|
|
Automatic vocal-oriented recognition of human emotions
Adamský, Aleš ; Kubánková, Anna (oponent) ; Atassi, Hicham (vedoucí práce)
This work deals with the characteristics, formation, representation and analysis of speech and the speech signal. It explains the details of concepts such as emotions and prosody. It analyzes different emotion state of human, as well as prosodic parameters: intensity, harmonisity and formants. It includes a database emotional states of human. This database was analyzed using the Praat and suitable features were selected for detecting of emotional states of human speech. It also deals with neural networks. It contains a description of Java Neural Network Simulator, which is used to detect emotional states of human speech. Results of recognition are processed in tables and graphs for easier navigation.
|
|
|
Speaker Segmentation using statistical methods of classification
Adamský, Aleš ; Přinosil, Jiří (oponent) ; Smékal, Zdeněk (vedoucí práce)
The thesis discusses in detail some concepts of speech and prosody that can contribute to build a speech corpus for the speaker segmentation purpose. Moreover, the Elan multimedia annotator used for labeling is described. The theoretical part highlights some frequently used speech features such as MFCC, PLP and LPC and deals with currently most popular speech segmentation methods. Some classification algorithms are also mentioned. The practical part describes implementation of Bayesian information criterium algorithm in system for automatic speaker segmentation. For classification of speaker change point in speech, were used different speech features. The results of tests were evaluated by the graphic method of receiver operating characteristic (ROC) and his quantitative indices. As the best speech features for this system were provided MFCC and HFCC.
|
|
|
Automatic vocal-oriented recognition of human emotions
Adamský, Aleš ; Kubánková, Anna (oponent) ; Atassi, Hicham (vedoucí práce)
This work deals with the characteristics, formation, representation and analysis of speech and the speech signal. It explains the details of concepts such as emotions and prosody. It analyzes different emotion state of human, as well as prosodic parameters: intensity, harmonisity and formants. It includes a database emotional states of human. This database was analyzed using the Praat and suitable features were selected for detecting of emotional states of human speech. It also deals with neural networks. It contains a description of Java Neural Network Simulator, which is used to detect emotional states of human speech. Results of recognition are processed in tables and graphs for easier navigation.
|
|
|
Speaker Segmentation using statistical methods of classification
Adamský, Aleš ; Přinosil, Jiří (oponent) ; Smékal, Zdeněk (vedoucí práce)
The thesis discusses in detail some concepts of speech and prosody that can contribute to build a speech corpus for the speaker segmentation purpose. Moreover, the Elan multimedia annotator used for labeling is described. The theoretical part highlights some frequently used speech features such as MFCC, PLP and LPC and deals with currently most popular speech segmentation methods. Some classification algorithms are also mentioned. The practical part describes implementation of Bayesian information criterium algorithm in system for automatic speaker segmentation. For classification of speaker change point in speech, were used different speech features. The results of tests were evaluated by the graphic method of receiver operating characteristic (ROC) and his quantitative indices. As the best speech features for this system were provided MFCC and HFCC.
|
host ::
RSS.