|
|
Fixed-Point Implementation Speech Recognizer
Král, Tomáš ; Černocký, Jan (referee) ; Burget, Lukáš (advisor)
Master thesis is related to the problematics of automatic speech recognition on systems with restricted hardware resources - embedded systems. The object of this work was to design and implement speech recognition system on embedded systems, that do not contain floating-point processing units. First objective was to choose proper hardware architecture. Based on the knowledge of available HW resources, the recognition system design was made. During the system development, optimalization was made on constituent elements so they could be mounted on chosen HW. The result of the the project is successful recognition of Czech numerals on embedded system.
|
|
| |
|
|
Text to Audio Alignment
Šíma, Tomáš ; Baskar, Murali Karthick (referee) ; Szőke, Igor (advisor)
The purpose of this work is to research existing text-to-speech aligning algorithms. We chose an implementation of one these algorithms, based on Hidden-Markov Joint-Sequence Models, and we explored its strengths, quirks and weaknesses. We explored whether it is possible to predict the alignment accuracy using probability values generated from Viterbi algorithm and the beam search value. Our testing data comes from the BBC as part of MGB Challenge 2015. This data creates, with its high content diversity, near perfect testing set to prove our algorithm is flexible and error independent.
|
|
|
Character recognition in the soundtrack with SOM
Malásek, Jan ; Honzík, Petr (referee) ; Honzík, Petr (referee) ; Pohl, Jan (advisor)
This bachelor´s thesis describes a history of neural networks evolution and their using in speech recognition systems and shows problems with working and learning neural networks. It presents three chosen systems for speech recognition including their evaluation in experiments, their advantages and disadvantages. It is also about human speech characteristics and systems of its recognition. The last part is focused on frequency spectrums of different types of vowels and gives instructions for programming neural networks using MATLAB.
|
|
|
Mouse-Less Keyboard-Less Human-Computer Interaction
Jaroň, Lukáš ; Mlích, Jozef (referee) ; Beran, Vítězslav (advisor)
In this Bachelor thesis are described suggestions of ways you can control the computer without a mouse and keyboard, just motion of hand, and user interfaces. Then there is the theory describes tools used to develop experimental applications that simulate the proposed interface. And the entire development cycle from problem analysis, specification and implementation, to testing of final application. The result of this work is the interface, that can recognize eight different hand movements and use them as input to the system.
|
|
|
Handwriting Recognition
Zouhar, David ; Řezníček, Ivo (referee) ; Mlích, Jozef (advisor)
This bachelor thesis deals with the handwritten character recognition in real time. It describes the ways how to obtain information for the text recognition, methods used in classification and it describes application made for getting text from drawn characters. It is also engaged in evaluation the created application. It deals with the experiments that were conducted to improve success of recognition. Thanks to the experiments, the success that was achieved was approximately 85%.
|
|
|
Gene Detection in DNA Sequences
Višňovský, Marek ; Burgetová, Ivana (referee) ; Martínek, Tomáš (advisor)
The main goal of this work is to create a method for gene prediction in prokaryotic genomes, which will be later demonstrated and tested on Escherichia coli. The first chapter contains a short introduc-tion into molecular biology. In the second one, we take a closer look on current methods of gene de-tection and prediction and the work ends with an application of acquired knowledge on gene predic-tion mostly using position weight matrices.
|
|
|
Kinect-Based Gesture Recognition
Zapletal, Filip ; Šolony, Marek (referee) ; Žák, Pavel (advisor)
This paper describes methods of obtaining position data of individual body parts using different technologies, with particular focus on Kinect. Based on this knowledge was designed and implemented library for the detection of dynamic motion gestures, which has been tested on a set of designed gestures.
|
|
| |
|
|
Gesture Recognition
Svoboda, Tomáš ; Mlích, Jozef (referee) ; Hradiš, Michal (advisor)
This Bachelor's thesis is engaged in recognition hand gestures. The advantages and disavantages of various color models for skin color detection are discussed here. Skin is detected by look-up table. Look-up table is created from histogram of skin color and optional from Gaussian distribution, whose parameters are estimated from histogram. Hidden Markov models are used for gesture classification. The HTK toolkit have been used for working with the models. Own decoder of Hidden Markov models based on Viterbi algorithm was created for real-time gesture recognition. Several experiments were accomplished with data sets for 4 gestures. The results of the experiments are very good.
|
guest ::
