Les communications téléphoniques en voix sur IP souffrent de la perte de paquets causée par les problèmes d'acheminement dus aux nœuds du réseau. La perte d'un paquet de voix induit la perte d'un segment de signal de parole (généralement 10ms par paquet perdu). Face à la grande diversité des codeurs de parole, nous nous sommes intéressés dans le cadre de cette thèse à proposer une méthode de masquage de pertes de paquets générique, indépendante du codeur de parole utilisé. Ainsi, le masquage de pertes de paquets est appliqué au niveau du signal de parole reconstruit, après décodage, s'affranchissant ainsi du codeur de parole. Le système proposé repose sur une modélisation classique de type « modèles de Markov cachés » afin de suivre l'évolution acoustique de la parole. À notre connaissance, une seule étude a proposé l'utilisation des modèles de Markov cachés dans ce cadre [4]. Toutefois, Rødbro a utilisé l'utilisation de deux modèles, l'un pour la parole voisée, l'autre pour les parties non voisées, posant ainsi le problème de la distinction voisée/non voisée. Dans notre approche, un seul modèle de Markov caché est mis en œuvre. Aux paramètres classiques (10 coefficients de prédiction linéaire dans le domaine cepstral (LPCC) et dérivées premières) nous avons adjoint un nouvel indicateur continu de voisement [1, 2]. La recherche du meilleur chemin avec observations manquantes conduit à une version modifiée de l'algorithme de Viterbi pour l'estimation de ces observations. Les différentes contributions (indice de voisement, décodage acoutico-phonétique et restitution du signal) de cette thèse sont évaluées [3] en terme de taux de sur et sous segmentation, taux de reconnaissance et distances entre l'observation attendue et l'observation estimée. Nous donnons une indication de la qualité de la parole au travers d'une mesure perceptuelle : le PESQ. / Packet loss due to misrouted or delayed packets in voice over IP leads to huge voice quality degradation. Packet loss concealment algorithms try to enhance the perceptive quality of the speech. The huge variety of vocoders leads us to propose a generic framework working directly on the speech signal available after decoding. The proposed system relies on one single "hidden Markov model" to model time evolution of acoustic features. An original indicator of continuous voicing is added to conventional parameters (Linear Predictive Cepstral Coefficients) in order to handle voiced/unvoiced sound. Finding the best path with missing observations leads to one major contribution: a modified version of the Viterbi algorithm tailored for estimating missing observations. All contributions are assessed using both perceptual criteria and objective metrics.

Orientadores: Nancy Lopes Garcia, Alexsandro Giacomo Grimbert Gallo / Tese (doutorado) - Universidade Estadual de Campinas, Instituto de Matemática Estatística e Computação Científica / Made available in DSpace on 2018-08-24T12:54:22Z (GMT). No. of bitstreams: 1 Carvalho_WalterAugustoFonsecade_D.pdf: 1034671 bytes, checksum: 25dd72305f343655bedfde62a785a259 (MD5) Previous issue date: 2014 / Resumo: Esta tese é dedicada ao estudo dos processos de renovação binários obtidos como agregação de estados a partir de processos Markovianos com alfabeto finito. Na primeira parte, utilizamos uma abordagem matricial para obter condições sob as quais o processo agregado pertence a cada uma das seguintes classes: (1) Markoviano de ordem finita, (2) processo de ordem infinita com probabilidades de transição contínuas, (3) processo Gibbsiano. A segunda parte trata da distância d entre processos de renovação binários. Obtivemos condições sob as quais esta distância pode ser atingida entre tais processos / Abstract: This thesis is devoted to the study of binary renewal processes obtained as aggregation of states from Markov processes with finite alphabet. In the rst part, we use a matrix approach to obtain conditions under which the aggregated process belongs to each of the following classes: (1) Markov of finite order, (2) process of infinite order with continuous transition probabilities, (3) Gibbsian process. The second part deals with the distance d between binary renewal processes. We obtain conditions under which this distance can be achieved between these processes / Doutorado / Estatistica / Doutor em Estatística

Communication underwater is challenging because of the inherent characteristics of the media. First, common radio frequency (RF) signals utilized in wireless communications cannot be used under water. RF signals are attenuated in such as way that RF communication underwater is restricted to very few meters. As a result, acoustic-based communication is utilized for underwater communications; however, acoustic communication has its own limitations. For example, the speed of sound is five orders of magnitude lower than the speed of light, meaning that communications under water experience long propagation delays, even in short distances. Long propagation delays impose strong challenges in the design of Data Link Layer (DLL) protocols. The underwater communication channel is noisy, too. The bit error rate (BER) can also change depending on depth and other factors, and the errors are correlated, like in wireless communications. As in wireless communications, transducers for acoustic communication are half duplex, limiting the application of well-known detection mechanisms in Medium Access Control (MAC) layer protocols. Further, known problems like the hidden and exposed terminal problem also occur here. All these aspects together make the underwater communication channel to have the worst characteristics of all other known channels. Because of these reasons, underwater scenarios are complicated to implement, especially when they have underwater autonomous vehicles exchanging information among them. This dissertation proposes data link layer protocols in support of swarming of underwater autonomous vehicles that deal with the problems mentioned before. At the MAC sublayer, a MAC protocol called 2MAC is introduced. 2MAC improves the throughput of the network using the multichannel capabilities of OFDM at the physical layer. At the logical link control sublayer, a protocol named SW-MER is proposed. SW-MER improves the throughput and the reliability combining the well-known stop and wait protocol with the sliding window strategy, and using an exponential retransmission strategy to deal with errors. 2MAC and SW-MER are evaluated and compared with other protocols using analytical means and simulations. The results show that by using 2MAC, packet collisions are considerably reduced and the throughput improved. In addition, the use of SW-MER improves the packet delivery ratio over existing mechanisms. In general, the evaluations indicate that the proposed data link layer protocols offer a better communication alternative for underwater autonomous vehicles (UAV) than traditional protocols.

La restauration statistique non-supervisée de signaux admet d'innombrables applications dans les domaines les plus divers comme économie, santé, traitement du signal, ... Un des problèmes de base, qui est au coeur de cette thèse, est d'estimer une séquence cachée (Xn)1:N à partir d'une séquence observée (Yn)1:N. Ces séquences sont considérées comme réalisations, respectivement, des processus (Xn)1:N et (Yn)1:N. Plusieurs techniques ont été développées pour résoudre ce problème. Le modèle parmi le plus répandu pour le traiter est le modèle dit "modèle de Markov caché" (MMC). Plusieurs extensions de ces modèles ont été proposées depuis 2000. Dans les modèles de Markov couples (MMCouples), le couple (X, Y) est markovien, ce qui implique que p(x|y) est également markovienne (alors que p(x) ne l'est plus nécessairement), ce qui permet les mêmes traitements que dans les MMC. Plus récemment (2002) les MMCouples ont été étendus aux "modèles de Markov triplet" (MMT), dans lesquels on introduit un processus auxiliaire U et suppose que le triplet T = (X, U, Y) est markovien. Là encore il est possible, dans un cadre plus général que celui des MMCouples, d'effectuer des traitements avec une complexité raisonnable. L'objectif de cette thèse est de proposer des nouvelles modélisations faisant partie des MMT et d'étudier leur pertinence et leur intérêt. Nous proposons deux types de nouveautés: (i) Lorsque la chaîne cachée est discrète et lorsque le couple (X, Y) n'est pas stationnaire, avec un nombre fini de "sauts" aléatoires dans les paramètres, l'utilisation récente des MMT dans lesquels les sauts sont modélisés par un processus discret U a donné des résultats très convaincants (Lanchantin, 2006). Notre première idée est d'utiliser cette démarche avec un processus U continu, qui modéliserait des non-stationnarités "continues" de(X, Y). Nous proposons des chaînes et des champs triplets et présentons quelques expériences. Les résultats obtenus dans la modélisation de la non-stationnarité continue semblent moins intéressants que dans le cas discret. Cependant, les nouveaux modèles peuvent présenter d'autres intérêts; en particulier, ils semblent plus efficaces que les modèles "chaînes de Markov cachées" classiques lorsque le bruit est corrélé; (ii) Soit un MMT T = (X, U, Y) tel que X et Y sont continu et U est discret fini. Nous sommes en présence du problème de filtrage, ou du lissage, avec des sauts aléatoires. Dans les modélisations classiques le couple caché (X, U) est markovien mais le couple (U, Y) ne l'est pas, ce qui est à l'origine de l'impossibilité des calculs exacts avec une complexité linéaire en temps. Il est alors nécessaire de faire appel à diverses méthodes approximatives, dont celles utilisant le filtrage particulaire sont parmi les plus utilisées. Dans des modèles MMT récents le couple caché (X, U) n'est pas nécessairement markovien, mais le couple (U, Y) l'est, ce qui permet des traitements exacts avec une complexité raisonnable (Pieczynski 2009). Notre deuxième idée est d'étendre ces derniers modèles aux triplets T = (X, U, Y) dans lesquels les couples (U, Y) sont "partiellement" de Markov. Un tel couple (U, Y) n'est pas de Markov mais U est de Markov conditionnellement àY. Nous obtenons un modèle T = (X, U, Y) plus général, qui n'est plus de Markov, dans lequel le filtrage et le lissage exacts sont possibles avec une complexité linéaire en temps. Quelques premières simulations montrent l'intérêt des nouvelles modélisations en lissage en présence des sauts. / Statistical unsupervised restoration of signal can be applied in many fields such as economy, health, signal processing, meteorology, finance, biology, reliability, transportation, environment, ... the main problem treated in this thesis is to estimate a hidden sequence (Xn)1:N based on an observed sequence (Yn)1:N. In Probabilistic treatment of the problem in these sequences are considered as accomplishments of respectively, process (Xn)1:N and (Yn)1:N. Several techniques based on statistical methods have been developed to solve this problem. The most common model known for this kind of problems is the “hidden Markov model”. In this model we assume that the hidden process X is Markovian and laws p(y|x) of Y are conditional on X are sufficiently simple so that the law p(x|y) is also Markovian, this property is necessary for treatment. Many Extensions of these models have been proposed since 2000. In Markov models couples (MMCouples), more general than the MMC, the pair (X,Y) is Markovian), implying that p(x|y) is also Markovian (when p(x) is not necessarily markovian), which allows the same treatment as in MMC. More recently (2002), were extended to MMCouples are extended to Markov models Triplet (MMT), in which we introduce an auxiliary process U and suppose that the triple T=(X,U,Y) is Markovian. It’s again possible, in a general case of MMCouples, to perform treatments with a reasonable complexity. The objective of this thesis is to propose new modeling of MMT and to investigate their relevance and interest. We offer two types of innovations: (i) When the hidden system is discrete and when the couple (X,Y) is not stationary with a finite number of random “jumps” in parameters, the recent use of MMT where the jumps are modelized by a discrete process U has been very convincing (Lanchantin, 2006). Our first idea is to use this approach with a continuous process U, which models non-steady "continuous" of (X,Y). We propose chains and triplet fields and present some experiments. The results obtained in the modeling of non-stationarity still seem less interesting that in the discrete case. However, new models may have other interests, in particular, they seem more efficient than “classic hidden Markov” when the noise is correlated; (ii) Considering an MMT T=(X,U,Y) such that X and Y are continuous and U is discrete finite. We are dealing with a problem of filtering, or smoothing, with random jumps. In classic modelling the hidden pair (X,U) is Markovian, but the pair (U,Y) is not, what is the cause of the impossibility of Exact calculations with time linear complexity. It is then necessary to use various approximate methods, including methods using particle filtering which are the most common. In recent models MMT the hidden pair (X,U) is not necessarily Markovian, but the pair (U,Y) is Markovian, which allows accurate treatment with a reasonable complexity (Pieczynski 2009). Our second idea is to extend these models to triplets T=(X,U,Y) where the pairs (U,Y) are "partially" Markovian. Such a pair (U,Y) is not Markovian but U is conditionally Markovian on Y. We have in result a model with general model T=(X,U,Y) , which is no more Markovian, wherein the filtering and smoothing are accurate possible with time linear complexity. Some preliminary Simulations show the importance of new smoothing models with of jumps.

Dans cette thèse, j'étudie les propriétés théoriques des modèles de Markov cachés non paramétriques. Le choix de modèles non paramétriques permet d'éviter les pertes de performance liées à un mauvais choix de paramétrisation, d'où un récent intérêt dans les applications. Dans une première partie, je m'intéresse à l'estimation du nombre d'états cachés. J'y introduis deux estimateurs consistants : le premier fondé sur un critère des moindres carrés pénalisés, le second sur une méthode spectrale. Une fois l'ordre connu, il est possible d'estimer les autres paramètres. Dans une deuxième partie, je considère deux estimateurs adaptatifs des lois d'émission, c'est-à-dire capables de s'adapter à leur régularité. Contrairement aux méthodes existantes, ces estimateurs s'adaptent à la régularité de chaque loi au lieu de s'adapter seulement à la pire régularité. Dans une troisième partie, je me place dans le cadre mal spécifié, c'est-à-dire lorsque les observations sont générées par une loi qui peut ne pas être un modèle de Markov caché. J'établis un contrôle de l'erreur de prédiction de l'estimateur du maximum de vraisemblance sous des conditions générales d'oubli et de mélange de la vraie loi. Enfin, j'introduis une variante non homogène des modèles de Markov cachés : les modèles de Markov cachés avec tendances, et montre la consistance de l'estimateur du maximum de vraisemblance. / During my PhD, I have been interested in theoretical properties of nonparametric hidden Markov models. Nonparametric models avoid the loss of performance coming from an inappropriate choice of parametrization, hence a recent interest in applications. In a first part, I have been interested in estimating the number of hidden states. I introduce two consistent estimators: the first one is based on a penalized least squares criterion, and the second one on a spectral method. Once the order is known, it is possible to estimate the other parameters. In a second part, I consider two adaptive estimators of the emission distributions. Adaptivity means that their rate of convergence adapts to the regularity of the target distribution. Contrary to existing methods, these estimators adapt to the regularity of each distribution instead of only the worst regularity. The third part is focussed on the misspecified setting, that is when the observations may not come from a hidden Markov model. I control of the prediction error of the maximum likelihood estimator when the true distribution satisfies general forgetting and mixing assumptions. Finally, I introduce a nonhomogeneous variant of hidden Markov models : hidden Markov models with trends, and show that the maximum likelihood estimators of such models is consistent.

京都大学 / 新制・課程博士 / 博士(情報学) / 甲第23311号 / 情博第747号 / 新制||情||128(附属図書館) / 京都大学大学院情報学研究科知能情報学専攻 / (主査)准教授 吉井 和佳, 教授 河原 達也, 教授 西野 恒, 教授 鹿島 久嗣 / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

In economic geography, a main research focus is on the relationship between innovation and space. Based on the observations of spatially clustered innovative activities in urban environments, a central argument is that the exchange of innovation-relevant knowledge across firms and other actors as well as the accompanying learning processes are promoted through geographical proximity. Agglomerations are said to offer multiple advantages, e.g. through frequent face-to-face contacts and opportunities for intense collaboration, a common labour pool and shared institutions. From this perspective, a location in large urban environments is beneficial for innovation, while by contrast, being located outside of agglomerations is not (Fitjar & Rodríguez‐Pose 2019). This dissertation relates to growing debates around the unease with the seemingly accepted truths about the strong connection of agglomerations and firm innovation. The research field has been found to be urban-biased, focussed on cases of successful regions and delivering multiple explanations of their success – while neglecting innovations occurring outside of agglomerations and largely portraying such regions and their actors as disadvantaged (Shearmur 2017). Within the emergent studies of innovation in peripheral contexts, some specifics have been proposed based on empirical studies, but a coherent theoretical framework is missing (e.g. Eder 2019). Against this background, this dissertation aims to contribute to a better understanding of innovation from a peripheral perspective based on comparison of firms by location. It explores knowledge creation processes and innovation activities of Hidden Champions in Germany. These highly innovative and globally active manufacturing firms are quite evenly distributed across Germany. By exploring practices and strategies of these firms towards innovation from a comparative perspective, this study investigates the following overarching research question: • What are the characteristics and main drivers of innovation outside of agglomerations and in how far do these differ from those inside agglomerations? This research builds on relational perspectives on economic action by adopting a geographical lens (Bathelt & Glückler 2003, Yeung 2005). It focusses on actors and how they act and interact in space without privileging any spatial scale or mechanism such as local interaction. Spaces and places are not perceived as territorially bounded units but as contexts in which actors organise their often multi-scalar relations. Following these basic theoretical positions, several concepts and approaches are utilised to develop a detailed understanding of firm innovation in space. While notions of slow innovation and the reliance on firm-internal capabilities point towards reduced interaction requirements especially of firms in peripheral regions to innovate (e.g. Shearmur 2015), the proximity approach (Boschma 2005) and the notion of global pipelines (Bathelt et al. 2004) highlight that geographical proximity is not a necessary precondition for interactive knowledge creation and innovation. Based on these conceptual perspectives and linked to the goal of understanding key mechanisms of innovation from a peripheral perspective, the guiding research question is complemented by the following sub-questions: • How and where do firms gain relevant knowledge for their innovation activities? • Which role do internal capabilities as well as external efforts towards innovation play and how do firms assess both dimensions? • What is the role of the firms’ location, especially regarding local options of knowledge creation? Based on a mixed method research design including a quantitative survey among the Hidden Champions and qualitative interviews with representatives of these firms, three dimensions relevant to the understanding of knowledge creation and innovation are considered for the empirical analyses: practices of knowledge creation at the individual level, strategic approaches towards innovation at the organisational level and the socio-spatial contexts in which knowledge creation processes and innovation are organised. The overarching finding of this dissertation is that firms like Hidden Champions largely follow the same principles to innovate independently from their location. Thereby, the results highlight the commonalities of firm innovation in urban and peripheral contexts instead of pointing towards major limitations or specificities of innovation in more peripheral regions. With taking the firm at the centre of analysis, this research demonstrates that regional economic pre-conditions do not necessarily relate to the capacities of firms to innovate. Neither do investigated firms located inside agglomera-tions largely capitalise on options of local interaction, nor do firms located outside of agglomerations face major disadvantages due to the lack of local options to source knowledge and interact. Instead and irrespectively of their location, firms strategically engage in various firm-internal and -external options to gain knowledge and have the capacities to shape their multi-scalar socio-spatial contexts for knowledge creation according to their needs. The results underline that intense interaction with externals is only one out of many options for firms to gain knowledge. Next to strong internal capabilities, non-interactive modes of knowledge sourcing via desk research, for instance, and more informal modes of knowledge creation via the participation in trade fairs have been identified as integral parts of firms’ innovation activities. This study suggests that such forms of ‘selective openness’ have not been sufficiently addressed in the research field so far. Selective openness not only stresses the strategic approaches of firms towards innovation but also the variety of options for knowledge creation which are usually not reliant on or connected to the regional contexts of firms. Moreover, this study finds that the connection between innovation and agglomeration is not as clear as suggested by urban perspectives, at least for the German context. Rather, much of the urban/rural and core/periphery divide seems to be discursively produced. This dissertation complements existing research on the geographies of innovation by providing insights from a peripheral view on innovation. It contributes to current debates on urban-biased perspectives and the dichotomous representation of firm innovation in urban and peripheral contexts. Based on the empirical results, it proposes a more differentiated view on openness and suggests recommendations for place-based policies towards regional development and innovation.:Summary 9 1. Introduction 11 1.1. Research objectives and questions 13 1.2. Hidden Champions in Germany 16 1.3. Structure of the dissertation 18 2. Re-thinking the geographies of firm innovation 21 2.1. Firms and innovation 22 2.1.1. Understanding firm innovation 24 2.1.2. Coordination of internal and external knowledge for innovation 25 2.1.3. Varieties of open innovation 29 2.2. Geographies and innovation 33 2.2.1. Beyond territorial innovation 34 2.2.2. Questioning the status quo: urban bias and the periphery label 41 2.2.3. Current understandings of innovation outside of agglomerations 45 2.3. Conceptual framework 51 2.3.1. Positioning the own research 51 2.3.2. A relational perspective on economic processes in space 55 2.3.3. Beyond dualistic conceptualisations of innovation and space 59 3. Methodological approach 66 3.1. Critical realism as the basic ontological and epistemological perspective 66 3.1.1. Basics notions of critical realism 67 3.1.2. Implications for research methodologies 68 3.2. Research design 69 3.2.1. Multi-dimensional comparative approach 70 3.2.2. Triangulation 72 3.2.3. Comparison 73 3.3. Empirical and analytical methods and proceedings 75 3.3.1. Development of a database of Hidden Champions in Germany 75 3.3.2. Quantitative survey 81 3.3.3. Semi-structured interviews 85 4. Patterns and socio-spatial contexts of firm innovation – Quantitative results 90 4.1. The spatial distribution of Hidden Champions in Germany 90 4.2. Firm characteristics and innovation patterns 93 4.2.1. Organisational and spatial aspects of firm structures 93 4.2.2. Innovation activities 94 4.2.3. Information sources and collaboration 96 4.3. Comparison of the firms by location 98 4.4. Types of innovative firms 101 4.4.1. Approach, implementation and results of the cluster analysis 102 4.4.2. Types of innovators and their locations 107 4.5. Interim results and arising questions 110 5. Strategies and practices towards knowledge creation and innovation – Qualitative results 113 5.1. Firm profiles 116 5.1.1. Firms located outside of agglomerations 116 5.1.2. Firms located inside agglomerations 120 5.2. The global integration of firms 124 5.2.1. Firms, their niche markets and ways of internationalisation 124 5.2.2. Knowledge creation strategies and the role of geography 127 5.2.3. Organisational structures to secure the global reach 134 5.2.4. The significance of innovation and high quality 136 5.3. Strategies towards innovation 137 5.3.1. Corporate culture and ambition 138 5.3.2. Key internal and external drivers of innovation 139 5.3.3. The temporal dimension of innovation 142 5.4. Firm-internal organisation of innovation activities 144 5.4.1. Main challenges 145 5.4.2. The headquarters as the central corporate unit 148 5.4.3. Internationalisation of knowledge creation and innovation 150 5.5. The external dimension of innovation activities 155 5.5.1. Access to external sources of knowledge 155 5.5.2. Collaboration with partners 158 5.5.3. Evaluation of the external dimension for innovation 164 5.6. The role of the regional contexts for firm innovation 165 5.6.1. The perception of regional contexts at the headquarters 166 5.6.2. The regional embeddedness of firms 171 5.6.3. Evaluation of the regional dimension 175 5.7. Summary of findings and comparison with the quantitative results 176 6. Firm innovation beyond agglomeration – Discussion of results 180 6.1. Globally dispersed knowledge dynamics and secrecy 180 6.2. The processual character of innovation activities 185 6.3. The role of the places and spaces for firm innovation 191 7. Main findings, conclusions and outlook 196 7.1. Summary of main findings and contributions of the research 196 7.2. Conclusions and policy recommendations 200 7.3. Reflections on the study and avenues for future research 202 Appendices 206 References 220

Main purpose of the thesis is to study the processes and methods of isolated words recognition. In the theoretical part a basic principals are explained. The practical part is about the program creating using these principles in practice. For isolated words recognition Hidden Markov Models (HMM) are used, for obtaining decision symptoms cepstral analysis is chosen.

This masters thesis describes possibilities and principles of gesture-based computer interface. The work describes general approaches for gesture control.  It also deals with implementation of the selected detection method of the hands and fingers using depth maps loaded form Kinect sensor. The implementation also deals with gesture recognition using hidden Markov models. For demonstration purposes there is also described implementation of a simple photo viewer that uses developed gesture-based computer interface. The work also focuses on quality testing and accuracy evaluation for selected gesture recognizer.

The thesis titled "The body of the other. The erotics as learning content in Art education." have character of an exploration probe. It focuses on erotism in environment of educational institutions. This work deals with the body and its erotic contents in art education. It seeks to clarify the concept of erotica. This work seeks various overhangs of erotica into philosophy, advertising, school, personal and public life. This thesis is linked to the teaching of erotic theme and with the issues of integration of eroticism in lessons of art education. The aim is to determine how are the children / students on this topic sensitive. All the text is supplemented by authentic testimonies of students, teachers and parents related to the topic of erotica in school.