|
|
Chatbot Based on Artificial Neural Networks
Červíček, Petr ; Novotný, Ondřej (referee) ; Szőke, Igor (advisor)
The thesis pursues the implementation of the chatbot based on neural networks. It uses Long short term memory networks, which remember long-term dependencies. Chatbot was implemented in Python with superstructure Keras and is based on sequence-to-sequence. Chatbot was also tested by BLEU and given to users, who chatted with the chatbot. For a better understanding of the given problematics, there is simple description of the chatbot history and used technologies.
|
|
|
Improving Robustness of Speaker Recognition using Discriminative Techniques
Novotný, Ondřej ; Ferrer, Luciana (referee) ; Pollák, Petr (referee) ; Černocký, Jan (advisor)
Tato práce pojednává o využití diskriminativních technik v oblasti rozpoznávání mluvčích za účelem získání větší robustnosti těchto systémů vůči vlivům negativně ovlivňující jejich výkonnost. Mezi tyto vlivy řadíme šum, reverberaci nebo přenosový kanál. Práce je rozdělena do dvou hlavních částí. V první části se věnujeme teoretickému úvodu do problematiky rozpoznávání mluvčích. Popsány jsou jednotlivé kroky rozpoznávacího systému od extrakce akustických příznaků, extrakce vektorových reprezentací nahrávek, až po tvorbu finálního rozpoznávacího skóre. Zvláštní důraz je věnován technikám extrakce vektorové reprezentace nahrávky, kdy popisujeme dvě rozdílná paradigmata možného přístupu, i-vektory a x-vektory. Druhá část práce se již více věnuje diskriminativním technikám pro zvýšení robustnosti. Techniky jsou organizovány tak, aby odpovídaly postupnému průchodu nahrávky rozpoznávacím systémem. Nejdříve je věnována pozornost předzpracování signálu pomocí neuronové sítě pro odšumění a obohacení signálu řeči jako univerzální technice, která je nezávislá na následně použitém rozpoznávacím systému. Dále se zameřujeme na využití diskriminativního přístupu při extrakci příznaků a extrakci vektorových reprezentací nahrávek. Práce rovněž pokrývá přechod od generativního paradigmatu k plně diskriminativnímu přístupu v systémech pro rozpoznávání mluvčích. Veškeré techniky jsou následně vždy experimentálně ověřeny a zhodnocen jejich přínos. V práci je navrženo několik přístupů, které se osvědčily jak u generativního přístupu v podobě i-vektorů, tak i u diskriminativních x-vektorů, a díky nim bylo dosaženo významného zlepšení. Pro úplnost jsou, v oblasti problematiky robustnosti, do práce zařazeny i další techniky, jako je normalizace skóre, či více-scénářové trénování systémů. Závěrem se práce zabývá problematikou robustnosti diskriminativních systému z pohledu dat využitých při jejich trénování.
|
|
|
Robust Speaker Verification
Profant, Ján ; Novotný, Ondřej (referee) ; Matějka, Pavel (advisor)
The goal of this paper is to analyze the impact of codec degraded speech on a state-ofthe-art speaker recognition system. Two feature extraction techniques are analyzed - Mel Frequency Cepstral Coefficients (MFCC) and the state-of-the-art system using Bottleneck features together with MFCC. Speaker recognition system is based on i-vector and Probabilistic Linear Discriminant Analysis (PLDA). We compared scenarios where PLDA is trained only on clean data, then system where we added also noise and reverberant data, and at last, codec degraded speech. We evaluated the systems on the matched conditions (data from the same codec are seen with PLDA) and also mismatched conditions (PLDA does not see any data from the tested codec). We experimented also with recently introduced technique for channel adaptation - Within-class Covariance Correction (WCC). We can see clear benefit of adding transcoded data to PLDA or WCC (with approximately same gain) for both tested conditions (matched and mismatched).
|
|
|
Web-Based Demonstration of Linear Filtering
Novotný, Ondřej ; Bařina, David (referee) ; Černocký, Jan (advisor)
The aim of this work is to create a demonstration application of discrete linear filtering. The introductory section summarizes the theory of digital filtering and filter design. The following chapter describes the existing applets. Subsequently, the concept of the demonstration and its implementation are described. The final part contains tutorial examples of using the demonstration and summary of users' reactions.
|
|
|
Voice Conversion
Hodaň, David ; Novotný, Ondřej (referee) ; Černocký, Jan (advisor)
Voice conversion is the process of transformation of speech parameters belonging to one speaker in such a way that his/her speech sounds as spoken by someone else. This thesis presents a short summary of several techniques currently used for conversion. First, the theory of voice creation with an emphasis on key atributes that characterize and identify a speaker’s voice is described. Methods for voice modification are discussed, together with the advantages and pitfalls that predetermine the use-cases for suitable application of these methods. A high-level overview of how speech is transformed between the source and the target speakers is presented. This description is subsequently used to design a voice conversion system that is aimed to demonstrate one of the possible approaches to the conversion problem. The process of conversion consists of two phases: training and synthesis. As part of this project, a computer program for voice conversion based on the MATLAB programming environment has been developed. Its design, implementation and results are discussed.
|
|
|
Mechanical excitation of self sensing SPM probes
Novotný, Ondřej ; Piastek, Jakub (referee) ; Pavera, Michal (advisor)
This bachelor thesis deals with the development of the SPM microscope probe holder which is designed for mechanical excitation of the probes. The first part of the thesis focuses on the description of physical theory, such as the principle of atomic force microscopy, the function of piezoceramics and the description of used quartz tunning fork based probes. The second part describes the gradual development and design of the new probe holder. Testing of the designed probe holder and comparison of mechanical and electric excitation is depicted at the end of this work. The designed probe holder was manufactured, the assembly procedure was described, and the drawings of the individual parts were created.
|
|
|
Slide adjustment of mechanical press
Novotný, Ondřej ; Pavlík, Jan (referee) ; Omes, Jiří (advisor)
The bachelor's thesis deals with the design of a slide adjustment of mechanical press for double-point mechanical press with nominal force 3150 kN. This thesis also includes the design of the kinematic diagram of the slide adjustment, design of the pressure point and drawing documentation. First part of the thesis is focused on the problematic, especially regulation of shut height. Next chapter is about overload protection, which is important for properly and safety working proces. I the second part, there is created kinematic mechanism and design of pressure points which are made in Autodesk Inventor Professional 2017. Last chapter includes valorization of pressure points design. The pressure point with the most advatages is chosen for the final slide adjustment mechanism. For the final mechanism is made a calculation and drawing documentation.
|
|
|
Acoustic Detection of Speaker Position Using Microphone Array
Pelz, Zdeněk ; Novotný, Ondřej (referee) ; Szőke, Igor (advisor)
This thesis explores problematics of speaker localization using microphone array. Aim of this thesis is implementation of algorithms for speaker localization and experiments with those algorithms. Calculation of TDOA was done using cross-correlation and hyperbolic method was used to calculate position estimation. Finished microphone array is able to locate speaker within certain variance. Results of this thesis allow reader to make assumptions regarding accuracy of localisation using microphone array and ARM kit with limited performance. Precision of position estimation using microphone array reached several decimeters, but this precision is dependent on distance from microphone array.
|
|
|
Correlated probe and electron microscopy for the study of modern magnetic nanomaterials
Novotný, Ondřej ; Flajšman, Lukáš (referee) ; Pavera, Michal (advisor)
High pressure on the development of new magnetic materials and their miniaturization also emphasizes the development of new analytical techniques. This diploma thesis deals with the development and demonstration of correlated magnetic force and electron microscopy, which is a promising tool for the characterization of magnetic nanomaterials. The first part of this thesis describes the fundamental physics of micromagnetism with a focus on cylindrical nanofibers. The following pages describe optic, probe, electron, and synchrotron methods for mapping the magnetic properties of materials. The next part describes magnetic domain wall motion in cylindrical nanowires performed as a part of a more extensive material study. The last part of the thesis describes the development of correlated magnetic force and electron microscopy on LiteScope device. A production of magnetic probes was designed and successfully tested. Probes were fabricated by focused electron beam-induced deposition from the Co2(CO)8 precursor. Further, the developed correlated microscopy is demonstrated on a multilayer PtCo sample, magnetic cylindrical nanofibers, NiFe vortex structures, and FeRh metamagnetic nano-islands.
|
|
|
Web-Based Demonstration of Linear Filters Design
Pospíšil, Ondřej ; Černocký, Jan (referee) ; Novotný, Ondřej (advisor)
The aim of this work is to create a demonstration application focused on the design of digital filters. In the first chapters we outline the theory of digital filtration and design of digital filters. Then we summarize and evaluate the existing solutions. The following chapters describe the design and implementation of the actual application.
|
guest ::
RSS feed.