Original title: Nástroj pro podporu cvičení klavírních skladeb
Translated title: Tool for Piano Practising
Authors: Ustinov, Nikita ; Hrubý, Martin (referee) ; Zbořil, František (advisor)
Document type: Master’s theses
Year: 2020
Language: cze
Publisher: Vysoké učení technické v Brně. Fakulta informačních technologií
Abstract: [cze] [eng]
Ucelem teto prace je navrhnout a implementovat aplikaci pro cviceni hry na klaviru. Hlavni nevyhodou jiz existujicich aplikaci je omezeny vyber skladeb, ktere lze cvicit, protoze tyto skladby jsou pevne zapsane v pameti. Aplikace ktera je vysledkem teto praci vyresi dany problem - uzivatel bude moct nahrat do aplikace libovolnou klavirni nahravku kterou chce cvicit a aplikace se postara o vytvoreni procesu cviceni. Proces cviceni se spociva v ukazce uzivatelu urcitym zpusobem upravenych not, a soucasna kontrola, pomoci mikrofonu, co hraje uzivatel. Nejvetsim vyzvou dane diplomove prace bylo najit zpusob jak presne a rychle klasifikovat audio signal z mikrofonu. Dana uloha byla vyresena pomoci dvou neza- vislych neuronovych siti s ruznou architekturou, ktere byli trenovany na ruznych datovych sadech. Za ucelem oduvodneni zvoleneho reseni budou uvedeny vsechny potrebne teoreticke muzikalni a vedecke pojmy a metody, ktere maji k tomu primy vztah. Vysledna aplikace bude testovana z trech hledisek: presnosti, rychlosti, uzivatelske pouzitelnosti. The purpose of this work is to design and implement an application for piano practice. The main disadvantage of existing applications is the limited selection of songs that can be practiced. The application, which is the result of this work, will solve the problem - the user will be able to upload to the application any piano record he wants to practice, and the application will take care of creating a training process. The training process consists of showing the user a certain way of editing notes and simultaneously controlling what the user is playing with a microphone. The biggest challenge of the diploma thesis was to find a way to accurately and quickly classify the audio signal from the microphone. This problem was solved using two independent neural networks with different architectures, which were trained on different data sets. To justify the chosen solution, all the necessary theoretical musical and scientific concepts and methods that are directly related to it will be presented. The resulting application will be tested in three respects: accuracy, speed, the usability of the user.
Keywords: automatic music transcription; machine learning; neural networks; automatizovana transkripce hudby; neuronove site; strojove uceni

Institution: Brno University of Technology (web)
Document availability information: Fulltext is available in the Brno University of Technology Digital Library.
Original record: http://hdl.handle.net/11012/194975

Permalink: http://www.nusl.cz/ntk/nusl-433611


The record appears in these collections:
Universities and colleges > Public universities > Brno University of Technology
Academic theses (ETDs) > Master’s theses