National Repository of Grey Literature 79 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Neural Language Model Acceleration
Labaš, Dominik ; Černocký, Jan (referee) ; Beneš, Karel (advisor)
This work adresses the topic of neural language model acceleration. The aim of this work is to optimize model of a feed-forward neural network. In accelerating of the neural network we used a change of activation function, pre-calculation of matrices for calculationg the hidden layer, implementation of the model's history cache and unnormalized model. The best-performing model was accelerated by 75.3\%.
Removal of a Known Signal from a Recording
Urbánek, Radomír ; Žmolíková, Kateřina (referee) ; Černocký, Jan (advisor)
The goal of this diploma thesis is to design and implement method for removing known signal from recorded sound. In the introductory part of the thesis are described the properties of sound and its propagation through the space, digital signal processing on the computer and the computing of the system impulse response. The sequential development of the methods leading to the removal of the known signal from the recording is described further. The following part contains a description and implementation of this method. It also describes how and at what data the method will be tested. Finally, testing is evaluated, improvements and further possible work is proposed.
Voice Conversion
Brukner, Jan ; Plchot, Oldřich (referee) ; Černocký, Jan (advisor)
Thesis deals with voice converion. Method, where we want to modify speech parameters of source speaker into that of a target speaker. At the beginning of thesis is described Voice Conversion Challenge (VCC), where participants tried to build better voice conversion systems. In the next part are analysed components of baseline system used in VCC. Modifications which could improve quality of converted voice are proposed. Then is briefly described implementation if these modifications and results are analysed. In the end is part dedicated to further improvements of voice conversion.
Neural Network Based Dereverberation
Karlík, Pavol ; Černocký, Jan (referee) ; Žmolíková, Kateřina (advisor)
In the past years, the usage of neural networks in speech processing has increased significantly. This thesis focuses on implementing and evaluating a speech dereverberation framework that utilizes a deep neural network (DNN) to estimate the power spectral density of the signal. The proposed framework is based on the state-of-the-art speech enhancement algorithm called Weighted prediction error (WPE), which is known to effectively reduce reverberation from the speech signal. This thesis summarizes the theory of dereverberation, neural networks and the Weighted prediction error algorithm. Different DNN architectures are experimented with and trained using different datasets with varying properties. The results have shown that our framework is able to outperform the conventional WPE, especially in situations where duration of processed signal is short.
Human Presence Detection and Applications in Smart Home Environments
Dostál, Pavel ; Juránek, Roman (referee) ; Černocký, Jan (advisor)
Práce se zabývá studiem detekce a rozpoznávání člověka a následnou implementací v prostředí softwaru Home Manager, což je projekt simulující chytrý dům s intelligentními zařízeními. Rozšíření o funkcionalitu rozpoznání uživatelů a narušitelů umožní lépe přizpůsobit chování zařízení preferencím jednotlivých osob. Použití rozpoznávání je demonstrováno na ukázce ovládání klimatizace v místnostech podle přítomnosti uživatelů. 
Detection of Malicious Websites using Machine Learning
Šulák, Ladislav ; Černocký, Jan (referee) ; Beneš, Karel (advisor)
Táto práca sa zaoberá problematikou škodlivého kódu na webe so zameraním na analýzu a detekciu škodlivého JavaScriptu umiestneného na strane klienta s využitím strojového učenia. Navrhnutý prístup využíva známe i nové pozorovania s ohľadom na rozdiely medzi škodlivými a legitímnymi vzorkami. Tento prístup má potenciál detekovať nové exploity i zero-day útoky. Systém pre takúto detekciu bol implementovaný a využíva modely strojového učenia. Výkon modelov bol evaluovaný pomocou F1-skóre na základe niekoľkých experimentov. Použitie rozhodovacích stromov sa podľa experimentov ukázalo ako najefektívnejšia možnosť. Najefektívnejším modelom sa ukázal byť Adaboost klasifikátor s dosiahnutým F1-skóre až 99.16 %. Tento model pracoval s 200 inštanciami randomizovaného rozhodovacieho stromu založeného na algoritme Extra-Trees. Viacvrstvový perceptrón bol druhým najlepším modelom s dosiahnutým F1-skóre 97.94 %.
Electric Guitar to MIDI Conversion
Klčo, Michal ; Glembek, Ondřej (referee) ; Černocký, Jan (advisor)
Automatický přepis hudby a odhad vícero znějících tónu jsou stále výzvou v oblasti dolování informací z hudby. Moderní systémy jsou založeny na různých technikách strojového učení pro dosažení co nejpřesnějšího přepisu hudby. Některé z nich jsou také omezeny na konkrétní hudební nástroj nebo hudební žánr, aby se snížila rozmanitost analyzovaného zvuku. V této práci je navrženo, vyhodnoceno a porovnáváno několik systémů pro konverzi nahrávek elektrické kytary  do MIDI souború, založených na různých technikách strojového učení a technikách spektrální analýzy.
Neural Network Based Named Entity Recognition
Straková, Jana ; Hajič, Jan (advisor) ; Černocký, Jan (referee) ; Konopík, Miloslav (referee)
Title: Neural Network Based Named Entity Recognition Author: Jana Straková Institute: Institute of Formal and Applied Linguistics Supervisor of the doctoral thesis: prof. RNDr. Jan Hajič, Dr., Institute of Formal and Applied Linguistics Abstract: Czech named entity recognition (the task of automatic identification and classification of proper names in text, such as names of people, locations and organizations) has become a well-established field since the publication of the Czech Named Entity Corpus (CNEC). This doctoral thesis presents the author's research of named entity recognition, mainly in the Czech language. It presents work and research carried out during CNEC publication and its evaluation. It fur- ther envelops the author's research results, which improved Czech state-of-the-art results in named entity recognition in recent years, with special focus on artificial neural network based solutions. Starting with a simple feed-forward neural net- work with softmax output layer, with a standard set of classification features for the task, the thesis presents methodology and results, which were later used in open-source software solution for named entity recognition, NameTag. The thesis finalizes with a recurrent neural network based recognizer with word embeddings and character-level word embeddings,...
Tone and Chord Recognition as an Android Application
Kucharovič, Oliver ; Černocký, Jan (referee) ; Szőke, Igor (advisor)
The aim of this work is to recognize tones and chords on any musical instrument using the microphone on Android mobile devices. The app scans or records the sounds which are analyzed. It writes to a visual representation which is similar to the musical notation. The work describes the problems of recognition and the solution of the problem using fast Fourier transformation and analysis of the spectrum of volumes. Work describes the theory of music and the training of individual tones. The application was subjected to user tests and recognition accuracy tests. The conclusion includes tests results and statistics from the Google Play publication.
Signal Analyzer Based on DVB-T USB Tuner
Belica, Martin ; Grézl, František (referee) ; Černocký, Jan (advisor)
This bachelor thesis deals with the detection and analysis of a radio signals with the DVB-T USB tuner. The first step of the analysis is to capture some radio signal, in this case using a USB tuner. The next step is the appliction of signal processing algorithms. The most important algorithm for analysis is a discrete Fourier transform that is used to obtain a signal spectrum. Finally, several demodulation and filtering algorithms are used to better interpret the analyzed signal to the user.

National Repository of Grey Literature : 79 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.