|
|
Voice Activity Detection
Břenek, Roman ; Grézl, František (referee) ; Matějka, Pavel (advisor)
This thesis describes techniques for voice activity detection in audio recordings. It is necessary to correctly classify all non-speech segments and recognize speech with noisy background. The whole process of voice activity detection (VAD) is described in this thesis, i.e. digitizing audio signal, feature extraction, training of the system, post-processing and final evaluation. There are three different systems compared within the thesis . The first one is based on phoneme recognition using neural network, the other two are variations of Gaussian Mixture Models (GMM). Each system was tested on three data sets - Tactical Speaker Identification Speech Corpus (TSID), Ham Radio (HR) and Rich Transcription Evaluation (RT05-RT07). The best results of each system are compared with the results of the third side.
|
|
|
The Design and Creation of Application for IPTV Kuki
Hošák, Dalibor ; Břenek, Roman (referee) ; Dydowicz, Petr (advisor)
This master‘s thesis is focused on design and development of 2048 game for IPTV service Kuki metropolitan network Netbox. The game is design to fit into Kuki like functionally and graphically. 2048 is implemented by javascript and it saves player's score to compare with others Kuki users. Statistical data are processed in the form of scenarios for future marketing campaign to increase sales of movies.
|
|
|
Automatické rozpoznávání zpěvu ptáků
Břenek, Roman
This master thesis deals with methods of automatic recognition of bird species by their voices. In first, I defined the database of records and created a reference data by handmade evaluation. The next step is to find the optimal features for describing a bird singing. I use a Human Frequency cepstral Coefficients (HFCC). For the best accuracy of recognition is necessary to correctly classify a bird's vocalization from a non-vocalization segments. The VAD system is based on an algorithm k-Nearest Neighbours. The last step describes the system based on Hidden Markov Models which allows to recognize the concrete bird species from the parts of bird's singing.
|
|
|
The Design and Creation of Application for IPTV Kuki
Hošák, Dalibor ; Břenek, Roman (referee) ; Dydowicz, Petr (advisor)
This master‘s thesis is focused on design and development of 2048 game for IPTV service Kuki metropolitan network Netbox. The game is design to fit into Kuki like functionally and graphically. 2048 is implemented by javascript and it saves player's score to compare with others Kuki users. Statistical data are processed in the form of scenarios for future marketing campaign to increase sales of movies.
|
|
|
Voice Activity Detection
Břenek, Roman ; Grézl, František (referee) ; Matějka, Pavel (advisor)
This thesis describes techniques for voice activity detection in audio recordings. It is necessary to correctly classify all non-speech segments and recognize speech with noisy background. The whole process of voice activity detection (VAD) is described in this thesis, i.e. digitizing audio signal, feature extraction, training of the system, post-processing and final evaluation. There are three different systems compared within the thesis . The first one is based on phoneme recognition using neural network, the other two are variations of Gaussian Mixture Models (GMM). Each system was tested on three data sets - Tactical Speaker Identification Speech Corpus (TSID), Ham Radio (HR) and Rich Transcription Evaluation (RT05-RT07). The best results of each system are compared with the results of the third side.
|
|
|
Automatické rozpoznávání zpěvu ptáků
Břenek, Roman
This master thesis deals with methods of automatic recognition of bird species by their voices. In first, I defined the database of records and created a reference data by handmade evaluation. The next step is to find the optimal features for describing a bird singing. I use a Human Frequency cepstral Coefficients (HFCC). For the best accuracy of recognition is necessary to correctly classify a bird's vocalization from a non-vocalization segments. The VAD system is based on an algorithm k-Nearest Neighbours. The last step describes the system based on Hidden Markov Models which allows to recognize the concrete bird species from the parts of bird's singing.
|
|
|
The use of segmentation in the on-line sales of selected travel agency
Juhaňáková, Veronika ; Vaško, Martin (advisor) ; Břenek, Roman (referee)
The aim of this thesis is to analyze the online sales of the travel agency New Travel.cz for the past year 2010 and then use the particular results of the analysis and find out and characterize the major market segments of this company. The travel agency gets through the market segmentation better general view of it's customers and consumer's behavior and comapny can effectively focusing their marketing activities. This analysis can be regarded as pilot project of the New Travel.cz., therefore, deals only with the sale of the previous year. This analysis will serve as a source of information needed to progression of the new generation database of tours and administrative interface of travel agency New Travel.cz.
|
guest ::
