|
|
Stress recognition from speech signal
Staněk, Miroslav ; Přibil, Jiří (referee) ; Tučková,, Jana (referee) ; Sigmund, Milan (advisor)
Předložená disertační práce se zabývá vývojem algoritmů pro detekci stresu z řečového signálu. Inovativnost této práce se vyznačuje dvěma typy analýzy řečového signálu, a to za použití samohláskových polygonů a analýzy hlasivkových pulsů. Obě tyto základní analýzy mohou sloužit k detekci stresu v řečovém signálu, což bylo dokázáno sérií provedených experimentů. Nejlepších výsledků bylo dosaženo pomocí tzv. Closing-To-Opening phase ratio příznaku v Top-To-Bottom kritériu v kombinaci s vhodným klasifikátorem. Detekce stresu založená na této analýze může být definována jako jazykově i fonémově nezávislá, což bylo rovněž dokázáno získanými výsledky, které dosahují v některých případech až 95% úspěšnosti. Všechny experimenty byly provedeny na vytvořené české databázi obsahující reálný stres, a některé experimenty byly také provedeny pro anglickou stresovou databázi SUSAS.
|
|
|
Estimation of formant frequencies using machine learning
Káčerová, Erika ; Galáž, Zoltán (referee) ; Mekyska, Jiří (advisor)
This Master's thesis deals with the issue of formant extraction. A system of scripts in Matlab interface is created to generate values of the first three formant frequencies from speech recordings with the use of Praat and Snack(WaveSurfer). Mel Frequency Cepstral Coefficients and Linear Predictive Coefficients are extracted from the audio files in order to be added to the database. This database is then used to train a neural network. Finally, the designed neural network is tested.
|
|
|
Finite element modelling of voice propagation through the vocal tract and around the human head
Tomeček, Vojtěch ; Pellant, Karel (referee) ; Švancara, Pavel (advisor)
This diploma thesis deals with creating of finite element model for the analysis of acustic waves radiation through human vocal tract and through the head surrounding space. The thesis contains a short overview of the anatomy of relevant parts and a short overview of formerly published models relevant to the topic. Then the process of creating the 3D model of human head, including the vocal tract, based on CT scans, and the mesh itself follows. This is succeeded by the computational solution taking in the acount the acoustic absorption of the vocal tract walls and radiation into the open space. The results gained are compared to relevant literature on this topic. The changes in frequency spectra in specific nodes of the mesh are reviewed and compared to relevant literature on the topic. The results could be used as basis of eventual frequention corrections of microphones used for voice diagnosis or registration in general, eg of speach or singing.
|
|
|
Diagnosing Parkinson's disease from analysis of speech recording
Vymlátil, Petr ; Trzos, Michal (referee) ; Lněnička, Jakub (advisor)
This thesis is focused on diagnosing Parkinson’s disease from analysis of speech recording. Introduction of this work deals with description of voice production mechanism, it’s basic qualities and influence of hypokinetic dysarthria on speech. In next chapter, there is described voice signal and some methods of it’s preprocessing. Next part continues dealing with description of chosen individual symptoms, which are needed for PD diagnosing, followed by definition of chosen reduction methods and classifiers. There is a comparison of classify succes of naive bayes classifier, depending on chosen reduction method in last chapter of this work.
|
|
|
The Program simulating the mutes of brass instruments
Košař, Vojtěch ; Indrák, Michal (referee) ; Jirásek, Ondřej (advisor)
This Master’s thesis deals with the creation of a program that simulates an impact of sound mutes on the timbre of a trombone and a trumpet. The simulation in the Reaktor 6 environment is based on an analysis of this impact which compares the spectra and formant regions retrieved from the MATLAB environment. The analysis takes into account also the impact on harmonic overtones. Another part of this work is focusing on the theory of a trombone and a trumpet, their brief history, the parts they are consisting of and the principle of tone formation. In the Reaktor 6 environment there has been created also a sampler functioning as a virtual instrument for the trumpet and the trombon. The last part of the work deals with creating a simulation program with its structure and evaluation.
|
|
|
The Analysis of impedance properties of the bridge in string instruments
Němec, Petr ; Nop, Patrik (referee) ; Jirásek, Ondřej (advisor)
It is a known fact that stringed instruments bridge makes an important part of "acoustic circuit" of their bodies. Bridge acts as an acoustic filter which has the biggest impact on 2 – 6 kHz band and high frequency bands. To find the connection between the impact of a specific acoustic and mechanical properties of a bridge and acoustical behavior of the entire instrument remains as a matter of further exploration. Aim of this thesis is to find the mentioned relations of a chosen materials in an accordance to their mechanical properties within a full range of materials with common bridge properties. The experiments are designed to determine mechanical and acoustic properties of chosen materials which are then used to fabricate bridges. Subsequently the acoustical behavior of instruments with chosen bridges is determined. Based upon these findings we propose specific solutions and suggest further research.
|
|
|
The Program simulating the mutes of brass instruments
Košař, Vojtěch ; Indrák, Michal (referee) ; Jirásek, Ondřej (advisor)
This Master’s thesis deals with the creation of a program that simulates an impact of sound mutes on the timbre of a trombone and a trumpet. The simulation in the Reaktor 6 environment is based on an analysis of this impact which compares the spectra and formant regions retrieved from the MATLAB environment. The analysis takes into account also the impact on harmonic overtones. Another part of this work is focusing on the theory of a trombone and a trumpet, their brief history, the parts they are consisting of and the principle of tone formation. In the Reaktor 6 environment there has been created also a sampler functioning as a virtual instrument for the trumpet and the trombon. The last part of the work deals with creating a simulation program with its structure and evaluation.
|
|
|
The Analysis of mutes on trombone and trumpet timbre
Košař, Vojtěch ; Mojdl, Edgar (referee) ; Jirásek, Ondřej (advisor)
This work deals with the sound mute issues, specifically how they affect the timbre of a trombone and a trumpet, their sound spectrum, levels of individual harmonic tones, the presence of formants and the directional characteristics of individual tones played in various dynamics. A part of this work is also focused on the theoretical description of a trombone and a trumpet, including their brief history, their classification, the parts they are consisting of and the timbre. The theoretical part is further dealing with the description of mathematic functions like FFT or LPC analysis, which have been implemented in the MATLAB environment when creating the graphic dependents for this theme.
|
|
|
The comparison of acoustic properties of guitars from the same product line
Trávníčková, Hana ; Indrák, Michal (referee) ; Jirásek, Ondřej (advisor)
This work is dealing with acoustic features of Furch guitars. In theoretical introduction is possible to find an information about basic characteristics of a tone. Following chapter about acoustic guitars is dealing even with mostly used types of woods for their manufacturing. In special chapter are described spectres of signals, LPC analysis, sound radiation of instruments and Chladni figures. Mentioned terms have been evaluated from measurements and are available in practical part of this work also including description of implementation of the measurement. As an output of this work is a comparison of acoustic features of measured guitars, their colours and modes.
|
|
|
Estimation of formant frequencies using machine learning
Káčerová, Erika ; Galáž, Zoltán (referee) ; Mekyska, Jiří (advisor)
This Master's thesis deals with the issue of formant extraction. A system of scripts in Matlab interface is created to generate values of the first three formant frequencies from speech recordings with the use of Praat and Snack(WaveSurfer). Mel Frequency Cepstral Coefficients and Linear Predictive Coefficients are extracted from the audio files in order to be added to the database. This database is then used to train a neural network. Finally, the designed neural network is tested.
|
guest ::
