|
|
Sound to MIDI conversion
Pleva, Pavel ; Frýza, Tomáš (referee) ; Fedra, Zbyněk (advisor)
This thesis deal with possibilities of conversion simple musical signal to MIDI format. It contains brief introduction into chosen parts of MIDI standard which are important for this theme. Further there are examined characteristic attributes of sound which are needed to detect from musical signal to be written in SMF or which affects detection of useful attributes. There is given an account of algorithm for conversion implemented in Matlab.
|
|
|
Conversion of monophonic melody from the audio signal into the MIDI protocol stream
Krupička, Jan ; Rášo, Ondřej (referee) ; Mačák, Jaromír (advisor)
The aim of this thesis is to compare possibilities of the pitch extraction methods in the monophonic melody. There is presented the overview of the methods based on the speech pitch extraction techniques in the thesis. These methods uses frequency, time and „cepstral“ domain. They are compared in the term of success of the detection of various test signals. The part of the thesis specification is the implementation of these methods in Matlab. There are described basics of sound features at the beginning of this work. The overview of the musical tuning systems is mentioned and there is described a problem of the determination of the pitch from the detected frequency. There is considered an issue of MIDI protocol in the next part of the work. There are described the brief history and the essential structure of MIDI protocol. The last task of the work was the creation of the program in C language. The purpose of the program is to analyze the monophonic melody in audio signal form and assign note numbers to the detected sounds according to MIDI specification. After that the numbers are written into the standard MIDI file (SMF). There was implemented a correlation pitch detection algorithm in this program. It had the best results as compared to the others. There was used the fast correlation based on Fast Fourier transformation to accelerate computing of the correlation. The program was created in the form of MEX function, which provides various possibilities to be used in Matlab. There was also attached the description of the FFTW library, which was used to compute FFT.
|
|
|
Computer analysis of sport matches
Židlík, Pavel ; Balík, Miroslav (referee) ; Atassi, Hicham (advisor)
This work deals with the possibility of a fast football match analysis from audio part of record with the possibility of implementation of some methods for other than football matches as well. The first intention was concentrated on detection of whiz of the soccer whistle that has specific frequency in its specter, which is out of common speech frequency. After detection harmonic frequency , the attention was focused on the definition of whiz meaning. Referee was helpful with the issue as he informed me about the number of whiz styles and provided me with referential samples for whiz classification. Neural network with back propagation was used for definition of whiz meaning. Another subject for detection of important moments of the match was concentration on the commentator’s basic tone. In case the commentator is really excited with the match, his basic speech tone automatically intensifies with every important action of the game. Analysis of commentator’s intensified basic speech tone was realized in this work too. Also the national hymns of teams playing against each other are a significant moment of the match. That is why detection of a hymn became another subject of analysis. Advantages of MFCC were used to obtain audio signal feature, from which 20 coefficients were gained. These were used as an entrance for classifier based on neural network with back propagation. For easy usage of these methods a graphic user interface with possibility of well-arranged look on gained results and also with possibility of replaying chosen section was created.
|
|
|
Sound to MIDI conversion
Pleva, Pavel ; Frýza, Tomáš (referee) ; Fedra, Zbyněk (advisor)
This thesis deal with possibilities of conversion simple musical signal to MIDI format. It contains brief introduction into chosen parts of MIDI standard which are important for this theme. Further there are examined characteristic attributes of sound which are needed to detect from musical signal to be written in SMF or which affects detection of useful attributes. There is given an account of algorithm for conversion implemented in Matlab.
|
|
|
Conversion of monophonic melody from the audio signal into the MIDI protocol stream
Krupička, Jan ; Rášo, Ondřej (referee) ; Mačák, Jaromír (advisor)
The aim of this thesis is to compare possibilities of the pitch extraction methods in the monophonic melody. There is presented the overview of the methods based on the speech pitch extraction techniques in the thesis. These methods uses frequency, time and „cepstral“ domain. They are compared in the term of success of the detection of various test signals. The part of the thesis specification is the implementation of these methods in Matlab. There are described basics of sound features at the beginning of this work. The overview of the musical tuning systems is mentioned and there is described a problem of the determination of the pitch from the detected frequency. There is considered an issue of MIDI protocol in the next part of the work. There are described the brief history and the essential structure of MIDI protocol. The last task of the work was the creation of the program in C language. The purpose of the program is to analyze the monophonic melody in audio signal form and assign note numbers to the detected sounds according to MIDI specification. After that the numbers are written into the standard MIDI file (SMF). There was implemented a correlation pitch detection algorithm in this program. It had the best results as compared to the others. There was used the fast correlation based on Fast Fourier transformation to accelerate computing of the correlation. The program was created in the form of MEX function, which provides various possibilities to be used in Matlab. There was also attached the description of the FFTW library, which was used to compute FFT.
|
|
|
Computer analysis of sport matches
Židlík, Pavel ; Balík, Miroslav (referee) ; Atassi, Hicham (advisor)
This work deals with the possibility of a fast football match analysis from audio part of record with the possibility of implementation of some methods for other than football matches as well. The first intention was concentrated on detection of whiz of the soccer whistle that has specific frequency in its specter, which is out of common speech frequency. After detection harmonic frequency , the attention was focused on the definition of whiz meaning. Referee was helpful with the issue as he informed me about the number of whiz styles and provided me with referential samples for whiz classification. Neural network with back propagation was used for definition of whiz meaning. Another subject for detection of important moments of the match was concentration on the commentator’s basic tone. In case the commentator is really excited with the match, his basic speech tone automatically intensifies with every important action of the game. Analysis of commentator’s intensified basic speech tone was realized in this work too. Also the national hymns of teams playing against each other are a significant moment of the match. That is why detection of a hymn became another subject of analysis. Advantages of MFCC were used to obtain audio signal feature, from which 20 coefficients were gained. These were used as an entrance for classifier based on neural network with back propagation. For easy usage of these methods a graphic user interface with possibility of well-arranged look on gained results and also with possibility of replaying chosen section was created.
|
guest ::
