|
|
Music Recommendation System
Páleník, Radoslav ; Hrubý, Martin (referee) ; Zbořil, František (advisor)
This bachelor thesis aims to study and design computer program, which will be able to recognise 10 essential music genres using deep learning. This classification was implemented by convolutional neural network based on Tensorflow framework. This network process audio file into segments in form of spectograms and returns percentual propability of record being classified into specific genre by features found in spectogram.
|
|
|
Acoustic signal classification
Pospíšil, Aleš ; Balík, Miroslav (referee) ; Atassi, Hicham (advisor)
Bachelor's thesis is focused on automatic music genre classication. First part of work evaluates present situation and refer to published studies. Gained knowledge from there is applied in this work. In terms of nding solution for problem the work summarize and describe suitable music features and classication techniques like neural networks and k-nearest neighbor. Four selected classication classes were classical, electro, jazz and rock music. Result of work is user-friendly system that provides automatic music genre recognition. Achieved classication performance is more less comparable to human music genres recognition.
|
|
|
Musical genre classification
Káčerová, Erika ; Říha, Kamil (referee) ; Uher, Václav (advisor)
The aim of this bachelor thesis is creating a system for automatic music genre recognition. The thesis deals with two main issues, which are feature extraction of a genre and machine learning process. For the purpose of feature extraction a source code is written in JAVA programming language based on jAudio library. Six machine learning models are created in RapidMiner Studio software. The most appropriate one of them, Neural Networks method is then improved and tested on different parts of songs from database.These database contains 250 training songs and 25 test songs from five music genres: classical music, disco, drum and bass, hip hop and rock.
|
|
|
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.
|
|
|
Transformations in the Interpretation of Music Folklore: From the Protection of Everyday Culture to the Emergence of a Music Genre (Using the Czech Republic as a Case Study)
Uhlíková, Lucie ; Pavlicová, M.
From the 1960s onwards, efforts began to develop in Czech ethnology, which gradually began to include folklore manifestations in their second existence in professional research. The field of folklorism sometimes overlapped with the existence of folk traditions, sometimes built on them, and sometimes was only inspired by them to varying degrees. The distinction in such defined categories was not easy even in the past, and with the increasingly rapid development of society, it became blurred in the general consciousness. Within this scope, a contemporary broad music genre, music folklore, has emerged that is not easy to define in terms of content. In this paper, the authors outline its historical formation, show model moments of its development, and deal with its polyfunctionality: many collectives present themselves not only on stage (together with dancers) and in concert settings (independently), but also participate in local ethno-cultural traditions, dance parties, family celebrations (weddings, birthdays), and commercially focused events. To illustrate this, the paper uses archival source material, and field research based on interviews with selected musicians.
|
|
|
Transformations in the Interpretation of Music Folklore: From the Protection of Everyday Culture to the Emergence of a Music Genre (Using the Czech Republic as a Case Study)
Uhlíková, Lucie ; Pavlicová, M.
From the 1960s onwards, efforts began to develop in Czech ethnology, which gradually began to include folklore manifestations in their second existence in professional research. The field of folklorism sometimes overlapped with the existence of folk traditions, sometimes built on them, and sometimes was only inspired by them to varying degrees. The distinction in such defined categories was not easy even in the past, and with the increasingly rapid development of society, it became blurred in the general consciousness. Within this scope, a contemporary broad music genre, music folklore, has emerged that is not easy to define in terms of content. In this paper, the authors outline its historical formation, show model moments of its development, and deal with its polyfunctionality: many collectives present themselves not only on stage (together with dancers) and in concert settings (independently), but also participate in local ethno-cultural traditions, dance parties, family celebrations (weddings, birthdays), and commercially focused events. To illustrate this, the paper uses archival source material, and field research based on interviews with selected musicians.
|
|
|
Music Recommendation System
Páleník, Radoslav ; Hrubý, Martin (referee) ; Zbořil, František (advisor)
This bachelor thesis aims to study and design computer program, which will be able to recognise 10 essential music genres using deep learning. This classification was implemented by convolutional neural network based on Tensorflow framework. This network process audio file into segments in form of spectograms and returns percentual propability of record being classified into specific genre by features found in spectogram.
|
|
|
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.
|
|
|
A view of the current techno scene through photojournalism
Fialová, Karolína ; Turek, Pavel (advisor) ; Láb, Filip (referee)
The practical part of this dissertation presents the current techno scene in Prague, Czech Republic. Techno as a relatively new genre of electronic dance music has gone through a wave of popularity in Prague over the past few years, but without the influence of established promoters. The photobook covers events organised by three collectives of young people, with a more extensive focus on one of them. They capture the euphoria of the night and subsequent morning fatigue as well as behind the scenes shots. The enclosed photo book shows photographs mainly from parties organised by Cukr. This collective of three young people has been active on Prague's scene for the past few years and its founders regularly run techno events. They change the location for each party, but organising events in places such as churches, theaters, abandoned banks or warehouses carries a risk - and sometimes things don't go according to plan. The theoretical part focuses on the history of techno, its cultural and musical context and the characteristics of nightlife photography through presenting the views of photographers such as Wolfgang Tillmans or Dave Swindells. I also compare Prague's techno with the situation in Berlin or London. I explain that the scene in Prague, as it is now, is fragile - and can disappear along...
|
|
|
Two Pastoral Masses from the Ledenice Music Collection
ŠIMEK, Martin
This bachelor thesis deals with two vocal instrumental compositions from the first half of the 19th century which were designated to be performed during the Christmas worship. The compositions were found at the choir loft of the church in Ledenice in South Bohemia. Compositions of smaller sizes for the minimum cast were performed for the most of the time of the church year because of the abilities of the church musical operation in the small town. Therefore, the ambition of the schoolmasters was performed larger compositions during Christmas. Apart from smaller pastorellas in the Ledenice music collection were found also pastoral masses, which concerning to its range are the most ambitious compositions which can be performed in the countryside. This bachelor thesis also includes the edition of both masses in a digital form, description of the compositions, comparison of the used manners and a critical report.
|
guest ::
