|
|
Digital Text Steganography
Nodžák, Petr ; Nevoral, Jan (referee) ; Strnadel, Josef (advisor)
The goal of this bachelor project was to learn about digital text steganography, about methods for hiding the text, to implement my own or already existing methods and finally to compare acomplished results of these methods. This project introduces four methods (Zero distribution, semathics, syntax and Format based) which hide secret data into cover text, each of them by its own way. Research has found that semanthics method produces the best properties of stego text followed by Format based and Zero distribution, syntax method ended up worst. Based on the data found we can choose which method we will use.
|
|
|
Automatic Chord Recognition Using Deep Neural Networks
Nodžák, Petr ; Bidlo, Michal (referee) ; Vašíček, Zdeněk (advisor)
This work deals with automatic chord recognition using neural networks. The problem was separated into two subproblems. The first subproblem aims to experimental finding of most suitable solution for a acoustic model and the second one aims to experimental finding of most suitable solution for a language model. The problem was solved by iterative method. First a suboptimal solution of the first subproblem was found and then the second one. A total of 19 acoustic and 12 language models were made. Ten training datasets was created for acoustic models and three for language models. In total, over 200 models were trained. The best results were achieved on acoustic models represented by convolutional networks together with language models represented by recurent networks with LSTM modules.
|
|
|
Automatic Chord Recognition Using Deep Neural Networks
Nodžák, Petr ; Bidlo, Michal (referee) ; Vašíček, Zdeněk (advisor)
This work deals with automatic chord recognition using neural networks. The problem was separated into two subproblems. The first subproblem aims to experimental finding of most suitable solution for a acoustic model and the second one aims to experimental finding of most suitable solution for a language model. The problem was solved by iterative method. First a suboptimal solution of the first subproblem was found and then the second one. A total of 19 acoustic and 12 language models were made. Ten training datasets was created for acoustic models and three for language models. In total, over 200 models were trained. The best results were achieved on acoustic models represented by convolutional networks together with language models represented by recurent networks with LSTM modules.
|
|
|
Digital Text Steganography
Nodžák, Petr ; Nevoral, Jan (referee) ; Strnadel, Josef (advisor)
The goal of this bachelor project was to learn about digital text steganography, about methods for hiding the text, to implement my own or already existing methods and finally to compare acomplished results of these methods. This project introduces four methods (Zero distribution, semathics, syntax and Format based) which hide secret data into cover text, each of them by its own way. Research has found that semanthics method produces the best properties of stego text followed by Format based and Zero distribution, syntax method ended up worst. Based on the data found we can choose which method we will use.
|
guest ::
