|
|
Automatic speech recordings segmentation tool
Santa, Roman ; Zvončák, Vojtěch (referee) ; Kováč, Daniel (advisor)
Nástroj pre automatickú segmentáciu spracováva nahrávky reči a extrahuje hovorené slovo z nahrávok. Je dôležité, aby pokročilá analýza pracovala iba s rečovými časťami z nahrávky. Nástroj na segmentáciu má ulahčiť spracovanie nahrávok pre analýzu rozdielov medzi hláskami pacientov s parkinsonovou chorobou a tými zdravými. Cieľ tejto práce je navrhnúť a otestovať detektory reči s Google WebRTC detektorom a vybrať ten najvhodnejší detektor reči s minimálnym počtom chýb. Ďalej, vytvoriť nástroj na segmentáciu nahrávok a otestovať rozpoznávanie reči pomocou dynamic time warping. Bola použitá databáza poskytnutá laboratóriom pre analýzu mozgových ochorení. Obsahuje české a maďarské nahrávky s rovnakým počtom mužských a ženských pacientov a aj rovnakým počtom zdravých pacientov a pacientov s parkinsonovou chorobou. Najlepšie výsledky v testoch dosiahol detektor na základe energie reči. Nebol zistený žiaden rozdiel v presnosti detektoru pri spracovaní mužských a ženských nahrávok alebo nahrávok zdravých či chorých pacientov. Nahrávky s nízkym odstupom signálu od šumu boli náročnejšie na spracovanie s frekvenciou chýb od 12%. Na základe výsledkov, bol navrhnutý nový detektor pre spracovanie úplnej nahrávky. Na záver bol testovaný algoritmus pre rozpoznávanie podobnosti reči na základe melovských kepstrálnych koeficientov.
|
|
|
Android stock market application
Balaževič, Lukáš ; Ilgner, Petr (referee) ; Zvončák, Vojtěch (advisor)
The aim of the work is to design and implement an android application which will display parameters of cryptocurrencies, technical indicators and will predict the price based on the modern technology of machine learning. In addition to the displaying parameters, the user will be able to set up notifications. Application displays data from the Firebase database. The data are uploaded to an application from two services which run on Ubuntu server and are written in programming language Kotlin and Python. Services are in charge of obtaining and data processing. One of the services takes care of price prediction, the price is predicted using a LSTM neural network where each cryptocurrency has an own training model. The result of the work is a system that takes care of the whole lifecycle of the data from the acquisition, transformation and the presentation to the user. Based on acquired information from the application, the user is able to make statistically correct decisions in the cryptocurrency market without the need to constant market monitoring.
|
|
|
Recognition of music style from orchestral recording using Music Information Retrieval techniques
Jelínková, Jana ; Zvončák, Vojtěch (referee) ; Kiska, Tomáš (advisor)
As all genres of popular music, classical music consists of many different subgenres. The aim of this work is to recognize those subgenres from orchestral recordings. It is focused on the time period from the very end of 16th century to the beginning of 20th century, which means that Baroque era, Classical era and Romantic era are researched. The Music Information Retrieval (MIR) method was used to classify chosen subgenres. In the first phase of MIR method, parameters were extracted from musical recordings and were evaluated. Only the best parameters were used as input data for machine learning classifiers, to be specific: kNN (K-Nearest Neighbor), LDA (Linear Discriminant Analysis), GMM (Gaussian Mixture Models) and SVM (Support Vector Machines). In the final chapter, all the best results are summarized. According to the results, there is significant difference between the Baroque era and the other researched eras. This significant difference led to better identification of the Baroque era recordings. On the contrary, Classical era ended up to be relatively similar to Romantic era and therefore all classifiers had less success in identification of recordings from this era. The results are in line with music theory and characteristics of chosen musical eras.
|
|
|
Virtualization on routers
Ráboňová, Jana ; Zvončák, Vojtěch (referee) ; Ilgner, Petr (advisor)
This thesis deals with router based virtualization in the field of computer networking. The main goal is to present platforms suitable for virtualization and demonstrate practical usage afterwards. There were choosen three virtualization platforms, Mikrotik MetaROUTER, KVM and LXC containers. All of them have been tested for its performance. For MetaROUTER platform has been done modifications to allow deploy the newest version of linux distribution OpenWRT. Further, there were choosen testing scenarios, for which have been shown the possible aplication of virtualization on routers.
|
|
|
Chorus effect - innovation of laboratory exercise
Zvončák, Vojtěch ; Schimmel, Jiří (referee) ; Říha, Kamil (advisor)
The thesis is a theoretical preparation and description of the construction of a laboratory device, which will be used in the laboratory of Studio and Musical Electronics course. At the beginning of the thesis there are basic features of effects with delay line explained. Then CHORUS effect and its mathematical function is desribed. Features of delay line are shown - delay line contains BBD shift register working on CCD principle. There are Frequency Response characteristics of CHORUS effect simaluted in VST Plugin Analyser program. Practical part deals with the description of the individual parts of the whole device circuit. Results of the significant signals measurement are introduced in chapter 5. A design of power switching supply for this laboratory device is presented at the end of the thesis.
|
|
|
Django framework based web application for objective analysis of hypokinetic dysarthria
Čapek, Karel ; Zvončák, Vojtěch (referee) ; Galáž, Zoltán (advisor)
This master´s thesis deals with the calculation of parameters that would be able to differentiate healthy speech and speech impaired by hypokinetic dysarthria. There was staged hypokinetic dysarthria, which is a motoric disorder of speech and vocal tract. Were studied speech signal processing methods. Further parameters were studied, which could well differentiate healthy and diseased speech. Subsequently, these parameters were programmed in Python programming language. The next step was to create a web application in Django framework, which is used for the analysis of the dyzartic speech.
|
|
|
Recognition of music cover versions using Music Information Retrieval techniques
Martinek, Václav ; Zvončák, Vojtěch (referee) ; Kiska, Tomáš (advisor)
This master’s thesis deals with designs and implementation of systems for music cover recognition. The introduction part is devoted to the calculation parameters from audio signal using Music Information Retrieval techniques. Subsequently, various forms of cover versions and musical aspects that cover versions share are defined. The thesis also deals in detail with the creation and distribution of a database of cover versions. Furthermore, the work presents methods and techniques for comparing and processing the calculated parameters. Attention is then paid to the OTI method, CSM calculation and methods dealing with parameter selection. The next part of the thesis is devoted to the design of systems for recognizing cover versions. Then there are compared systems already designed for recognizing cover versions. Furthermore, the thesis describes machine learning techniques and evaluation methods for evaluating the classification with a special emphasis on artificial neural networks. The last part of the thesis deals with the implementation of two systems in MATLAB and Python. These systems are then tested on the created database of cover versions.
|
|
|
Research of Advanced Online Handwriting Analysis Methods with a Special Focus on Assessment of Graphomotor Disabilities in School-aged Children
Zvončák, Vojtěch ; Havigerová,, Jana Marie (referee) ; Drotár,, Peter (referee) ; Mekyska, Jiří (advisor)
Grafomotorické dovednosti (GA) představují skupinu psychomotorických procesů, které se zapojují během kreslení a psaní. GA jsou nutnou prerekvizitou pro zvládání základních školních schopností, konkrétně psaní. Děti v první a druhé třídě mohou mít potíže s prováděním jednoduchých grafomotorických úkolů (GD) a později ve třetí a čtvrté třídě také se samotným psaním (HD). Narušení procesů spojených se psaním je obecně nazýváno jako vývojová dysgrafie (DD). Prevalence DD v České republice se pohybuje kolem 3–5 %. V současné době je DD hodnocena subjektivně týmem psychologů a speciálních pedagogů. V praxi stále chybí objektivní měřicí nástroj, který by umožňoval hodnocení GD a HD. Z tohoto důvodu se tato disertační práce zabývá identifikováním symptomů spojených s grafomotorickou neobratností u dětí školního věku a vývojem nových parametrů, které je budou kvantifikovat. Byl vytvořen komplexní GA protokol (36 úloh), který představuje prostředí, ve kterém se mohou projevit různé symptomy spojené s GD a HD. K těmto symptomům bylo přiřazeno 76 kvantifikujících parametrů. Dále byla navrhnuta nová škála grafomotorických obtíží (GDRS) založena na automatizovaném zpracování online píma. Nakonec byla prezentována a otestována nová sada parametrizačních technik založených na Tunable Q Factor Wavelet Transform (TQWT). Parametry TQWT dokážou kvantifikovat grafomotorickou obratnost nebo nedostatečný projev v jemné motorice. GDRS přestavuje nový, moderní a objektivní měřící nástroj, který doposud chyběl jak v České republice, tak v zahraničí. Použití škály by pomohlo modernizovat jak diagnostiku DD, tak reedukační/remediační proces. Další výzkum by tento nástroj mohl adaptovat i do jiných jazyků. Navíc, tato metodologie může být použita a optimalizována pro diagnostiku dalších nemocí a poruch, které ovlivňují grafomotorické dovednosti, například pro autismus, poruchu pozornosti s hyperaktivitou (ADHD) nebo dyspraxii (DCD).
|
|
|
Music genre recognition using Music information retrieval techniques
Zemánková, Šárka ; Zvončák, Vojtěch (referee) ; Kiska, Tomáš (advisor)
This diploma work deals with music genre recognition using the techniques of Music Information Retrieval. It contains a brief description of the principle of this research area and its subfield called Music Genre Recognition. The following chapter includes selection of the most suitable parameters for describing music genres. This work further characterizes machine learning methods used in this field of research. The next chapter deals with the descriptions of music datasets created for genre classification studies. Subsequently, there is a draft and evaluation of the system for music genre recognition. The last part of this work describes the results of partial parameter analysis, dependence of genre classification accuracy on the amount of parameters and contains a discussion on the causes of classification accurancy for the individual genres.
|
|
|
Cancelling noise of magnetic resonance in recordings of speech
Vrba, Filip ; Galáž, Zoltán (referee) ; Zvončák, Vojtěch (advisor)
This thesis deals with the removal of noise in speech recordings that have been recorded in an MRI environment. For this purpose, the Nvidia RTX Voice technology, the VST plug-in module Noisereduce and a self-designed method of subtractive de-noising of recordings are used. A program with a simple graphical interface in Python is implemented within the work to retrieve the recordings and then de-noise them using the proposed methods. The work includes measurements in a magnetic resonance environment with two microphones. The quality of the processed recordings is tested within the program using the STOI (Short-Time Objective Intelligibility Measure) method as well as the subjective analysis method within listening tests.
|
guest ::
RSS feed.