Tesis sobre el tema "Traitement automatique du son"
Crea una cita precisa en los estilos APA, MLA, Chicago, Harvard y otros
Consulte los 50 mejores tesis para su investigación sobre el tema "Traitement automatique du son".
Junto a cada fuente en la lista de referencias hay un botón "Agregar a la bibliografía". Pulsa este botón, y generaremos automáticamente la referencia bibliográfica para la obra elegida en el estilo de cita que necesites: APA, MLA, Harvard, Vancouver, Chicago, etc.
También puede descargar el texto completo de la publicación académica en formato pdf y leer en línea su resumen siempre que esté disponible en los metadatos.
Explore tesis sobre una amplia variedad de disciplinas y organice su bibliografía correctamente.
Emiya, Valentin. "Transcription automatique de la musique de piano". Phd thesis, Télécom ParisTech, 2008. http://pastel.archives-ouvertes.fr/pastel-00004867.
Texto completoGianola, Lucie. "Aspects textuels de la procédure judiciaire exploitée en analyse criminelle et perspectives pour son traitement automatique". Thesis, CY Cergy Paris Université, 2020. http://www.theses.fr/2020CYUN1065.
Texto completoCriminal analysis is a discipline that supports investigations practiced within the National Gendarmerie. It is based on the use of the documents compiled in the judicial procedure file (witness interviews, search warrants, expert reports, phone and bank data, etc.) to synthesize the information collected and to propose a new understanding of the facts examined. While criminal analysis uses data visualization software (i. e. IBM Analyst’s Notebook) to display the hypotheses formulated, the digital and textual management of the file documents is entirely manual. However, criminal analysis relies on entities to formalize its practice.The presentation of the research context details the practice of criminal analysis as well as the constitution of judicial procedure files as textual corpora.We then propose perspectives for the adaptation of natural language processing(NLP) and information extraction methods to the case study, including a comparison of the concepts of entity in criminal analysis and named entity in NLP. This comparison is done on the conceptual and linguistic plans. A first approach to the detection of entities in witness interviews is presented.Finally, since textual genre is a parameter to be taken into account when applying automatic processing to text, we develop a structure of the « legal » textual genre into discourse, genres, and sub-genres through a textometric study aimed at characterizing different types of texts (including witness interviews) produced by the field of justice
Vercruysse, Michel. "Mesure en temps réel de l'orthogonalité des fils de trame d'un tissu en défilement et son traitement automatique". Lille 1, 1991. http://www.theses.fr/1991LIL10034.
Texto completoOuldja, Hadj. "Réalisation d'une interface en langage naturel et son application à l'enseignement assisté par ordinateur". Paris 6, 1988. http://www.theses.fr/1988PA066456.
Texto completoFedosov, Andrey. "Assistance automatique au mixage de microphones d'appoint dans une prise de son HOA". Thesis, Brest, 2017. http://www.theses.fr/2017BRES0016/document.
Texto completoIn this thesis we study the problematic of a sound engineer mixing HOA (Higher Order Ambisonics) and spot microphones, namely the estimation of parameters such as delay, position and gain of acoustic sources associated to spot microphones. We present a typical workflow in this context, and also propose an algorithm extracting parameters that could be applied to the spot microphone signals. This mixing assistance allows sound engineers to easily work with HOA 3D sound and to concentrate on artistic choices (fine adjustments of the parameters), by avoiding a low-added value work (coarse parameter estimation). The robustness of the estimators is evaluated on recorded and artificial sound scenes, with different degrees of complexity in terms of number of sources and acoustic conditions (reverberation, effect of real microphone encoding, …). We also provide performance evaluations, based on both sound scene simulations and real recordings, showing encouraging results along with actual limits, and conclude on perspectives
Perlerin, Vincent. "Sémantique légère pour le document : assistance personnalisée pour l'accès au document et l'exploration de son contenu". Caen, 2004. http://www.theses.fr/2004CAEN2048.
Texto completoLesage, Sylvain Bimbot Frédéric. "Apprentissage de dictionnaires structurés pour la modélisation parcimonieuse des signaux multicanaux". [S.l.] : [s.n.], 2007. ftp://ftp.irisa.fr/techreports/theses/2007/lesage.pdf.
Texto completoLiuni, Marco. "Adaptation Automatique de la Résolution pour l'Analyse et la Synthèse du Signal Audio". Phd thesis, Université Pierre et Marie Curie - Paris VI, 2012. http://tel.archives-ouvertes.fr/tel-00773550.
Texto completoCara, Hervé. "Conception d'un dispositif pour la détection automatique des premières variations du niveau de vigilance du conducteur au volant de son véhicule : capteur non-contraignant et électronique associée". Vandoeuvre-les-Nancy, INPL, 1992. http://www.theses.fr/1992INPL010N.
Texto completoAt the present time, there is no strainless and reliable mean to automatically detect the first variations of vigilance- state of a vehicule driver. This study is based upon the determination of the physiological parameter (breathing rhythm regularity) to predict sleeping one or two minutes before it occurs. Tests in a leepinglaboratory have pointed out that the EEG activity, during the early sleeping phase is characterized by a breathing rhythm regularization. Besides, this study deals with aH associated electronics of the data acquisition and processing device to seize the signal of thoracic impedance criterions : sens or, useful signal and detection criterions. After that, this report presents the results of the validation tests of detection device and the tests in real condition
Gauthier, Elodie. "Collecter, Transcrire, Analyser : quand la machine assiste le linguiste dans son travail de terrain". Thesis, Université Grenoble Alpes (ComUE), 2018. http://www.theses.fr/2018GREAM011/document.
Texto completoIn the last few decades, many scientists were concerned with the fast extinction of languages. Faced with this alarming decline of the world's linguistic heritage, action is urgently needed to enable fieldwork linguists, at least, to document languages by providing them innovative collection tools and to enable them to describe these languages. Machine assistance might be interesting to help them in such a task.This is what we propose in this work, focusing on three pillars of the linguistic fieldwork: collection, transcription and analysis.Recordings are essential, since they are the source material, the starting point of the descriptive work. Speech recording is also a valuable object for the documentation of the language.The growing proliferation of smartphones and other interactive voice mobile devices offer new opportunities for fieldwork linguists and researchers in language documentation. Field recordings should also include ethnolinguistic material which is particularly valuable to document traditions and way of living. However, large data collections require well organized repositories to access the content, with efficient file naming and metadata conventions.Thus, we have developed LIG-AIKUMA, a free Android app running on various mobile phones and tablets. The app aims to record speech for language documentation, over an innovative way.It includes a smart generation and handling of speaker metadata as well as respeaking and parallel audio data mapping.LIG-AIKUMA proposes a range of different speech collection modes (recording, respeaking, translation and elicitation) and offers the possibility to share recordings between users. Through these modes, parallel corpora are built such as "under-resourced speech - well-resourced speech", "speech - image", "speech - video", which are also of a great interest for speech technologies, especially for unsupervised learning.After the data collection step, the fieldwork linguist transcribes these data. Nonetheless, it can not be done -currently- on the whole collection, since the task is tedious and time-consuming.We propose to use automatic techniques to help the fieldwork linguist to take advantage of all his speech collection. Along these lines, automatic speech recognition (ASR) is a way to produce transcripts of the recordings, with a decent quality.Once the transcripts are obtained (and corrected), the linguist can analyze his data. In order to analyze the whole collection collected, we consider the use of forced alignment methods. We demonstrate that such techniques can lead to fine evaluation of linguistic features. In return, we show that modeling specific features may lead to improvements of the ASR systems
Ratajczak, Rémi. "Analyse automatique d'images aériennes historiques : application à une étude épidémiologique". Thesis, Lyon, 2020. http://www.theses.fr/2020LYSE2063.
Texto completoThis thesis, co-funded by the ADEME, takes place in the context of a collaboration between the LIRIS laboratory and the Centre Léon Bérard as part of the TESTIS epidemiological study. The TESTIS study aims to estimate the impact of pesticides on the development of germ cell tumor of testicular cancer. As this disease has a long development time, it is necessary to have access to data dating back to the birth of the subjects. In the case of TESTIS, the oldest subjects were born in the early 1970s. In order to take into account individual residential exposures to pesticides spread by winds, the Centre Léon Bérard has developed a metric based on land use around dwellings. Unfortunately no land use database before 1990 is sufficiently accurate to be used. In order to obtain this information, the geomatics specialists at the Centre Léon Bérard are tasked with photo-interpreting historical aerial images in grayscale. This manual process is particularly long and tedious. Therefore, the use of automatic or semi-automatic methods has been suggested. The objective of this thesis is to develop algorithms to help geomatics specialists obtain land cover maps in a reasonable time. For that, we were interested in the use of texture classification methods that we have integrated into an annotation assistance software. This software is currently used in the TESTIS study. We then put our focus on the development of unsupervised colorization methods to provide alternative visualizations of the historical aerial images. This work also led us to study the interest of the artificially generated colors for land use classification. Finally, we sought to improve the land use maps generated by our software through post-processing methods, paving the way for the development of more efficient pipelines
Fourer, Dominique. "Approche informée pour l’analyse du son et de la musique". Thesis, Bordeaux 1, 2013. http://www.theses.fr/2013BOR14973/document.
Texto completoIn the field of audio signal processing, analysis is an essential step which allows interactions with existing signals. In fact, the quality of transformed or synthesized audio signals depends on the accuracy over the estimated model parameters. However, theoretical limits exist and show that the best accuracy which can be reached by a classic estimator can be insufficient for the most demanding applications (e.g. active listening of music). The work which is developed in this thesis revisits well known audio analysis problems like spectral analysis, automatic transcription of music and audio sources separation using the novel ``informed'' approach. This approach takes advantage of a specific configuration where the parameters of the elementary signals which compose a mixture are known before the mixing process. Using the tools which are proposed in this thesis, the minimal side information is computed and transmitted with the mixture signal. This allows any kind of transformation of the mixture signal with a constraint over the resulting quality. When the compatibility with existing audio formats is required, the side information is embedded directly into the analyzed audio signal using a watermarking technique. This work describes several theoretical and practical aspects of audio signal processing. We show that a classic estimator combined with the sufficient side information can obtain better performances than classic approaches (classic estimation or pure coding)
Doucy, Jérémie. "Méthodologie pour l’orchestration sémantique de services, application au traitement de documents multimédia". Thesis, Rouen, INSA, 2011. http://www.theses.fr/2011ISAM0014.
Texto completoAfter a complete state of the art we detailed our semantic services approach which uses an innovative method for services composition: processing chains patterns. Our approach is composed on an hybrid semantic servicers registry which propose different levels of matching between services, some composition rules when the matching phase failde and an execution engine which is able to dynamically resolve and com^pose services. In order to solve the service regitry population issue, we have designed an upper ontology, which enables links between a service taxonomy class with a semantically annotated abstract service. Finally, we have evaluated our prototype using real processing chains used by Cassidian platforms
Kaddah, Wissam. "Apports de nouveaux outils de traitement d'images et de programmation pour le relevé automatique de dégradations sur chaussées". Thesis, Brest, 2018. http://www.theses.fr/2018BRES0102/document.
Texto completoThe road network is subject to degradations due to traffic and weather conditions. The detection of surface defects within pavement images is used to evaluate the road network and to schedule the necessary maintenance operations. The goal of this thesis is to develop unsupervised processing techniques for the analysis of 2D and 3D pavement images, which originate from imaging systems operating in the field of road engineering. We focus on the detection of road marking damage and the detection of cracks on the pavement. In the context of road marking, our objective is to realize an algorithm for detecting, recognizing, geo-locating and monitoring the wearing conditions of road marking using a panoramic imaging system. The performed image processing uses a color segmentation method to facilitate the extraction phase of the road marking zones. Then, an inverse perspective technique is applied to ease the identification of detected objects.The wearing conditions of road marking is established from the variations in the geometric (length, width, etc.) and colorimetric (white color level) characteristics of the objects identified in the image.In the context of road crack detection, our aspiration is the automatic segmentation of cracks within pavement images, assuming that they represent fine and dark features in the image. Among the many existing methods, our chosen approaches follow a classical scheme composed of three main phases, namely, a pre-processing phase to reduce the amount of information to be processed in the image, a processing phase to extract the points having a high likelihood of belonging to a crack on the road and a post-processing phase to estimate the severity and the damage level of the pavement. The performances of our proposed algorithms are evaluated on 2D and 3D real images, coming from 3 types of existing imaging devices for road engineering (VIAPIX®, LCMS and Aigle-RN)
Dufour, Olivier. "Reconnaissance automatique de sons d'oiseaux et d'insectes". Thesis, La Réunion, 2016. http://www.theses.fr/2016LARE0005.
Texto completoThe present manuscript deals with computer science applied to ecology. The main objective was to assembly algorithms able to analyse acoustic recordings and automatically detect, list and count sounds of insects, amphibiansand birds. We tested a non exhaustive list of audio features and classifiers to (first part) organize and participate to three international challenges of automatic regnotion of animal's sounds and (second part) build a automatic and passive acoustic monitoring of two species of pelagic seabirds on the Reunion island
Pasquier, David. "Imagerie par Résonance Magnétique et radiothérapie conformationnelle : caractérisation de l'Imagerie par Résonance Magnétique pour son utilisation dans l'établissement des plans de traitement en radiothérapie conformationnelle : développement et évaluation d'un outil de délinéation automatique et semi-automatique des volumes d'intérêt pour la radiothérapie conformationnelle du cancer prostatique". Lille 2, 2006. http://www.theses.fr/2006LIL2S045.
Texto completoRadiotherpy is a curative treatment of malignant tumours. Radiotherapy techniques considerably evolved last years with the increasing integration of medical images in conformal radiotherapy. This technique makes it possible to elaborate a complex ballistics conforming to target volume ans sparing healthy tissues. The examination currently used to delineate volumes of interest is Computed Tomography (CT), on account of its geometrical precision and the information that it provides on electronic densities needed to dose calculation. Magnetic Resonance Imaging (MRI) ensures a more precise delineation of target volumes in many locations, such as pelvis and brain. For pelvic tumours, the use of MRI needs image registration, which complicates treatment planning and poses the problem of the lack of in vivo standard method of validation. The obstacles in the use of MRI alone on treatment planning were evaluated. Neither geometrical distorsion linked with the system and the patient nor the lack of information on electronic densities represent stumbling obstacles. Distortion remained low even in edge of large field of view on medern machines. The assignment of electronic densities to bone structures and soft tissues in MR images permitted to obtain equivalent dosimetry to that carried out on the original CT, with a good reproducibility and homogeneous distribution within target volume. The assignment of electronic densities could not be carried out using 20 MV photons and suitable ballistics. The development of Image Guided Radiotherapy could facilitate the use of MRI alone in treatment planning. Target volumes and organ at risk delineation is a time consuming task in radiotherapy planning. We took part in the development and evaluated a method of automatic and semi automatic delineation of volumes of interst from MRI images for prostate cancer radiotherapy. For prostate and organ at risk automatic delineation an organ model-based method and a seeded region growing method were used respectively. Our results are reproducible with minimal repercussion on dosimetry
Durrieu, Jean-Louis. "Transcription et séparation automatique de la mélodie principale dans les signaux de musique polyphoniques". Phd thesis, Télécom ParisTech, 2010. http://pastel.archives-ouvertes.fr/pastel-00006123.
Texto completoDurrieu, Jean-Louis. "Transcription et séparation automatique de la mélodie principale dans les signaux de musique polyphoniques". Phd thesis, Paris, Télécom ParisTech, 2010. https://pastel.hal.science/pastel-00006123.
Texto completoWe propose to address the problem of melody extraction along with the monaural lead instrument and accompaniment separation problem. The first task is related to Music Information Retrieval (MIR), since it aims at indexing the audio music signals with their melody. The separation problem is related to Blind Audio Source Separation (BASS), as it aims at breaking an audio mixture into several source tracks. Leading instrument source separation and main melody extraction are addressed within a unified framework. The lead instrument is modelled thanks to a source/filter production model. Its signal is generated by two hidden states, the filter state and the source state. The proposed signal spectral model therefore explicitly uses pitches both to separate the lead instrument from the others and to transcribe the pitch sequence played by that instrument, the "main melody". This model gives rise to two alternative models, a Gaussian Scaled Mixture Model (GSMM) and the Instantaneous Mixture Model (IMM). The accompaniment is modelled with a more general spectral model. Five systems are proposed. Three systems detect the fundamental frequency sequence of the lead instrument, i. E. They estimate the main melody. A system returns a musical melody transcription and the last system separates the lead instrument from the accompaniment. The results in melody transcription and source separation are at the state of the art, as shown by our participations to international evaluation campaigns (MIREX'08, MIREX'09 and SiSEC'08). The proposed extension of previous source separation works using "MIR" knowledge is therefore a very successful combination
Caillon, Antoine. "Hierarchical temporal learning for multi-instrument and orchestral audio synthesis". Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS115.
Texto completoRecent advances in deep learning have offered new ways to build models addressing a wide variety of tasks through the optimization of a set of parameters based on minimizing a cost function. Amongst these techniques, probabilistic generative models have yielded impressive advances in text, image and sound generation. However, musical audio signal generation remains a challenging problem. This comes from the complexity of audio signals themselves, since a single second of raw audio spans tens of thousands of individual samples. Modeling musical signals is even more challenging as important information are structured across different time scales, from micro (e.g. timbre, transient, phase) to macro (e.g. genre, tempo, structure) information. Modeling every scale at once would require large architectures, precluding the use of resulting models in real time setups for computational complexity reasons.In this thesis, we study how a hierarchical approach to audio modeling can address the musical signal modeling task, while offering different levels of control to the user. Our main hypothesis is that extracting different representation levels of an audio signal allows to abstract the complexity of lower levels for each modeling stage. This would eventually allow the use of lightweight architectures, each modeling a single audio scale. We start by addressing raw audio modeling by proposing an audio model combining Variational Auto Encoders and Generative Adversarial Networks, yielding high-quality 48kHz neural audio synthesis, while being 20 times faster than real time on CPU. Then, we study how autoregressive models can be used to understand the temporal behavior of the representation yielded by this low-level audio model, using optional additional conditioning signals such as acoustic descriptors or tempo. Finally, we propose a method for using all the proposed models directly on audio streams, allowing their use in realtime applications that we developed during this thesis. We conclude by presenting various creative collaborations led in parallel of this work with several composers and musicians, directly integrating the current state of the proposed technologies inside musical pieces
Pasquier, David. "Imagerie par Résonance Magnétique et radiothérapie conformationnelle: Caractérisation de l' Imagerie par Résonance Magnétique pour son utilisation dans l' établissement des plans de traitement en radiothérapie conformationnelle. Développement et évaluation d'un outil de délinéation automatique et semi- automatique des volumes d'intérêt pour la radiothérapie conformationnelle du cancer prostatique". Phd thesis, Université du Droit et de la Santé - Lille II, 2006. http://tel.archives-ouvertes.fr/tel-00483654.
Texto completoFourer, Dominique. "Approche informée pour l'analyse du son et de la musique". Phd thesis, Université Sciences et Technologies - Bordeaux I, 2013. http://tel.archives-ouvertes.fr/tel-00954965.
Texto completoDouwes, Constance. "On the Environmental Impact of Deep Generative Models for Audio". Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS074.
Texto completoIn this thesis, we investigate the environmental impact of deep learning models for audio generation and we aim to put computational cost at the core of the evaluation process. In particular, we focus on different types of deep learning models specialized in raw waveform audio synthesis. These models are now a key component of modern audio systems, and their use has increased significantly in recent years. Their flexibility and generalization capabilities make them powerful tools in many contexts, from text-to-speech synthesis to unconditional audio generation. However, these benefits come at the cost of expensive training sessions on large amounts of data, operated on energy-intensive dedicated hardware, which incurs large greenhouse gas emissions. The measures we use as a scientific community to evaluate our work are at the heart of this problem. Currently, deep learning researchers evaluate their works primarily based on improvements in accuracy, log-likelihood, reconstruction, or opinion scores, all of which overshadow the computational cost of generative models. Therefore, we propose using a new methodology based on Pareto optimality to help the community better evaluate their work's significance while bringing energy footprint -- and in fine carbon emissions -- at the same level of interest as the sound quality. In the first part of this thesis, we present a comprehensive report on the use of various evaluation measures of deep generative models for audio synthesis tasks. Even though computational efficiency is increasingly discussed, quality measurements are the most commonly used metrics to evaluate deep generative models, while energy consumption is almost never mentioned. Therefore, we address this issue by estimating the carbon cost of training generative models and comparing it to other noteworthy carbon costs to demonstrate that it is far from insignificant. In the second part of this thesis, we propose a large-scale evaluation of pervasive neural vocoders, which are a class of generative models used for speech generation, conditioned on mel-spectrogram. We introduce a multi-objective analysis based on Pareto optimality of both quality from human-based evaluation and energy consumption. Within this framework, we show that lighter models can perform better than more costly models. By proposing to rely on a novel definition of efficiency, we intend to provide practitioners with a decision basis for choosing the best model based on their requirements. In the last part of the thesis, we propose a method to reduce the inference costs of neural vocoders, based on quantizated neural networks. We show a significant gain on the memory size and give some hints for the future use of these models on embedded hardware. Overall, we provide keys to better understand the impact of deep generative models for audio synthesis as well as a new framework for developing models while accounting for their environmental impact. We hope that this work raises awareness on the need to investigate energy-efficient models simultaneously with high perceived quality
Baelde, Maxime. "Modèles génératifs pour la classification et la séparation de sources sonores en temps-réel". Thesis, Lille 1, 2019. http://www.theses.fr/2019LIL1I058/document.
Texto completoThis thesis is part of the A-Volute company, an audio enhancement softwares editor. It offers a radar that translates multi-channel audio information into visual information in real-time. This radar, although relevant, lacks intelligence because it only analyses the audio stream in terms of energy and not in terms of separate sound sources. The purpose of this thesis is to develop algorithms for classifying and separating sound sources in real time. On the one hand, audio source classification aims to assign a label (e.g. voice) to a monophonic (one label) or polyphonic (several labels) sound. The developed method uses a specific feature, the normalized power spectrum, which is useful in both monophonic and polyphonic cases due to its additive properties of the sound sources. This method uses a generative model that allows to derive a decision rule based on a non-parametric estimation. The real-time constraint is achieved by pre-processing the prototypes with a hierarchical clustering. The results are encouraging on different databases (owned and benchmark), both in terms of accuracy and computation time, especially in the polyphonic case. On the other hand, source separation consists in estimating the sources in terms of signal in a mixture. Two approaches to this purpose were considered in this thesis. The first considers the signals to be found as missing data and estimates them through a generative process and probabilistic modelling. The other approach consists, from sound examples present in a database, in computing optimal transformations of several examples whose combination tends towards the observed mixture. The two proposals are complementary, each having advantages and drawbacks (computation time for the first, interpretability of the result for the second). The experimental results seem promising and allow us to consider interesting research perspectives for each of the proposals
Guilment, Thomas. "Classification de vocalises de mammifères marins en environnement sismique". Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2018. http://www.theses.fr/2018IMTA0080/document.
Texto completoIn partnership with Sercel, the thesis concerns the implementation of algorithms for recognizing the sounds emitted by mysticetes (baleen whales). These sounds can be studiedusing passive acoustic monitoring systems. Sercel, through its seismic activities related to oïl exploration, has its own software to detect and locate underwater sound energy sources. The thesis work therefore consists in adding a recognition module to identify if the detected andlocalized energy corresponds to a possible mysticete. Since seismic shooting campaigns areexpensive, the method used must be able to reduce the probability of false alarms, as recognitioncan invalidate detection. The proposed method is based on dictionary learning. It is dynamic, modular, depends on few parameters and is robust to false alarms. An experiment on five types of vocalizations is presented. We obtain an average recall of 92.1% while rejecting 97.3% of the noises (persistent and transient). In addition, a confidence coefficient is associated with each recognition and allows semi-supervised incremental learning to be achieved. Finally, we propose a method capable of managing detection and recognition together. This "multiclassdetector" best respects the constraints of false alarm management and allows several types of vocalizations to be identified at the same time. This method is well adapted to the industrial context for which it is dedicated. It also opens up very promising prospects in the bioacoustic context
Ota, Kenko. "Traitement du signal pour la reconnaissance de la parole robuste dans des environnements bruités et réverbérants". Phd thesis, Ecole Centrale de Lille, 2008. http://tel.archives-ouvertes.fr/tel-00260343.
Texto completoLesage, Sylvain. "Apprentissage de dictionnaires structurés pour la modélisation parcimonieuse des signaux multicanaux". Phd thesis, Université Rennes 1, 2007. http://tel.archives-ouvertes.fr/tel-00564061.
Texto completoMeseguer, Brocal Gabriel. "Multimodal analysis : informed content estimation and audio source separation". Electronic Thesis or Diss., Sorbonne université, 2020. http://www.theses.fr/2020SORUS111.
Texto completoThis dissertation proposes the study of multimodal learning in the context of musical signals. Throughout, we focus on the interaction between audio signals and text information. Among the many text sources related to music that can be used (e.g. reviews, metadata, or social network feedback), we concentrate on lyrics. The singing voice directly connects the audio signal and the text information in a unique way, combining melody and lyrics where a linguistic dimension complements the abstraction of musical instruments. Our study focuses on the audio and lyrics interaction for targeting source separation and informed content estimation. Real-world stimuli are produced by complex phenomena and their constant interaction in various domains. Our understanding learns useful abstractions that fuse different modalities into a joint representation. Multimodal learning describes methods that analyse phenomena from different modalities and their interaction in order to tackle complex tasks. This results in better and richer representations that improve the performance of the current machine learning methods. To develop our multimodal analysis, we need first to address the lack of data containing singing voice with aligned lyrics. This data is mandatory to develop our ideas. Therefore, we investigate how to create such a dataset automatically leveraging resources from the World Wide Web. Creating this type of dataset is a challenge in itself that raises many research questions. We are constantly working with the classic ``chicken or the egg'' problem: acquiring and cleaning this data requires accurate models, but it is difficult to train models without data. We propose to use the teacher-student paradigm to develop a method where dataset creation and model learning are not seen as independent tasks but rather as complementary efforts. In this process, non-expert karaoke time-aligned lyrics and notes describe the lyrics as a sequence of time-aligned notes with their associated textual information. We then link each annotation to the correct audio and globally align the annotations to it. For this purpose, we use the normalized cross-correlation between the voice annotation sequence and the singing voice probability vector automatically, which is obtained using a deep convolutional neural network. Using the collected data we progressively improve that model. Every time we have an improved version, we can in turn correct and enhance the data
Haffner, Julien. "Conception d'un sol instrumenté pour la détection de chutes de personnes à l'aide de capteurs capacitifs et de techniques de l'apprentissage statistique". Electronic Thesis or Diss., Paris 6, 2016. http://www.theses.fr/2016PA066117.
Texto completoAlmost 9000 people aged over 65 die each year in France, as consequences of a fall. Falls represent over 80% of all domestic accidents in this part of the population. This number should substantially increase, as the average age of the population is expected to constantly grow up in the next decades. The longest the fallen person stay on the floor without being rescued, the worst are the consequences of the fall. In order to decrease negative effects of falls in older people, it is decisive to develop a technological way to keep isolated people in contact with outside world. In this thesis two fall detection systems are presented, made up with capacitive sensors integrated into the floor. Sensors are totally hidden to the view of people living in the room, in a way that their privacy is most respected. In the first system, parallel sensors are laid out in one direction of the room. One sensor is composed of four electrodes, whose relative spaces have been chosen to favor the detection of a person laying down on the floor. The second system consists of two perpendicular layers of capacitive sensors. Several rooms have been equipped with such sensors. Installing sensors in a new environment has an influence on the measured capacitive signal, due to the own floor configuration in each room. Methods of data preprocessing are proposed, in order to give equivalent detection performances in each environment
Joder, Cyril. "Alignement temporel musique-sur-partition par modèles graphiques discriminatifs". Phd thesis, Télécom ParisTech, 2011. http://pastel.archives-ouvertes.fr/pastel-00664260.
Texto completoPelletier, Charlotte. "Cartographie de l'occupation des sols à partir de séries temporelles d'images satellitaires à hautes résolutions : identification et traitement des données mal étiquetées". Thesis, Toulouse 3, 2017. http://www.theses.fr/2017TOU30241/document.
Texto completoLand surface monitoring is a key challenge for diverse applications such as environment, forestry, hydrology and geology. Such monitoring is particularly helpful for the management of territories and the prediction of climate trends. For this purpose, mapping approaches that employ satellite-based Earth Observations at different spatial and temporal scales are used to obtain the land surface characteristics. More precisely, supervised classification algorithms that exploit satellite data present many advantages compared to other mapping methods. In addition, the recent launches of new satellite constellations - Landsat-8 and Sentinel-2 - enable the acquisition of satellite image time series at high spatial and spectral resolutions, that are of great interest to describe vegetation land cover. These satellite data open new perspectives, but also interrogate the choice of classification algorithms and the choice of input data. In addition, learning classification algorithms over large areas require a substantial number of instances per land cover class describing landscape variability. Accordingly, training data can be extracted from existing maps or specific existing databases, such as crop parcel farmer's declaration or government databases. When using these databases, the main drawbacks are the lack of accuracy and update problems due to a long production time. Unfortunately, the use of these imperfect training data lead to the presence of mislabeled training instance that may impact the classification performance, and so the quality of the produced land cover map. Taking into account the above challenges, this Ph.D. work aims at improving the classification of new satellite image time series at high resolutions. The work has been divided into two main parts. The first Ph.D. goal consists in studying different classification systems by evaluating two classification algorithms with several input datasets. In addition, the stability and the robustness of the classification methods are discussed. The second goal deals with the errors contained in the training data. Firstly, methods for the detection of mislabeled data are proposed and analyzed. Secondly, a filtering method is proposed to take into account the mislabeled data in the classification framework. The objective is to reduce the influence of mislabeled data on the classification performance, and thus to improve the produced land cover map
Ambroise-Renault, Valérie. "L'hyperhidrose et son traitement". Nancy 1, 1996. http://www.theses.fr/1996NAN10055.
Texto completoMontels, Isabelle. "Le zona : son traitement allopathique ; son traitement homéopathique : Apis mellifica, Arsenicum album, Rhus toxicodendron". Bordeaux 2, 1993. http://www.theses.fr/1993BOR2P043.
Texto completoColin, Émilie. "Traitement automatique des langues et génération automatique d'exercices de grammaire". Electronic Thesis or Diss., Université de Lorraine, 2020. http://www.theses.fr/2020LORR0059.
Texto completoOur perspectives are educational, to create grammar exercises for French. Paraphrasing is an operation of reformulation. Our work tends to attest that sequence-to-sequence models are not simple repeaters but can learn syntax. First, by combining various models, we have shown that the representation of information in multiple forms (using formal data (RDF), coupled with text to extend or reduce it, or only text) allows us to exploit a corpus from different angles, increasing the diversity of outputs, exploiting the syntactic levers put in place. We also addressed a recurrent problem, that of data quality, and obtained paraphrases with a high syntactic adequacy (up to 98% coverage of the demand) and a very good linguistic level. We obtain up to 83.97 points of BLEU-4*, 78.41 more than our baseline average, without syntax leverage. This rate indicates a better control of the outputs, which are varied and of good quality in the absence of syntax leverage. Our idea was to be able to work from raw text : to produce a representation of its meaning. The transition to French text was also an imperative for us. Working from plain text, by automating the procedures, allowed us to create a corpus of more than 450,000 sentence/representation pairs, thanks to which we learned to generate massively correct texts (92% on qualitative validation). Anonymizing everything that is not functional contributed significantly to the quality of the results (68.31 of BLEU, i.e. +3.96 compared to the baseline, which was the generation of text from non-anonymized data). This second work can be applied the integration of a syntax lever guiding the outputs. What was our baseline at time 1 (generate without constraint) would then be combined with a constrained model. By applying an error search, this would allow the constitution of a silver base associating representations to texts. This base could then be multiplied by a reapplication of a generation under constraint, and thus achieve the applied objective of the thesis. The formal representation of information in a language-specific framework is a challenging task. This thesis offers some ideas on how to automate this operation. Moreover, we were only able to process relatively short sentences. The use of more recent neural modelswould likely improve the results. The use of appropriate output strokes would allow for extensive checks. *BLEU : quality of a text (scale from 0 (worst) to 100 (best), Papineni et al. (2002))
Sananes, Anne-Marie. "La cystite et son traitement". Bordeaux 2, 1994. http://www.theses.fr/1994BOR2P090.
Texto completoHaffner, Julien. "Conception d'un sol instrumenté pour la détection de chutes de personnes à l'aide de capteurs capacitifs et de techniques de l'apprentissage statistique". Thesis, Paris 6, 2016. http://www.theses.fr/2016PA066117.
Texto completoAlmost 9000 people aged over 65 die each year in France, as consequences of a fall. Falls represent over 80% of all domestic accidents in this part of the population. This number should substantially increase, as the average age of the population is expected to constantly grow up in the next decades. The longest the fallen person stay on the floor without being rescued, the worst are the consequences of the fall. In order to decrease negative effects of falls in older people, it is decisive to develop a technological way to keep isolated people in contact with outside world. In this thesis two fall detection systems are presented, made up with capacitive sensors integrated into the floor. Sensors are totally hidden to the view of people living in the room, in a way that their privacy is most respected. In the first system, parallel sensors are laid out in one direction of the room. One sensor is composed of four electrodes, whose relative spaces have been chosen to favor the detection of a person laying down on the floor. The second system consists of two perpendicular layers of capacitive sensors. Several rooms have been equipped with such sensors. Installing sensors in a new environment has an influence on the measured capacitive signal, due to the own floor configuration in each room. Methods of data preprocessing are proposed, in order to give equivalent detection performances in each environment
Jeanjean, Philippe. "Le traitement automatique des actes juridiques". Montpellier 1, 1988. http://www.theses.fr/1988MON10014.
Texto completoIn order to deal with the increasing inflation and complexity of legal acts, computers appear to be the right tool. Legal reasoning and logic which emerges have to be compared with computer's logic. Automated drafting of acts has legal consequences ( problems of proof, copyright, modification of the acts) but also in the field of economics. Among those ones we have to underline the fact that drafting itself is less important now than the activity of counsel. That embodies the legal preeminence of negotium on instrumentum. Furthermore, once dedicated to deal with the mechanical part of the lawyer's activity, computers are going now to deal with legal reasoning itself. That's the role of expert systems. In the future the automated drafting of legal acts must be a part of a real help to the organisation which will use such tools as legal audit but also a better flow of legal information
Jeanjean, Philippe. "Le Traitement automatique des actes juridiques". Lille 3 : ANRT, 1989. http://catalogue.bnf.fr/ark:/12148/cb376145258.
Texto completoValentini, Paul Emile. "L'athérosclérose : les différents stades de sa lésion, son mécanisme, son épidémiologie, son traitement". Paris 5, 1989. http://www.theses.fr/1989PA05P083.
Texto completoCortial, Odile. "La cataracte et son traitement chirurgical". Paris 5, 1998. http://www.theses.fr/1998PA05P211.
Texto completoHuynh, Ba-Nghiêm. "Le dysfonctionnement érectile et son traitement". Paris 5, 2001. http://www.theses.fr/2001PA05P022.
Texto completoBordato, Agnès. "L'ostéoporose et son traitement par l'alendronate". Bordeaux 2, 1998. http://www.theses.fr/1998BOR2P002.
Texto completoCoeugnet, Chantal. "La dermatite atopique et son traitement". Bordeaux 2, 1994. http://www.theses.fr/1994BOR2P063.
Texto completoDuchêne, Chantal. "L' acte suicidaire et son traitement". Paris 7, 2011. http://www.theses.fr/2011PA070123.
Texto completoThis research aims to clarify what is happening in the suicidal person's psyche. It is based on two assumptions: the relation to the primal object and then the patient's identification with it. When identification is failing, commiting suicide reproduces the original situation leading to experience of loss. Then, the suicidal patient would "resort to suicide", " avoir recours à l'acte" according to Claude Balier's theory. In other words, the suicidal is not able to overcome a " fundamental anthropological situation" described by Jean Laplanche i. E. That of the "central complex" as explained by Mervin Classer. When the identification with the primal object is strong enough, the act of suicide takes the pattern of melancholy. The suicidal uses the hostile feelings he feels towards the primal object who he felt had abandoned him , and turns these negative feelings against himself. In this case, the transition to self damage is the enactment of the primal fantasies (against the primal objet) and results in a loss of the ego. Whether the loss is a primal loss or loss of the ego, what is at stake for the suicidal is narcissism or rather its weaknesses, excess or lack. The second part of this thesis concerns the therapeutic management of suicidal patients, unable to talk about their suicide attempts and represent it emotionally. This difficulty is strengthened by the fact that the current direction of the health care policy concerning the prevention of suicide, is focused on factual and external realities to the detriment of the psychic reality of the suicidal patient
FOULET, BERNARD. "La maculopathie diabetique et son traitement". Lille 2, 1992. http://www.theses.fr/1992LIL2M155.
Texto completoKessler, Rémy. "Traitement automatique d'informations appliqué aux ressources humaines". Phd thesis, Université d'Avignon, 2009. http://tel.archives-ouvertes.fr/tel-00453642.
Texto completoHaddad, Afifa. "Traitement des nominalisations anaphoriques en indexation automatique". Lyon 2, 2001. http://theses.univ-lyon2.fr/documents/lyon2/2001/haddad_a.
Texto completoThis thesis proposes en indexation method for integral texts based on anaphoric noun phrases. The motivation is to take advantage from the wide context of an anaphora relation in order to build a rich descriptor ? and to get consequently a performant index. The main contribution here is the design of a complete method enabling the systematic reconstitution of all arguments of each anaphoric nominalization encountered in the text. A completely resolved noun phrase constitutes a rich descriptor that is then added to the index. The resolution a nominal anaphora makes use the results of other preliminarly activities. These consists in collecting the syntactic structures of the possible noun phrase corresponding to a nominalization and, identifying a set of the anaphoric noun phrase and the form of its precedent. The feasibility of the proposed has been demonstrated through an application to a real-life corpus
Konfe, Amadou. "Contribution au traitement automatique de la polysemie". Caen, 1991. http://www.theses.fr/1991CAEN2028.
Texto completoHubert, Christian. "Traitement automatique des comptes rendus d'echographie abdominale". Paris 6, 1990. http://www.theses.fr/1990PA066173.
Texto completoMela, Augusta. "Traitement automatique de la coordination par et". Paris 13, 1992. http://www.theses.fr/1992PA132040.
Texto completoHaddad, Afifa Le Guern Michel. "Traitement des nominalisations anaphoriques en indexation automatique". [S.l.] : [s.n.], 2001. http://theses.univ-lyon2.fr/sdx/theses/lyon2/intranet/haddad_a.
Texto completo