|
|
Automatic vocal-oriented recognition of human emotions
Houdek, Miroslav ; Přinosil, Jiří (referee) ; Atassi, Hicham (advisor)
This master thesis concerns with emotional states and gender recognition on the basis of speech signal analysis. We used various prosodic and cepstral features for the description of the speech signal. In the text we describe non-invasive methods for glottal pulses estimation. The described features of speech were implemented in MATLAB. For their classification we used the GMM classifier, which uses the Gaussian probability distribution for modeling a feature space. Furthermore, we constructed a system for recognition of emotional states of the speaker and a system for gender recognition from speech. We tested the success of created systems with several features on speech signal segments of various lengths and compared the results. In the last part we tested the influence of speaker and gender on the success of emotional states recognition.
|
|
|
Protection of personality in the legal system of the Czech republic
Houdek, Miroslav ; Uhlík, Milan (advisor) ; Pavla, Pavla (referee)
The thesis deals with the protection of personality in the legal system of the Czech Republic. Its aim is to specify the possible ways protection of personality in the legal system of the Czech Republic with using of appropriate methods; and also to determine the number of reported and the Czech Police investigated cases including their treatment and in case of deficiencies in the legislation, organization and management are found, to propose measures to eliminate them. The theoretical part contains international and national legislation regulating protection of personality in the legal system of the Czech Republic. In the practical part there is an evaluation of legislation at first, followed by proposed measures to eliminate deficiencies in the field protection of personality. This is followed by analysis of wiretapping and recording of telecommunication operations and analysis of statistical data of selected cases undertaken by the CZ Police. At the end of the empirical part there is performed a quantitative research by using a questionnaire that is intended to members of police and citizens. The resulting values are analyzed, evaluated and translated into charts and graphs. In conclusion there is a proposed change in the law in the sense of de lege ferenda.
|
|
|
Automatic vocal-oriented recognition of human emotions
Houdek, Miroslav ; Přinosil, Jiří (referee) ; Atassi, Hicham (advisor)
This master thesis concerns with emotional states and gender recognition on the basis of speech signal analysis. We used various prosodic and cepstral features for the description of the speech signal. In the text we describe non-invasive methods for glottal pulses estimation. The described features of speech were implemented in MATLAB. For their classification we used the GMM classifier, which uses the Gaussian probability distribution for modeling a feature space. Furthermore, we constructed a system for recognition of emotional states of the speaker and a system for gender recognition from speech. We tested the success of created systems with several features on speech signal segments of various lengths and compared the results. In the last part we tested the influence of speaker and gender on the success of emotional states recognition.
|
guest ::
RSS feed.