|
|
Audio inpainting algorithms
Kolbábková, Anežka ; Veselý, Vítězslav (referee) ; Rajmic, Pavel (advisor)
Tato práce se zabývá doplňováním chybějících dat do audio signálů a algoritmy řešícími problém založenými na řídké reprezentaci audio signálu. Práce se zaměřuje na některé algoritmy, které řeší doplňování chybějících dat do audio signálů pomocí řídké reprezentace signálů. Součástí práce je také návrh algoritmu, který používá řídkou reprezentaci signálu a také nízkou hodnost signálu ve spektrogramu audio signálu. Dále práce uvádí implementaci tohoto algoritmu v programu Matlab a jeho vyhodnocení.
|
|
|
Dictionary learning for sparse signal reconstruction
Ozdobinski, Roman ; Rajmic, Pavel (referee) ; Mach, Václav (advisor)
This bachelor thesis discusses the dictionary learning for the reconstruction of signal based on sparse representations. There are methods of static and optimized dictionary of matrices described that are used with approximative Orthogonal Matching Pursuit algorithm to reconstruct the missing groups of samples in the audio signal. There is theoretically analyzed algorithm for learning K-SVD dictionary together with its implementation in Matlab. Furthermore, the selected dictionaries are compared to the various types of audio signals.
|
|
|
Methods of acquisition and processing of images based on sparse representations
Talár, Ondřej ; Mach, Václav (referee) ; Rajmic, Pavel (advisor)
Thesis deals with the reconstruction possibilities provided by the sparse representation of signals. This representation reduces the signal to a mere vector of elements which indicate the signal portion in the dictionary array. It outlined the problems with the quantized signal and recalled modulation type, involving a quantization and its ways. The solution is selected Douglas-Rachford algorithm that allows us to approximate on to the set of all acceptable solutions. At the end is demonstrated problem solution and several tests for presentation of created program.
|
|
|
Modern audio denoising with utilization of phase information
Skyva, Pavel ; Záviška, Pavel (referee) ; Rajmic, Pavel (advisor)
The thesis deals with modern methods of audio denoising. Reconstruction of the audiosignal is primarly based on utilization of phase information of signals and phase derivatives. Denoising methods also use sparse signal representations. In thesis is described the way of searching sparse coefficients using proximal Condat algorithm and following computation of reconstructed signal using this coefficients. The reconstruction algorithms are implemented in the MATLAB software with toolbox LTFAT included. Results of the reconstruction are compared using objective evaluation method Signal-to-Noise Ratio (SNR) and also by subjective evaluation.
|
|
|
Applications of sparse data representations
Navrátilová, Barbora ; Veselý, Vítězslav (referee) ; Rajmic, Pavel (advisor)
The goal of this thesis is to demonstrate practical application of sparse data representation in the processing of sparse signals. For solving several example problems - denoising, dequantization, and sparse signal decomposition - convex optimization was used. The solutions were implemented in the Matlab environment. For each of the problems, there are two solutions - one for one-dimensional, and one for two-dimensional signal.
|
|
|
Restoration of signals with limited instantaneous value for the multichannel audio signal
Hájek, Vojtěch ; Vrba, Kamil (referee) ; Záviška, Pavel (advisor)
This master’s thesis deals with the restoration of clipped multichannel audio signals based on sparse representations. First, a general theory of clipping and theory of sparse representations of audio signals is described. A short overview of existing restoration methods is part of this thesis as well. Subsequently, two declipping algorithms are introduced and are also implemented in the Matlab environment as a part of the thesis. The first one, SPADE, is considered a state- of-the-art method for mono audio signals declipping and the second one, CASCADE, which is derived from SPADE, is designed for the restoration of multichannel signals. In the last part of the thesis, both algorithms are tested and the results are compared using the objective measures SDR and PEAQ, and also using the subjective listening test MUSHRA.
|
|
|
Making up missing audio signal sections
Pospíšil, Jiří ; Rášo, Ondřej (referee) ; Mach, Václav (advisor)
The goal of this bachelor’s thesis is to get introduced with methods for reconstruction of missing samples in audio signal using periodicity-based interpolation and AR model based interpolation. Further it’s introducing us with Audio Inpainting method based on sparse representation. In practical part there are programmed three algorithms based on these interpolation methods and described an algorithm which is used in Audio Inpainting. These algorithms are compared with objective methods, SNR measurements depending on gap length and value of input parameter.
|
|
|
Optimization of data representation for target tracking using sensor network
Cabalová, Klára ; Veselý, Vítězslav (referee) ; Rajmic, Pavel (advisor)
The aim of this bachelor thesis is to find optimal data representation for target tracking using sensor network. There is described a model of decentralized sensor network and also the application of so called dictionary to represent the measured data. Also, there is theoretically introduced the K-SVD algorithm that is used for dictionary learning and there are learnt dictionaries for data representation based on the model signals. These dictionaries are compared with each other.
|
|
|
Restoration of audio signals damaged by quantization
Šiška, Jakub ; Rajmic, Pavel (referee) ; Záviška, Pavel (advisor)
This master’s thesis deals with the restoration of audio signals damaged by quantization. The theoretical part starts with a description of quantization and dequantization in general, few existing methods of dequantization of audio signals and theory of sparse representations of signals are also presented. The next part introduces algorithms suitable for dequantization, specifically Douglas–Rachford, Chambolle–Pock, SPADEQ and implementation of these algorithms in MATLAB application in the next chapter. In the last part of this thesis, testing of reconstructed signals using the algorithms takes place and results are evaluated by objective measures SDR, PEMO-Q, PEAQ and subjective listening test MUSHRA.
|
|
|
Determining the optimal patch size for sparse image representation
Šuránek, David ; Zátyik, Ján (referee) ; Špiřík, Jan (advisor)
Introduction of this thesis is dedicated to the description of basic concepts and algorithms for image processing using sparse representation. Furthermore there is mentioned neural network model called Restricted Boltzmann machine, which is in the practical part of the thesis subject of behaving observation in the task of determining the optimal block size for extrapolation using K-SVD algorithm
|
guest ::
