La version intégrale de ce mémoire est disponible uniquement pour consultation individuelle à la Bibliothèque de musique de l’Université de Montréal (www.bib.umontreal.ca/MU). / L’hypothèse d’une influence réciproque entre l’environnement et notre perception sonore représente la base de ma recherche musicale. Villusions est un projet acousmatique qui puise sa source dans l’analyse introspective de cette complexe relation, plus précisément entre les sons du quotidien et l’oreille curieuse d’un voyageur éternel. Les parties les plus intimement liées à mes expériences personnelles de la ville de Montréal et ses banlieues représentent donc le théâtre de cette exploration assidue; les illusions correspondent à trois pièces acousmatiques inspirées par ce contexte de réciprocité. Dans l’ensemble des œuvres présentées, les moments musicaux s’alternent, s’intègrent et se confondent aux éléments sonores naturels qui en constituent souvent la racine génératrice. Ces matériaux ont été développés suivant trois axes principaux : d’abord l’axe des mouvements, associés aux moyens de transport et aux centres névralgiques à travers lesquels se répandent les impulsions de la ville; ensuite l’axe des voix qui témoigne de sa multiethnicité, de sa lymphe vitale; finalement, l’axe de l’alternance des saisons comme prétexte sonore lié au contexte temporel. Des sources sonores instrumentales, dérivées des tablâ et de la harpe, trouvent également leur place dans le projet, en lui donnant une empreinte à la fois rythmique et harmonique. La composante spatiale doit être considérée comme un élément incontournable du discours musical de Villusions. Sa construction octophonique porte sur l’équilibre, délicat et illusoirement immersif, généré par des trajectoires dessinées sur la même ligne temporelle que celle des évènements musicaux, suivant des stratégies intégrées directement dans le processus compositionnel. / This musical research is based on the theory of interaction between the environment and our sound perception. Villusions is an acousmatic project that emerged from the introspective analysis of this complex relationship, in particular between daily sounds and the curious ear of an eternal traveller. Thus, the parts most closely related to my personal experiences in the city (“ville”) of Montréal and its suburbs are where this diligent exploration took place; the illusions are three acousmatic pieces inspired by this context of reciprocity. In the works presented, musical moments alternate, integrate with each other, and merge with the natural sound elements that often constitute the originating roots. This material was developed with three main focuses: firstly, movement, associated with modes of transportation and the nerve centres through which beats the city’s pulse; secondly, the voices that express its multi ethnicity, its vital lymph; and, lastly, the changing of the seasons as an acoustic proxy related to the temporal context. Instrumental sound sources, derived from the tablâ and the harp, are also used in the project, lending both a rhythmic and a harmonic feel. The spatial component should be seen as an essential element of the musical discourse of Villusions. Its octophonic construction features the delicate and deceptively immersive balance created by trajectories drawn on the same timeline as those of the musical events, using techniques directly integrated into the compositional process.

S’il est aujourd’hui communément admis que la perception de la parole s’effectue d’une manière plus optimale en mode audiovisuel qu’en mode auditif seul (Benoît, Mohamadi et Kandel, 1994, Schwartz, Berthommier et Savariaux, 2004), la nature des informations visuelles dont il est le plus souvent question est la mimo-gestuelle articulatoire fournie par le locuteur en face à face. Cependant, dans une situation d’enseignement d’une langue étrangère, un autre type d’aide visuelle intervient généralement : la forme écrite des éléments oraux. Pourtant en didactique des langues étrangères, la question du passage à l’écrit est loin d’être consensuelle et certains didacticiens se prononcent en faveur d’un entraînement intensif de la prononciation au tout début de l’apprentissage, avant que l’apprenant ne soit confronté au code écrit (Lauret, 2007). Notre hypothèse est que la dimension facilitante de la forme écrite pour certains publics ne doit pas être négligée, même en début d’apprentissage. Notre recherche se fonde sur des expérimentations menées auprès d’apprenants hindiphones. Tenant compte des spécificités de ce public, nous pensons que l’écrit peut, dans certains cas, faciliter sa réception orale des sons du français en début d’apprentissage, condition nécessaire et préalable à leur production (Renard, 1979). Les tests que nous avons conçus obligent les apprenants à recentrer leur attention sur la graphie de sons (les voyelles nasales [ɑ̃] et [ɔ̃]) dès le début de leur apprentissage au moyen de diverses focalisations visuelles écrites (Fort, Spinelli, Savariaux et Kandel, 2010). Les propositions didactiques que nous formulons à la suite reposent sur la suite logique perception – (transcription graphique) — production même si cette présente étude se centre sur l’évaluation de la perception des sons. / It is commonly admitted today that speech perception is more performing in an audiovisual context than in a visual one (Benoît, Mohamadi and Kandel, 1994, Schwartz, Berthommier and Savariaux, 2004). Visual information in this situation often consists of the speaker’s articulatory and facial gestures provided by the face-to-face interaction. However, when learning a foreign language, another type of visual help is generally available to identify oral forms: their written forms. And yet, in the field of didactics of foreign languages, the issue of the oral-written transition is far from being consensual and some didacticians favour training the pronunciation skills of the learner at the beginning of the learning process, before he is confronted to the written code (Lauret, 2007). Our hypothesis is that the facilitating effect of written forms should not be neglected, even at the beginning of a foreign language learning process. Our research is based on the case of Hindi speakers. Taking into consideration the specificities of this population, we think that written information can, in some cases, facilitate the oral reception of French sounds in the beginning of the learning process, which would be a preliminary condition to their production (Renard, 1979). We have conceived a series of test, forcing the Hindi speaking learners to refocus their attention on the nasal vowels [ɑ̃] and [ɔ̃]’s written form from the beginning of the learning process, using different forms of visual written focuses (Fort, Spinelli, Savariaux and Kandel, 2010). Our didactic proposal relies on the following process: perception – (written form transcription) – production, even though the present study is centred on the evaluation of speech perception.

Ce travail de recherche interlangue arabe-français s’inscrit à la croisée de la psycholinguistique, la psychologie cognitive etla didactique. Il se déroule au Maroc (Agadir) pays polyglossique. Notre étude s’attache à déterminer dans quelle mesure etavec quelle importance, l’apprentissage de la lecture en français (L2) intervient dans le développement de la perception etde la prononciation de cette même langue. Nous supposons que les connaissances orthographiques et phonologiques,acquises par le biais de la lecture, permettraient de rendre plus saillantes certaines représentations phonologiques de lalangue cible. Nous étudions cette hypothèse en nous appuyant sur l’acquisition des phonèmes [e] et [y] du français sourcede difficultés pour le locuteur marocain. Nous avons mené une étude longitudinale sur une année scolaire avec des enfants arabophones marocains apprenant le français écrit au Maroc. Nous avons mis en place un protocole d’évaluation des compétences orales en français à partir de tâches de conscience phonologique, de perception, de prononciation et delecture. Un questionnaire a également été distribué aux parents afin de nous renseigner sur l’environnement linguistiquedes enfants testés. L’analyse des résultats indique que l’apprentissage de la lecture en L2 entraîne la consolidation desconversions graphophonologiques, ce qui permet aux enfants de disposer de catégories phonémiques mieux définies, et de mieux percevoir et prononcer des sons absents du système phonologique de leur langue première. / This research on French-Arabic interlanguage is at the junction of psycholinguistics , cognitive psychology and didactics . It takes place in a multilingual country, Morocco (Agadir). Our study seeks to establish to what extent learning to read in French (L2) impacts the development of perception and pronunciation of this language and how important this learning is. We assume indeed that spelling and phonological skills gained through reading, could make certain phonological representations of the target language more salient. We explore this hypothesis by resorting to the acquisition of two French phonemes [e] and [y] create difficulties for Moroccan speakers.In order to verify that mastering spelling-phonological correspondences contributes to improving the quality of the phonological system of this language , we carried out a longitudinal study during a school year with Arabic-speaking Moroccan children Learning written French in Morocco. We have established a protocol for assessing oral proficiency in Arabic and French based on phonological awareness tasks (validated speech therapy tests) and on perception and expression skills. We set up to a reading test to provide information on speed , reading correction and vocabulary maturity of the subject. A questionnaire was also distributed to parents to provide insights into the linguistic environment of tested children. Result analysis shows that learning how to read in L2 consolidates writing and phonological conversion , which would allow children to own better defined phoneme categories , and consequently to better perceive and pronounce sounds that are absent from their first language phonological system.

[pt] Este trabalho tem o seu foco no estudo da expressão hiuotesía, na literatura de tradição paulina, que é, em toda a Sagrada Escritura, a única que a utiliza. Embora haja trabalhos significativos sobre a questão, esta pesquisa estabelece um estudo comparativo entre a hiuotesía no contexto imediato de Gl 4,1-7, circunstanciada pela expressão plerôma tou chrónou e de Ef 1,3-10, onde, curiosamente, é utilizada a expressão plerôma tõn Kairôn. Nessa comparação reside a originalidade da presente pesquisa. Como os dois textos que reportam este termo encontram-se em contextos literários mais amplos, a primeira tarefa diz respeito ao estudo da estrutura de cada um desses contextos. Em seguida, passa-se ao estudo exegético de cada um deles, levando-se em conta aspectos semânticos, sobretudo em sua abordagem diacrônica. Com isto chega-se a identificar o alcance do vocábulo hiotesía e das expressões plerôma tou chrónou e plerôma tõn Kairôn em cada perícope A análise e comparação desses dois textos da tradição paulina evidenciam que as dessemelhanças existentes entre eles são decorrentes de paradigmas distintos que demandam, por isso mesmo, diferenciadas abordagens teológicas. Nesse sentido, o autor de Ef, ao se apropriar das expressões hiuotesía e plerôma tõn Kairôn, apresenta, de sua parte, uma nova e diferente interpretação do que o autor de Gl, anteriormente, dissera ao servir-se das expressões plerôma tou chrónou e hiuotesía. / [en] This work concentrates on the study of the expression hiuotesía in the writings of the Pauline tradition, the only one to use it in all the Holy Scriptures. Though significant works have been written on this matter, our present research frames a study on hiuotesía in the immediate context of Gal 4:1-7 and accompanied by the expression plerôma tou chrónou, as compared with that of Eph 1:3-10 where, stringly, the expression plerôma tõn Kairôn is used. In this comparison lies the originality of the present research. Since each of the texts that employ this term must be seen in it ampler literary context, the first task is to study the structure of each of those contexts. Next, follows the exegetical study of each of them, taking into consideration semantic aspects, especially in their diachronic approach. We thus manage to identify the range of the word hiuotesía and expression plerôma tou chrónou and plerôma tõn Kairôn in each pericope. Analysis and comparison between these two texts of the Pauline tradition show that the dissimilarities between them result from distinct paradigms which, therefore, demand differing theological approaches. In this sense, the author of Eph, by making his own the expressions hiuotesía and plerôma tõn Kairôn, offers, for his part, a new interpretation, differing from what the author of Gal had previously said by using the expressions plerôma tou chrónou and hiuotesía.

L’âge moyen de la population française et européenne augmente, cette constatation apporte de nouveaux enjeux techniques et sociétaux, les personnes âgées étant les personnes les plus fragiles et les plus vulnérables, notamment du point de vue des accidents domestiques et en particulier des chutes. C’est pourquoi de nombreux projets d’aide aux personnes âgées : techniques, universitaires et commerciaux ont vu le jour ces dernières années. Ce travail de thèse a été effectué sous convention Cifre, conjointement entre l’entreprise KRG Corporate et le laboratoire BMBI (Biomécanique et Bio-ingénierie) de l’UTC (Université de technologie de Compiègne). Elle a pour objet de proposer un capteur de reconnaissance de sons et des activités de la vie courante, dans le but d’étoffer et d’améliorer le système de télé-assistance déjà commercialisé par la société. Plusieurs méthodes de reconnaissance de parole ou de reconnaissance du locuteur ont déjà été éprouvées dans le domaine de la reconnaissance de sons, entre autres les techniques : GMM (Modèle de mélange gaussien–Gaussian Mixture Model), SVM-GSL (Machine à vecteurs de support, GMM-super-vecteur à noyau linéaire – Support vector machine GMM Supervector Linear kernel) et HMM (Modèle de Markov caché – Hidden Markov Model). De la même manière, nous nous sommes proposés d’utiliser les i-vecteurs pour la reconnaissance de sons. Les i-vecteurs sont utilisés notamment en reconnaissance de locuteur, et ont révolutionné ce domaine récemment. Puis nous avons élargi notre spectre, et utilisé l’apprentissage profond (Deep Learning) qui donne actuellement de très bon résultats en classification tous domaines confondus. Nous les avons tout d’abord utilisés en renfort des i-vecteurs, puis nous les avons utilisés comme système de classification exclusif. Les méthodes précédemment évoquées ont également été testées en conditions bruités puis réelles. Ces différentes expérimentations nous ont permis d’obtenir des taux de reconnaissance très satisfaisants, les réseaux de neurones en renfort des i-vecteurs et les réseaux de neurones seuls étant les systèmes ayant la meilleure précision, avec une amélioration très significative par rapport aux différents systèmes issus de la reconnaissance de parole et de locuteur. / The average age of the French and European population is increasing; this observation brings new technical and societal challenges. Older people are the most fragile and vulnerable, especially in terms of domestic accidents and specifically falls. This is why many elderly people care projects : technical, academic and commercial have seen the light of day in recent years. This thesis work wasc arried out under Cifre agreement, jointly between the company KRG Corporate and the BMBI laboratory (Biomechanics and Bioengineering) of the UTC (Université of Technologie of Compiègne). Its purpose is to offer a sensor for sound recognition and everyday activities, with the aim of expanding and improving the tele-assistance system already marketed by the company. Several speech recognition or speaker recognition methods have already been proven in the field of sound recognition, including GMM (Modèle de mélange gaussien – Gaussian Mixture Model), SVM-GSL (Machine à vecteurs de support, GMM-super-vecteur à noyau linéaire – Support vector machine GMM Supervector Linear kernel) and HMM (Modèle de Markov caché – Hidden Markov Model). In the same way, we proposed to use i-vectors for sound recognition. I-Vectors are used in particular in speaker recognition, and have revolutionized this field recently. Then we broadened our spectrum, and used Deep Learning, which currently gives very good results in classification across all domains. We first used them to reinforce the i-vectors, then we used them as our exclusive classification system. The methods mentioned above were also tested under noisy and then real conditions. These different experiments gaves us very satisfactory recognition rates, with neural networks as reinforcement for i-vectors and neural networks alone being the most accurate systems, with a very significant improvement compared to the various speech and speaker recognition systems.

Submitted by Filipe dos Santos (fsantos@pucsp.br) on 2018-04-16T12:55:23Z No. of bitstreams: 1 Rosemy Aparecida Mendonça Villela.pdf: 720043 bytes, checksum: 6a003060750d207b7242e975da7e3b55 (MD5) / Made available in DSpace on 2018-04-16T12:55:23Z (GMT). No. of bitstreams: 1 Rosemy Aparecida Mendonça Villela.pdf: 720043 bytes, checksum: 6a003060750d207b7242e975da7e3b55 (MD5) Previous issue date: 2018-02-23 / Conselho Nacional de Pesquisa e Desenvolvimento Científico e Tecnológico - CNPq / This dissertation arises from the uneasiness resulting from the intersections of paths that make up my personal, professional and academic trajectory. In it, the focus is directed to the problematic involved in the mother-child relationship. When a child is born healthy, without malformation or sensory deprivation, parents generally find themselves in more favorable conditions to support the set of representations involved in the birth of a child. Accidents can have a disturbing effect on this group and produce a "wound" there. In many cases, there is disinvestment of the parents towards the child, which can be marked by the sign of pathology. This study takes a dip in the psychoanalytic theory in the subject. In this theoretical framework, language has a determining role in the structuring of the subject. Its logical antecedence is admitted in relation to the arrival of the baby to the world and that, thus, the child, is "captured" by the language, in other words, in the imaginary and symbolic networks of the Other that even precede the child’s arrival. It is recognized by this dissertation the recognition of the hypothesis of the unconscious, introduced by Freud (1900) and of the consequent theorization about the subject, developed by Jacques Lacan in his work. It is understood, therefore, that the child-language-other relationship is the soil of language acquisition and the constitution of the subject (Lemos, 1992). Psychoanalysis conceptualizes the mother-child relationship in a vertical way and throws light on the conflict involved in the idea of "catching the child by the other speaker". This work contributes, this way, to the understanding of situations where "something is not going well": situations that are resolved in complex clinical settings or in difficult relationships. This dissertation reflects a formation driven by the studies in the field of Language Clinic, led and constructed by Maria Francisca Lier-DeVitto, in the LAEL-PUCSP, in which an original direction of theorization and research focused on language pathologies are developed. This Research Group is linked to the Interactionism in Language Acquisition (Lemos, since 1992) and also Psychoanalysis. The encounter with this theoretical aspect has guided, as a sort of "lens", my discussion about the complex matrix that is the mother-child relationship and its effects on the acquisition of language and the structuring of the subject. Membership in the Acquisition, Pathologies and Clinical Clinical Research Group (LAEL-PUCSP / CNPq) stimulated and is in the basis of this this work’s discussions / Esta dissertação surge de inquietações resultantes do entrecruzamentos de caminhos que compõem minha trajetória pessoal, profissional e acadêmica. Nele, o foco está dirigido para a problemática envolvida na relação mãe-filho. Quando uma criança nasce saudável, sem malformação ou privação sensorial, os pais encontram-se, geralmente, em condições mais favoráveis para sustentar o conjunto de representações implicadas no nascimento de um filho. Acidentes podem incidir de forma perturbadora nesse conjunto e produzir ali uma “ferida”. Em muitos casos, há desinvestimento dos pais na criança, que pode ficar marcada pelo signo de patologia. Este estudo faz um mergulho na teoria psicanalítica sobre o assunto. Neste âmbito teórico, a linguagem tem papel determinante na estruturação do sujeito. Admite-se sua anterioridade lógica em relação à chegada do bebê ao mundo e que, sendo assim, a criança, é “capturada” pela linguagem, i.e., nas redes imaginárias e simbólicas do Outro que, inclusive, precedem sua chegada. Nesta dissertação dá-se reconhecimento à hipótese do inconsciente, introduzida por Freud (1900) e à consequente teorização sobre o sujeito, desenvolvida por Jacques Lacan em sua obra. Entende-se, assim, que a relação criança-língua-outro é solo da aquisição da linguagem e da constituição do sujeito (LEMOS, 1992). A Psicanálise problematiza de forma vertical a relação mãe-criança e joga luz sobre o conflito implicado na ideia de “captura da criança pelo outro-falante”. Este trabalho contribui, assim, para o entendimento de situações em que “algo não vai bem”: situações que se resolvem em quadros clínicos complexos ou em relações difíceis. Esta dissertação reflete uma formação impulsionada pelos estudos no campo da Clínica de Linguagem, liderada e construída por Maria Francisca Lier-DeVitto, no LAEL-PUCSP, em que se desenvolve uma direção original de teorização e pesquisa focadas nas patologias de linguagem. Este Grupo de Pesquisa tem vínculos com Interacionismo em Aquisição de Linguagem (Lemos, desde 1992) e, também, com a Psicanálise. O encontro com esta vertente teórica tem guiado, como uma espécie de “lente”, minha discussão sobre a matriz complexa que é a relação mãe-criança e seus efeitos na aquisição da linguagem e na estruturação do sujeito. A filiação ao Grupo de Pesquisa Aquisição, patologias e clínica de linguagem (LAEL-PUCSP/CNPq) impulsionou e está na base das discussões deste trabalho

O presente estudo tem como objetivo determinar se a gravidade da DPOC poderá ser estimada através da área do gráfico das intensidades sonoras dos sons respiratórios de pacientes com DPOC. O estudo realizado com 51 pacientes com DPOC leve, moderado, grave, muito grave e 7 indivíduos saudáveis não fumantes. Os sons respiratórios de cada participante, foram coletados através de estetoscópio adaptado com um mini microfone. O método compara as áreas das intensidades sonoras em função da frequência de pacientes de DPOC e indivíduos saudáveis. Neste contexto, para atender ao objetivo, um método foi proposto e testado baseado na combinação de técnicas de filtragem e TFTC, seguida de análise estatística, cálculo da média, desvio padrão e interpolação. Os resultados sugerem que a área do gráfico da variância da intensidade sonora em função da frequência diminui quando aumenta a gravidade da DPOC, exceto para os casos em que a bronquite crônica é predominante. / The present study aims to determine if the severity of COPD can be estimated through the chart area of the sound intensities of respiratory sounds in patients with COPD. The study included 51 patients with mild, moderate, severe, very severe COPD and 7 healthy non-smokers. The breathing sounds of each participant were collected through a stethoscope adapted with a mini microphone. The method compares the areas of intensity sonic densities as a function of the frequency of COPD patients and healthy individuals. In this context, to meet the objective, a method was proposed and tested based on the combination of filtering techniques and TFTC, followed by statistical analysis, calculation of the mean, standard deviation and interpolation. The results suggest that the area of the graph of frequency-frequency sound intensity variance decreases as the severity of COPD increases, except for cases where chronic bronchitis is predominant.

Dans beaucoup de pays du monde, on observe une importante augmentation du nombre de personnes âgées vivant seules. Depuis quelques années, un nombre significatif de projets de recherche sur l’assistance aux personnes âgées ont vu le jour. La plupart de ces projets utilisent plusieurs modalités (vidéo, son, détection de chute, etc.) pour surveiller l'activité de la personne et lui permettre de communiquer naturellement avec sa maison "intelligente", et, en cas de danger, lui venir en aide au plus vite. Ce travail a été réalisé dans le cadre du projet ANR VERSO de recherche industrielle, Sweet-Home. Les objectifs du projet sont de proposer un système domotique permettant une interaction naturelle (par commande vocale et tactile) avec la maison, et procurant plus de sécurité à l'habitant par la détection des situations de détresse. Dans ce cadre, l'objectif de ce travail est de proposer des solutions pour la reconnaissance des sons de la vie courante dans un contexte réaliste. La reconnaissance du son fonctionnera en amont d'un système de Reconnaissance Automatique de la Parole. Les performances de celui-ci dépendent donc de la fiabilité de la séparation entre la parole et les autres sons. Par ailleurs, une bonne reconnaissance de certains sons, complétée par d'autres sources informations (détection de présence, détection de chute, etc.) permettrait de bien suivre les activités de la personne et de détecter ainsi les situations de danger. Dans un premier temps, nous nous sommes intéressés aux méthodes en provenance de la Reconnaissance et Vérification du Locuteur. Dans cet esprit, nous avons testé des méthodes basées sur GMM et SVM. Nous avons, en particulier, testé le noyau SVM-GSL (SVM GMM Supervector Linear Kernel) utilisé pour la classification de séquences. SVM-GSL est une combinaison de SVM et GMM et consiste à transformer une séquence de vecteurs de longueur arbitraire en un seul vecteur de très grande taille, appelé Super Vecteur, et utilisé en entrée d'un SVM. Les expérimentations ont été menées en utilisant une base de données créée localement (18 classes de sons, plus de 1000 enregistrements), puis le corpus du projet Sweet-Home, en intégrant notre système dans un système plus complet incluant la détection multi-canaux du son et la reconnaissance de la parole. Ces premières expérimentations ont toutes été réalisées en utilisant un seul type de coefficients acoustiques, les MFCC. Par la suite, nous nous sommes penchés sur l'étude d'autres familles de coefficients en vue d'en évaluer l'utilisabilité en reconnaissance des sons de l'environnement. Notre motivation fut de trouver des représentations plus simples et/ou plus efficaces que les MFCC. En utilisant 15 familles différentes de coefficients, nous avons également expérimenté deux approches pour transformer une séquence de vecteurs en un seul vecteur, à utiliser avec un SVM linéaire. Dans le première approche, on calcule un nombre fixe de coefficients statistiques qui remplaceront toute la séquence de vecteurs. La seconde approche (une des contributions de ce travail) utilise une méthode de discrétisation pour trouver, pour chaque caractéristique d'un vecteur acoustique, les meilleurs points de découpage permettant d'associer une classe donnée à un ou plusieurs intervalles de valeurs. La probabilité de la séquence est estimée par rapport à chaque intervalle. Les probabilités obtenues ainsi sont utilisées pour construire un seul vecteur qui remplacera la séquence de vecteurs acoustiques. Les résultats obtenus montrent que certaines familles de coefficients sont effectivement plus adaptées pour reconnaître certaines classes de sons. En effet, pour la plupart des classes, les meilleurs taux de reconnaissance ont été observés avec une ou plusieurs familles de coefficients différentes des MFCC. Certaines familles sont, de surcroît, moins complexes et comptent une seule caractéristique par fenêtre d'analyse contre 16 caractéristiques pour les MFCC / In many countries around the world, the number of elderly people living alone has been increasing. In the last few years, a significant number of research projects on elderly people monitoring have been launched. Most of them make use of several modalities such as video streams, sound, fall detection and so on, in order to monitor the activities of an elderly person, to supply them with a natural way to communicate with their “smart-home”, and to render assistance in case of an emergency. This work is part of the Industrial Research ANR VERSO project, Sweet-Home. The goals of the project are to propose a domotic system that enables a natural interaction (using touch and voice command) between an elderly person and their house and to provide them a higher safety level through the detection of distress situations. Thus, the goal of this work is to come up with solutions for sound recognition of daily life in a realistic context. Sound recognition will run prior to an Automatic Speech Recognition system. Therefore, the speech recognition’s performances rely on the reliability of the speech/non-speech separation. Furthermore, a good recognition of a few kinds of sounds, complemented by other sources of information (presence detection, fall detection, etc.) could allow for a better monitoring of the person's activities that leads to a better detection of dangerous situations. We first had been interested in methods from the Speaker Recognition and Verification field. As part of this, we have experimented methods based on GMM and SVM. We had particularly tested a Sequence Discriminant SVM kernel called SVM-GSL (SVM GMM Super Vector Linear Kernel). SVM-GSL is a combination of GMM and SVM whose basic idea is to map a sequence of vectors of an arbitrary length into one high dimensional vector called a Super Vector and used as an input of an SVM. Experiments had been carried out using a locally created sound database (containing 18 sound classes for over 1000 records), then using the Sweet-Home project's corpus. Our daily sounds recognition system was integrated into a more complete system that also performs a multi-channel sound detection and speech recognition. These first experiments had all been performed using one kind of acoustical coefficients, MFCC coefficients. Thereafter, we focused on the study of other families of acoustical coefficients. The aim of this study was to assess the usability of other acoustical coefficients for environmental sounds recognition. Our motivation was to find a few representations that are simpler and/or more effective than the MFCC coefficients. Using 15 different acoustical coefficients families, we have also experimented two approaches to map a sequence of vectors into one vector, usable with a linear SVM. The first approach consists of computing a set of a fixed number of statistical coefficients and use them instead of the whole sequence. The second one, which is one of the novel contributions of this work, makes use of a discretization method to find, for each feature within an acoustical vector, the best cut points that associates a given class with one or many intervals of values. The likelihood of the sequence is estimated for each interval. The obtained likelihood values are used to build one single vector that replaces the sequence of acoustical vectors. The obtained results show that a few families of coefficients are actually more appropriate to the recognition of some sound classes. For most sound classes, we noticed that the best recognition performances were obtained with one or many families other than MFCC. Moreover, a number of these families are less complex than MFCC. They are actually a one-feature per frame acoustical families, whereas MFCC coefficients contain 16 features per frame

Quantificar e qualificar o bem-estar de animais de produção, ainda é um desafio. Em qualquer avaliação de bem-estar, deve-se analisar, principalmente, a ausência de sentimentos negativos fortes, como o sofrimento, e a presença de sentimentos positivos, como o prazer. O objetivo principal dessa pesquisa foi quantificar a vocalização de suínos em grupos sob diferentes condições térmicas. Em termos de objetivos específicos foram avaliar a existência de padrões vocálicos de comunicação entre animais alojados em grupo e extrair as características acústicas dos espectros sonoros das vocalizações relacionando com as diferentes condições do micro-clima da instalação. O experimento foi realizado em uma unidade de experimentação com suínos, junto à University of Illinois (EUA), com ambiente controlado. Quatro grupos de seis leitões foram utilizados para a coleta dos dados. Foram instalados dataloggers para registrar as variáveis ambientais (T, °C e UR, %) e posterior cálculo dos índices de conforto (ITU e Entalpia do ar). Foram instalados microfones do tipo cardióide no centro geométrico de cada baia que abrigava os leitões, para registro das vocalizações. Os microfones foram conectados a um amplificador de sinais, e este a uma placa de captura dos sinais de áudio e vídeo, instalados em um computador. Para as edições dos arquivos de áudio contendo as vocalizações dos leitões, o programa Goldwave® foi utilizado na separação, e aplicação de filtros para a retirada de ruídos. Na sequência, os áudios foram analisados com auxílio do programa Sounds Analysis Pro 2011, onde foram extraídos as características acústicas. A amplitude (dB), frequência fundamental (Hz), frequência média (Hz), frequência de pico (Hz) e entropia foram utilizados para caracterização do espectro sonoro das vocalizações do grupo de leitões nas diferentes condições térmicas. O delineamento do experimento foi em blocos casualizados, com dois tratamentos, e três repetições na semana, sendo executado em duas semanas. Os dados foram amostrados para uma análise do comportamento do banco de dados de vocalização em relação aos tratamentos que foram aplicados. Os dados foram submetidos a uma análise de variância utilizando o proc GLM do SAS. Dentre os parâmetros acústicos analisados, a amplitude (dB), frequência fundamental e entropia. Os tratamentos, condição de conforto e condição de calor, apresentaram diferenças significativas, pelo teste de Tukey (p<0,05). A análise de variância mostrou diferenças no formato da onda para cada condição térmica nos diferentes períodos do dia. É possível quantificar a vocalização em grupos de suínos em diferentes condições térmicas, por intermédio da extração das características acústicas das amostras sonoras. O espectro sonoro foi extraído, indicando possíveis variações do comportamento dos leitões nas diferentes condições térmicas dentro dos períodos do dia. No entanto, a etapa de reconhecimento de padrão, ainda necessita de um banco de dados maior e mais consistente para o reconhecimento do espectro em cada condição térmica, seja por análise das imagens ou pela extração das características acústicas. Dentre as características acústicas analisadas, a amplitude (dB), frequência fundamental (Hz) e entropia das vocalizações em grupo de suínos foram significativas para expressar a condição dos animais quando em diferentes condições térmicas. / To quantify and to qualify animal well-being in livestock farms is still a challenge. To assess animal well-being, it must be analyzed, mainly, the absence of strong negative feelings, like pain, and the presence of positive feelings, like pleasure. The main objective was to quantify vocalization in a group of pigs under different thermal conditions. The specific objectives were to assess the existence of vocal pattern of communication between housing groups of pigs, and get the acoustic characteristics of the sound spectrum from the vocalizations related to the different microclimate conditions. The trial was carried out in a controlled environment experimental unit for pigs, at the University of Illinois (USA). Four groups of six pigs were used in the data collection. Dataloggers were installed to record environmental variables (T, °C and RH, %). These environmental variable were used to calculate two thermal comfort index: Enthalpy and THI. Cardioid microphones were installed to record continuous vocalizations in the geometric center of each pen where the pigs were housing. Microphones were connected to an amplifier, and this was connected to a dvr card installed in a computer to record audio and video information. For doing the sound edition in a pig vocalization database, the Goldwave® software was used to separate, and filter the files excluding background noise. In the sequence, the sounds were analyzed using the software Sounds Analysis Pro 2011, and the acoustic characteristics were extracted. Amplitude (dB), pitch (Hz), mean frequency (Hz), peak frequency (Hz) and entropy were used to characterize the sound spectrum of vocalizations of the groups of piglets in the different thermal conditions. A randomized block design was used, composed by two treatments and three repetitions in a week and executed in two weeks. Data were sampled to analyze the behavior of the databank of vocalization as a relation to the applied treatments. Data were submitted to an analysis of variance using the proc GLM of SAS. Among the studied acoustic parameters, the amplitude (dB), pitch and entropy. The treatments (comfort and heat stress conditions) presented significative differences, through Tukey\'s test (p<0,05). The analysis of variance showed differences to the wave format to each thermal condition in the different periods of the day. The quantification of vocalization of swine in groups under different thermal conditions is possible, using the extraction of acoustic characteristics from the sound samples. The sound spectrum was extracted, which indicated possible alterations in the piglets behavior in the different thermal conditions during the periods of the day. However, the stage of pattern\'s recognition still needs a larger and more consistent database to the recognition of the spectrum in each thermal condition, through image analysis or by the extraction of the acoustic characteristics. Among he analyzed acoustic characteristics, the amplitude (dB), pitch (Hz) and entropy of the vocalizations of groups of swine were significative to express the condition of the animals in different thermal conditions.

Le développement croissant des données numériques et l'explosion des accès multimédia à l'information, sont confrontés au manque d'outils automatiques efficaces. Dans ce cadre, plusieurs approches relatives à l'indexation et la structuration de la bande sonore de documents audiovisuels sont proposées. Leurs buts sont de détecter les composantes primaires telles que la parole, la musique et les sons clés (jingles, sons caractéristiques, mots clés...). Pour la classification parole/musique, trois paramètres inhabituels sont extraits : la modulation de l'entropie, la durée des segments (issue d'une segmentation automatique) et le nombre de ces segments par seconde. Les informations issues de ces trois paramètres sont ensuite fusionnées avec celle issue de la modulation de l'énergie à quatre hertz. Des expériences sur un corpus radiophonique montrent la robustesse de ces paramètres : notre système possède un taux de classification correcte supérieur à 90%. Le système est ensuite comparé, puis fusionné à un système classique basé sur des Modèles de Mélanges de lois Gaussiennes (MMG) et une analyse cepstrale. Un autre partitionnement consiste à détecter des sons clés. La sélection de candidats potentiels est effectuée en comparant la « signature » de chacun des jingles au flux de données. Ce système est simple par sa mise en œuvre mais rapide et très efficace : sur un corpus audiovisuel d'une dizaine d'heures (environ 200 jingles) aucune fausse alarme n'est présente. Il y a seulement deux omissions dans des conditions extrêmes. Les sons caractéristiques (applaudissements et rires) sont modélisés à l'aide de MMG dans le domaine spectral. Un corpus télévisuel permet de valider cette première étude par des résultats encourageants. La détection de mots clés est effectuée de manière classique : il ne s'agit pas ici d'améliorer les systèmes existants mais de se placer toujours dans un besoin de structuration. Ainsi, ces mots clés renseignent sur le type des émissions (journal, météo, documentaire...). Grâce à l'extraction de ces composantes primaires, les émissions audiovisuelles peuvent être annotées de manière automatique. Au travers de deux études, une réflexion est conduite quant à l'utilisation de ces composantes afin de trouver une structure temporelle aux documents. La première étude permet une détection d'un motif récurrent dans une collection d'émissions, dites de plateau, alors que la seconde réalise la structuration en thèmes d'un journal télévisé. Quelques pistes de réflexions sur l'apport de l'analyse vidéo sont développées et les besoins futurs sont explorés.