|
|
Speech segmentation
Andrla, Petr ; Míča, Ivan (referee) ; Sysel, Petr (advisor)
The programme for the segmentation of a speech into fonems was created as a part of the master´s thesis. This programme was made in the programme Matlab and consists of several scripts. The programme serves for automatic segmentation. Speech segmentation is the process of identifying the boundaries between phonemes in spoken natural languages. Automatic segmentation is based on vector quantization. In the first step of algorithm, feature extraction is realized. Then speech segments are assigned to calculated centroids. Position where centroid is changed is marked as a boundary of phoneme. The audiorecords were elaborated by the programme and a operation of the automatic segmentation was analysed. A detailed manual was created to the programme too. Individual used methods of the elaboration of a speech were in the master´s thesis briefly descripted, its implementations in the programme and reasons of set of its parameters.
|
|
|
The data transfer technologies in optical access networks (FTTx)
Matušík, Lukáš ; Míča, Ivan (referee) ; Reichert, Pavel (advisor)
The objective of diploma thesis is describe problems connected with designed of FTTX networks and bring the reader problems of data transmission in optical acces networks the type of PON. In the introduction are mentinoned individual technologies that already operate, and there are describe advantages disadvantages of the use topology point-to-point and point-to-multipoint. In the following chapters are dealt with problems with data broadcasting in the direction from final participant. In the other part of diploma thesis are described elements, that were used for the proposed transmission route. The own PON acces network was presented on the basis information obtained by comparing the various networks and the elements involved in them. The network presented in conclusion diploma thesis is involved in topology point to multipoint. This transmission route is simulated in the program that allows the involvement of network by the user’s need with real values. The acces network is simulated for different transmission speed and different distances. The assesment of created optical route results from the measured values, theirs source is program OptiSystem, these values are summarized in the final chapter.
|
|
|
Decoder for key word detection system
Krotký, Jan ; Míča, Ivan (referee) ; Pfeifer, Václav (advisor)
The essay presents the basic characteristics of human speech recognition, describes systems for the detection of key words and further deals with the proposal of each decoder blocks divided into three chapters. The first one describes the operations that are performed before the signal distribution of the framework and the segmentation. The second chapter describes the calculation of short-term energy, the number of zero passes and self-correlative, prediction and Mel-frequency cepstral coefficients. The third chapter, which describes the design of the block decoder, describes the method of dynamic time destruction and the method based on hidden Markov model. The final part of the essay describes decoders working with a speech and a proposal for a simple decoder working with isolated words, which was based issued and tested based on the preceding chapters.
|
|
| |
|
|
Tool for statistical evaluation of the simulation process of JSimlib4 library
Pivoda, Štefan ; Míča, Ivan (referee) ; Burget, Radim (advisor)
This master's thesis deals with the analysis of simulation of computer networks. A statistical tool was designed for evaluating a communication between stations in the computer network. JSimlib4 Java library was used for the simulation of computer networks. It is a lightweight but robust simulation library, designed for creating simple or even quite complex simulation models of distributed systems. The Statistical tool was written in Java programming language and developed in an EasyEclipse integrated development environment. It was designed as an Eclipse Rich Client Platform application. Eclipse Rich Client Platform is a relatively new technology, which has a lot of favorable properties. The Statistical tool can be divided into 3 parts: • creating a log file, • creating a filter, • creating/showing an output. The Statistical tool creates records into a log file during every communication between stations. This log file contains a comment on the first line. This comment describes the definition of records. Every record contains 2 IP addresses with the used ports at the beginning of the record, then the time, the amount of bytes, the protocol and the direction of communication. Every item in the record is divided by a colon. The Statistical tool can evaluate a communication between stations. At first, it has to define a filter according to which it will assess the suitable stations. It can be created either by adding IP addresses or names of the stations onto a list on a workbench. Filter can be loaded from a file that already includes these IP addresses and other information too. After defining the filter, the Statistical tool can create either a diagram or a file. At first, the Statistical tool reads the log file line by line and compares the IP addresses, which were added to the filter with the IP addresses in a log file. When the Statistical tool finds a complying IP address, it reads the whole line and adds an amount of bytes defined on that line to the final diagram that is shown after reading the whole log file. In the case of finding 2 or more complying IP addresses that sent the data at the same time, an amount of these transfers is calculated by adding them and this amount is then shown in a diagram. After reading the whole log file a diagram or a file is shown at the bottom of the window. The diagram is created by a Java library JFreechart and it shows the amount of transferred bytes. The x-axis represents the time and the y-axis represents the amount of transferred bytes. The created file is for next work with the calculated data and it can be loaded for example by Matlab or Octave. The first line in the file represents the time for axis x and the second one represents the amount of transferred bytes for axis y. These lines are followed by a command "plot(x,y)" for drawing a diagram.
|
|
|
Generator of ASP pages
Hrbáček, Martin ; Míča, Ivan (referee) ; Kacálek, Jan (advisor)
Submisson of my project is identification with background ASP.NET and realization program for creating ASP pages based on database structure. I began with my study from Microsoft .NET Framework, which provides all tools and technologies for creating .NET aplications. I described features a structure ASP.NET. I followed also, for my project, very important tool ADO.NET, which contains rich group of functions for manipulation with lot of date types. In text I also described object model of this tool. One of parts is about very important ObjectDataSource class. Next part of my project is devote to SQL database and tools for managing and manipulation. One chapters is devote to System register, which serve for database description. Next is described some of realization this type of program. My work is finished by description of my program. Here are aplications of mentioned technologies, which together forms web aplication and her output is web page for data presentation.
|
|
|
Neural networks in speaker classification
Svoboda, Libor ; Atassi, Hicham (referee) ; Míča, Ivan (advisor)
The content of this work is focused on the neural network per speaker recognition. The work deals with problems of processing speech signal and there are introduction some types of neural network. The part of work was made database of records from speakers with have various sex and ages. The train and test group was made from the database. For classifier were suggested afterwards. One of them was nominated on base Gaussian mixture model and three of them were nominated on neural. This system was tested and analyzed on the basis of age, gender and both criterions each other at the end. Attention is focused on choice suitable feature in each mission of classification at the same time. At the end of work are introduced results of analysis for individual groups and features. The most suitable features are diagnosed from given mission of classification and the most prosperous classifier.
|
|
|
Eye blink detection and recognition
Tesárek, Viktor ; Míča, Ivan (referee) ; Vlach, Jan (advisor)
This master thesis deals with the issues of the eye blink recognition from video. The main task is to analyse algorithms dealing with a detection of persons and make a program that could recognize the eye blink. Analysis of these algorithms and their problems are in the first part of this thesis. In the second part design and properties of my program are described. The realization of the program is based on the method of move detection using the accumulated difference frame, which helps to identify the eye areas. The eye blink detection algorithm tests a match between a tresholded pattern of the eye area taken from the actual frame and the frame before. The resolution whether the eye blink happened or not, is based on the level of the match. The algorithm is designed for watching a sitting man, which is slightly moving. The background can be a little dynamic as well. An average quality video with a moderator and dynamic backround was used as a tested subject.
|
|
|
Comparison of success rate of multi-channel methods of speech signal separation
Přikryl, Petr ; Zezula, Radek (referee) ; Míča, Ivan (advisor)
The separation of independent sources from mixed observed data is a fundamental problem in many practical situations. A typical example is speech recordings made in an acoustic environment in the presence of background noise or other speakers. Problems of signal separation are explored by a group of methods called Blind Source Separation. Blind Source Separation (BSS) consists on estimating a set of N unknown sources from P observations resulting from the mixture of these sources and unknown background. Some existing solutions for instantaneous mixtures are reviewed and in Matlab implemented , i.e Independent Componnent Analysis (ICA) and Time-Frequency Analysis (TF). The acoustic signals recorded in real environment are not instantaneous, but convolutive mixtures. In this case, an ICA algorithm for separation of convolutive mixtures in frequency domain is introduced and in Matlab implemented. This diploma thesis examines the useability and comparisn of proposed separation algorithms.
|
|
|
Application for content management of Internet pages
Kaplan, Jiří ; Míča, Ivan (referee) ; Kacálek, Jan (advisor)
This master’s thesis is focused on description of .NET Framework, versions, architecture, assembly and data formats. Describes programming language C#, his supporting programming processes and architecture. Contains description of ASP.NET, characteristics, used directories, control items and design model Model-View-Controller. Next part describes usability .NET background for creation of aplication and comparsion with PHP. Shortly introduces with ADO.NET, databinding, databases, his types and SQL language and content management system. At the end is desribed database structure of content management system, user administration and his parts and functions.
|
guest ::
