the period. The non-standard phonetic, morphological, syntactic, and lexical features in the texts were therefore compared with findings in other texts by previous commentators. Following these analyses it was noted to what extent the relative frequency of the variables correlates with the salience of certain features in popular speech in Paris at the period, as already observed in other texts by previous commentators, and it was concluded that in general established characteristics of the 'patois de Paris' at the period are to be found in the 'Sarcelades', even though there do remain certain features which do not appear to be generally attested elsewhere. Nevertheless, despite reservations concerning the authenticity of some of the non-standard features employed by Jouin, by bringing attention to this little-known series of texts this study may help to claim a place for the Sarcelades amongst the corpus of texts which reflect aspects of the lower-class sociolect, the 'patois de Paris', at the period.

(in English): The work in this diploma contains an analysis of speech accuracy and fluency of Russian speaking and English speaking students of Czech language, based on case studies. For these case studies two Russian speaking students and two English speaking students were chosen to take part. The results were compared to the results of one native Czech speaker. The accuracy and fluency analysis was carried out based on the language principles of Rod Ellis. Within the accuracy analysis, the number of error free clauses and the average number of mistakes per one hundred words were measured. Accuracy of speech is examined through concrete grammatical phenomena like the usage of reflexive particle se/si and the usage of the verb to be in the past tense. The work in this diploma also considers the ability of analysed speakers to switch between language codes and to distinguish features of formal and spoken Czech language (spoken language in informal situations). The fluency of speech is studied based on the speech rate of all analysed speakers by counting the number of syllables per one hundred words. Subsequently, the number of false starts, repetition of words or phrases, the frequency of usage of parasite words and hesitation sounds were also examined. One of the diploma hypothesis is the statement...

科学研究費補助金 研究種目:基盤研究(B)(2) 課題番号:07458049 研究代表者:尾崎 明人 研究期間:1995-1997年度

L’objectif de la présente étude est de cerner les difficultés rencontrées en lecture et en orthographe par les enfants issus de l’immigration de 2ème et 3ème génération qui on été comparés à leurs pairs autochtones inscrits dans les même classes. L’échantillon comprend 357 élèves scolarisés dans des écoles communales en discrimination positive de la région de Bruxelles Capitale. Un suivi longitudinal de la 3ème à la 5ème année primaire a également été mené. Les résultats nous ont permis d’évaluer les performances en langue orale et en langue écrite de ces élèves, et de mettre en évidence d’une part les mécanismes de lecture et d’écriture et d’autre part les facteurs susceptibles d’expliquer les retards sur le plan psycholinguistique. Deux programmes d’entraînements, au niveau phonologique et syntaxique ont été élaborés en vue de mesurer leur effet sur les différences de compétences. / The objective of this study is to determine the difficulties encountered in reading and spelling by children from emigrant families (2nd and 3rd generation) compared with their pars autochthons registered in the same classes. The sample includes 357 pupils in positive discrimination elementary schools from the area of Brussels City. A longitudinal follow-up from 3rd to 5th primary grade was also carried out. The results enabled us to evaluate the performances in spoken and written language of these pupils and to highlight the mechanisms of reading and writing and the factors which explain psycholinguistics delays. Two training programs, one phonologic, the other syntactic were elaborate in order to measure their effect on the differential of skills. / Doctorat en Sciences Psychologiques et de l'éducation / info:eu-repo/semantics/nonPublished