|
|
Comparison of analysis of speech in dependence on age and gender
Báňa, Josef ; Smékal, Zdeněk (referee) ; Atassi, Hicham (advisor)
This thesis deals with analysis of speech signal in dependence on the gender and the age of the speaker. We tried to investigate through the features to find the best set for the automatic classification of speakers. It also contains a brief discussion about the speech signal and its characteristics. We used a program called Praat for the speech analysis purpose. This program is also described in this work. We mainly focused on the suprasegmental features of speech. Our first step was to make our own speech corpus which should contain speech records from speakers with various age and gender. We made the analysis using Praat and reported it within this thesis. For the automatic classification purpose, twelve features were selected basing on there quality criteria and used with a neural network to classify the speakers to classes with different age and gender. As it was mentioned, a neural network was used as a classifier. We used “Neural Network Toolbox” in the Matlab program to create and train our networks.
|
|
|
Detection and Correspondence of Image Features
Hasmanda, Martin ; Kohoutek, Michal (referee) ; Říha, Kamil (advisor)
The main goal of this bachelor‘s thesis was obtain basic knowledge about image processing. Especially was this work specialized on features detection in images captured from different perspectives and for finding correspondences between those images. Preliminary were to be described the basic principles for understanding computer vision such as perspective projection, description model of the camera and two views geometry. From methods of the detection was introduced best-known and most widely used of the detectors Harris corner detector. He is independent of images rotation and he is analyzed in detail. Further was described SIFT detector, that is independent of images scale. In this work further be described to several methods for finding correspondences of images features. First were to be described and derived two basic transformation matrixes that arrange to the association with features of two images. The first homography matrix describes transformation of two 2D views and fundamental matrix. Fundamental matrix obtains from two images full information of captured 3D scene and projection matrixes of cameras. For to primary definition correspondences were to be used to methods SSD and NCC. These methods match correspondences after similarities surroundings of features. These methods unfiled correct assignment features. Therefore uses stochastic RANSAC algorithm. The RANSAC algorithm was in detail described in this work in basic form and further modified on MLESAC algorithm. This algorithm can find better correspondences than RANSAC. In the end was described simple application for implementation introduced methods.
|
|
|
Analysis of phonation in patients with Parkinson's disease
Kopřiva, Tomáš ; Smékal, Zdeněk (referee) ; Mekyska, Jiří (advisor)
This work deals with analysis of phonation in patients with Parkinson’s disease (PD). Approximately 90% of patients with Parkinson’s disease suffer from speech motor dysfunction called hypokinetic dysarthria. System for Parkinson’s disease analysis from speech signals is proposed and several types of features are examined. Czech Parkinson’s speech database called PARCZ is used for classification. This dataset consists of 84 PD patients and 49 healthy controls. Results are evaluated in two ways. Firstly, features are individually analysed by Spearman correlation, mutual information and Mann-Whitney U test. Classification is based on random forests along with leave-one-out validation. Secondly, SFFS algorithm is employed for feature selection in order to get the best classification result. Proposed system is tested for each gender individually and both genders together as well. Best result for both genders together is expressed by accuracy 89,47 %, sensitivity 91,67% and specificity 85,71 %. Results of this work showed that the most important vowel realizations for phonation analysis are sustained vowels pronounced with maximum or minimum intensity (not whispering).
|
|
|
Determining person's height from spoken utterance
Pelikán, Pavel ; Mekyska, Jiří (referee) ; Atassi, Hicham (advisor)
Diploma’s thesis is focused on determining person’s height from spoken utterance. First part of the work evaluates present situation and refers to the published studies. Knowledge gained in these studies was used in this thesis. Study with the best results according to estimated height of the speakers was chosen. The experiment realized in the chosen study was performed in this work. The system for the estimation of the height of the speakers based on the speech signal was created. This system was successfully tested by using several acoustic features on spoken utterances from TIMIT database.
|
|
| |
|
|
Speaker Segmentation using statistical methods of classification
Adamský, Aleš ; Přinosil, Jiří (referee) ; Smékal, Zdeněk (advisor)
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.
|
|
|
Paralinguistic signals recognition in spoken dialogs
Mašek, Jan ; Míča, Ivan (referee) ; Atassi, Hicham (advisor)
This document describes the three methods for the detection and classification of paralinguistic expressions such as laughing and crying from usual speech by analysis of the audio signal. The database of records was originally designed for this purpose. When analyzing everyday dialogs, music might be included, so the database was extended by four new classes as speech, music, singing with music and usual speech with background music. Feature extraction, feature reduction and classification are common steps in recognizing for all three methods. Difference of the methods is given by classification process in detail. One classification of all six classes at once is proposed in the first method called straight approach. In the second method called decision tree oriented approach we are using five intuitive sub classifiers in the tree structure and the final method uses for classification emotion coupling approach. The best features were reduced by feature evaluation using F-ratio and GMM classifiers were used for the each classification part.
|
|
|
Optic flow software module design
Grulich, Jan ; Růžička, Michal (referee) ; Věchet, Stanislav (advisor)
This bachelor thesis is focused on the analysis of optical flow. The first part is dedicated to the theoretical analysis of the motion of image features. Especially important is finding quality features that can be tracked in a videosequence. Detailed mathematical description of the necessary algorithms is presented. The second part describes the software and its functions with the implemented algorithms. The main function is determining the distance of an object from the camera based on its velocity. Empirical tests of this function are presented.
|
|
|
Suggestopedia as inspiration for English language teaching in the context of interest adult education
MALÍKOVÁ, Andrea
The diploma thesis deals with the suggestopedical English language teaching in the context of leisure education. Characterizes the interest adult learning as a part of lifelong education, defines its objectives, functions, motivation and language barriers within the adult education. More specifically, it focuses on the alternative method suggestopedia in detail; it examines its origin, development, features and principles. It describes the different stages of learning that forms the characteristic profile of this unconventional method. The empirical part is focused on the suggestopedic course itself. The use of case study helped to understand the features of suggestopedic education, processes and conditions from the point of experiences and attitudes of the course participants, i.e. the advantages and disadvantages of this method.
|
|
|
Aplikácia sociálnych sietí v školskom zariadení
Bálint, Vladimír ; Pavlíček, Antonín (advisor) ; Řezníček, Václav (referee)
This thesis focuses on the development of strategy for universal application of social networking in a school of pre-primary and primary education level and its subsequent application in a real school. It describes potential benefits of such application and discusses other ways of use of social networks in primary schools. In addition, in theoretical part it defines actors of school environment and information flows between them. Subsequently discusses about communication needs of these actors given the current communication tools and generational differences. The practical part is based on applying a specific strategy of social networks in a school in Slovakia along with the information and summarized results of this application.
|
guest ::
