In immersive audio environments with distributed microphones, Independent Component Analysis (ICA) can be applied to uncover signals from a mixture of other signals and noise, such as in a cocktail party recording. ICA algorithms have been developed for instantaneous source mixtures and convolutional source mixtures. While ICA for instantaneous mixtures works when no delays exist between the signals in each mixture, distributed microphone recordings typically result various delays of the signals over the recorded channels. The convolutive ICA algorithm should account for delays; however, it requires many parameters to be set and often has stability issues. This thesis introduces the Channel Aligned FastICA (CAICA), which requires knowledge of the source distance to each microphone, but does not require knowledge of noise sources. Furthermore, the CAICA is combined with Time Frequency Masking (TFM), yielding even better SOI extraction even in low SNR environments. Simulations were conducted for ranking experiments tested the performance of three algorithms: Weighted Beamforming (WB), CAICA, CAICA with TFM. The Closest Microphone (CM) recording is used as a reference for all three. Statistical analyses on the results demonstrated superior performance for the CAICA with TFM. The algorithms were applied to experimental recordings to support the conclusions of the simulations. These techniques can be deployed in mobile platforms, used in surveillance for capturing human speech and potentially adapted to biomedical fields.

This thesis discusses the use of Kalman filtering for noise reduction in a 3-D gesture- based computer music controller known as the Radio Drum and for real-time tempo tracking of rhythmic and melodic musical performances. The Radio Drum noise reduction Kalman filter is designed based on previous research in the field of target tracking for radar applications and prior knowledge of a drummer’s expected gestures throughout a performance. In this case we are seeking to improve the position estimates of a drum stick in order to enhance the expressivity and control of the instrument by the performer. Our approach to tempo tracking is novel in that a multi- modal approach combining gesture sensors and audio in a late fusion stage lead to higher accuracy in the tempo estimates.

Ce mémoire de thèse de doctorat présente, discute et propose des outils de fouille automatique de mégadonnées dans un contexte de classification supervisée musical.L'application principale concerne la classification automatique des thèmes musicaux afin de générer des listes de lecture thématiques.Le premier chapitre introduit les différents contextes et concepts autour des mégadonnées musicales et de leur consommation.Le deuxième chapitre s'attelle à la description des bases de données musicales existantes dans le cadre d'expériences académiques d'analyse audio.Ce chapitre introduit notamment les problématiques concernant la variété et les proportions inégales des thèmes contenus dans une base, qui demeurent complexes à prendre en compte dans une classification supervisée.Le troisième chapitre explique l'importance de l'extraction et du développement de caractéristiques audio et musicales pertinentes afin de mieux décrire le contenu des éléments contenus dans ces bases de données.Ce chapitre explique plusieurs phénomènes psychoacoustiques et utilise des techniques de traitement du signal sonore afin de calculer des caractéristiques audio.De nouvelles méthodes d'agrégation de caractéristiques audio locales sont proposées afin d'améliorer la classification des morceaux.Le quatrième chapitre décrit l'utilisation des caractéristiques musicales extraites afin de trier les morceaux par thèmes et donc de permettre les recommandations musicales et la génération automatique de listes de lecture thématiques homogènes.Cette partie implique l'utilisation d'algorithmes d'apprentissage automatique afin de réaliser des tâches de classification musicale.Les contributions de ce mémoire sont résumées dans le cinquième chapitre qui propose également des perspectives de recherche dans l'apprentissage automatique et l'extraction de caractéristiques audio multi-échelles. / This doctoral dissertation presents, discusses and proposes tools for the automatic information retrieval in big musical databases.The main application is the supervised classification of musical themes to generate thematic playlists.The first chapter introduces the different contexts and concepts around big musical databases and their consumption.The second chapter focuses on the description of existing music databases as part of academic experiments in audio analysis.This chapter notably introduces issues concerning the variety and unequal proportions of the themes contained in a database, which remain complex to take into account in supervised classification.The third chapter explains the importance of extracting and developing relevant audio features in order to better describe the content of music tracks in these databases.This chapter explains several psychoacoustic phenomena and uses sound signal processing techniques to compute audio features.New methods of aggregating local audio features are proposed to improve song classification.The fourth chapter describes the use of the extracted audio features in order to sort the songs by themes and thus to allow the musical recommendations and the automatic generation of homogeneous thematic playlists.This part involves the use of machine learning algorithms to perform music classification tasks.The contributions of this dissertation are summarized in the fifth chapter which also proposes research perspectives in machine learning and extraction of multi-scale audio features.

Ce manuscrit porte sur la modélisation et l'estimation de certaines non-stationnarités dans les signaux audio. Nous nous intéressons particulièrement à une classe de modèles de sons que nous nommons timbre*dynamique dans lesquels un signal stationnaire, associé au phénomène physique à l'origine du son, est déformé au cours du temps par un opérateur linéaire unitaire, appelé opérateur de déformation, associé à l'évolution temporelle des caractéristiques de ce phénomène physique. Les signaux audio sont modélisés comme des processus gaussiens généralisés et nous donnons dans un premier temps un ensemble d'outils mathématiques qui étendent certaines notions utilisées en traitement du signal au cas des processus stochastiques généralisés.Nous introduisons ensuite les opérateurs de déformations étudiés dans ce manuscrit. L'opérateur de modulation fréquentielle qui est l'opérateur de multiplication par une fonction à valeurs complexes de module unité, et l'opérateur de changement d'horloge qui est la version unitaire de l'opérateur de composition.Lorsque ces opérateurs agissent sur des processus stationnaires les processus déformés possèdent localement des propriétés de stationnarité et les opérateurs de déformation peuvent être approximés par des opérateurs de translation dans les plans temps-fréquence et temps-échelle. Nous donnons alors des bornes pour les erreurs d'approximation correspondantes. Nous développons ensuite un estimateur de maximum de vraisemblance approché des fonctions de dilatation et de modulation. L'algorithme proposé est testé et validé sur des signaux synthétiques et des sons naurels. / This manuscript deals with the modeling and estimation of certain non-stationarities in audio signals. We are particularly interested in a sound class models which we call dynamic*timbre in which a stationary signal, associated with the physical phenomenon causing the sound, is deformed over time by a linear unitary operator, called deformation operator, associated with the temporal evolution of the characteristics of this physical phenomenon.Audio signals are modeled as generalized Gaussian processes. We give first a set of mathematical tools that extend some classical notions used in signal processing in case of generalized stochastic processes.We then introduce the two deformations operators studied in this manuscript. The frequency modulation operator is the multiplication operator by a complex-valued function of unit module and the time-warping operator is the unit version of the composition operator by a bijective function.When these operators act on generalized stationary processes, deformed process are non-stationary generalized process which locally have stationarity properties and deformation operators can be approximated by translation operators in the time-frequency plans and time-scale.We give accurate versions of these approximations, as well as bounds for the corresponding approximation errors.Based on these approximations, we develop an approximated maximum likelihood estimator of the warping and modulation functions. The proposed algorithm is tested and validated on synthetic signals. Its application to natural sounds confirm the validity of the timbre*dynamic model in this context.

This work explores the topic of digital audio signal processing for modular synthesizers and the design of digital oscillator for modular standard known as Eurorack. Introduction of the theoretical part is dedicated to basic terms and blocks used in modular synthesizers. The thesis also characterizes and presents the methods of sound synthesis. The second part of the theory concerns analog and digital signal conversion made by digital signal processors DSP, focusing on ARM with focus on ARM architecture. The practical part of the thesis concerns design and construction of the digital oscillator which generates periodic waveforms without aliasing distortion. The oscillator also allows several types of modulations and waveforming and the module has several inputs for connecting control voltages or external audio signals.

This diploma thesis deals with methods of the onset and tempo detection in audio signals using specific techniques of digital processing. It analyzes and describes the issue from both the musical and the technical side. First, several implementations using different programming environments are tested. The system with the highest detection accuracy and adjustable parameters is selected, which is then used to test functionality on the reference database. Then, an extension of the algorithm based on the Teager-Kaiser energy operator in the preprocessing stage is created. The difference in accuracy of both systems is compared – the operator has on average increased the accuracy of detection of a global tempo and inter-beat intervals. Finally, a second dataset containing 33 different interpretations of the first movement of Bedřich Smetana’s composition, String Quartet No. 1 in E minor "From My Life". The results show that the average tempo of the entire first movement of the song slightly decreases depending on the later year of the recording.

This master thesis deals with the problem of audio-classification of the chainsaw logging sound in natural environment using mainly convolutional neural networks. First, a theory of grafical representation of audio signal is discussed. Following part is devoted to the machine learning area. In third chapter, some of present works dealing with this problematics are given. Within the practical part, used dataset and tested neural networks are presented. Final resultes are compared by achieved accuracy and by ROC curves. The robustness of the presented solutions was tested by proposed detection program and evaluated using objective criteria.

Master’s thesis deals with the generation of digital audio signals with band-limited frequency spectrum, i.e. without the aliasing distortion. Various methods of generating band-limited rectangular, triangular, and sawtooth waveforms are described in the theoretical part. The described methods are programmed in the Matlab programming environment and compared in terms of real-time parameter changes, such as duty cycle change of rectangular waveform or continuous change of frequency. The main part of the thesis describes implementation of methods of successive integration of band-limited impulse train and method of differentiated parabolic waveforms in C++ language. The implemented methods were integrated into a plug-in of VST technology that generates an audio signal in real time. The implemented methods are compared in terms of computational complexity and distortion of the generated signal.

Several applications have been proposed for wireless sensor networks, including habitat monitoring, structural health monitoring, pipeline monitoring, and precision agriculture. Among the desirable features of wireless sensor networks, one is the ease of deployment. Since the nodes are capable of self-organization, they can be placed easily in areas that are otherwise inaccessible to or impractical for other types of sensing systems. In fact, some have proposed the deployment of wireless sensor networks by dropping nodes from a plane, delivering them in an artillery shell, or launching them via a catapult from onboard a ship. There are also reports of actual aerial deployments, for example the one carried out using an unmanned aerial vehicle (UAV) at a Marine Corps combat centre in California -- the nodes were able to establish a time-synchronized, multi-hop communication network for tracking vehicles that passed along a dirt road. While this has a practical relevance for some civil applications (such as rescue operations), a more realistic deployment involves the careful planning and placement of sensors. Even then, nodes may not be placed optimally to ensure that the network is fully connected and high-quality data pertaining to the phenomena being monitored can be extracted from the network. This work aims to address the problem of random deployment through two complementary approaches: The first approach aims to address the problem of random deployment from a communication perspective. It begins by establishing a comprehensive mathematical model to quantify the energy cost of various concerns of a fully operational wireless sensor network. Based on the analytic model, an energy-efficient topology control protocol is developed. The protocol sets eligibility metric to establish and maintain a multi-hop communication path and to ensure that all nodes exhaust their energy in a uniform manner. The second approach focuses on addressing the problem of imperfect sensing from a signal processing perspective. It investigates the impact of deployment errors (calibration, placement, and orientation errors) on the quality of the sensed data and attempts to identify robust and error-agnostic features. If random placement is unavoidable and dense deployment cannot be supported, robust and error-agnostic features enable one to recognize interesting events from erroneous or imperfect data.

This thesis deals with oportunity of ROC curve usage in the description of methods that work with sound signals. Specifically, it focuses on ways of detecting of stress in speech signals. The detection itselfs is done in a range of frequencies of the sound signal. There is also a classifier designed using ROC curves that decides whether the input signal is stressed or not. The output of this thesis are findings gathered from analyses and also some recommendation based on those analyses.