|
|
Text to Audio Alignment
Šikula, Vojtěch ; Beneš, Karel (referee) ; Szőke, Igor (advisor)
This bachelors thesis is dealing with text to audio alignment. I present here works which are dealing with same problem. For evaluation have been used data from MGB Challenge 2015. Technique used here is using phoneme transcription and its alignment with transcript. Alignment was done with different models. The best results have been achieved by intersection of two alignments from models from good records.
|
|
|
Comparison of Two Audio Examples as an Android Application
Zhantemirov, Sultan ; Beneš, Karel (referee) ; Szőke, Igor (advisor)
This bachelor thesis deals with an implementation of an Android application for comparison of two audio examples by using special technics. The goal of the fnal program is a simple demonstration of comparison algorithm and it’s acceleration. The frst part of this thesis is concerned with theoretical analysis and suggestion for the comparison, while following parts review implementation, acceleration and testing of the algorithm in scope of final demo application.
|
|
|
Chatbot Based on Artificial Neural Networks
Čechák, Jiří ; Beneš, Karel (referee) ; Szőke, Igor (advisor)
The thesis describes an implementation and the way generative chatbot operates. The chatbot was implemented in Python using artificial neural networks and is based on a sequence-to-sequence principle. The final chatbot contains three models, which can be trained and used for conversations in a created GUI. After training of all three models, the chatbot was then tested by using BLEU metric. It was also tested by some users who compared the quality of its generated answers with the quality of answers created by already an existing chatbot Cleverbot. For a better understanding of the given problematics, there is a simple description of the basic terms, such as artificial intelligence, artificial neural networks, the difference between closed and open domain, word embedding and a basic description of the chatbots and their types, including their advantages, disadvantages and usage.
|
|
|
Chatbot Capable of Information Search
Ďurista, Michal ; Beneš, Karel (referee) ; Černocký, Jan (advisor)
Pojem ''chatbot'' je v dnešnej dobe umelej inteligencie veľmi populárny výraz. Chatbotov vidno stále viac a viac v biznis riešeniach dnešných firiem. Hlavným cieľom práce je vytvoriť algoritmus, ktorý je schopný vyťahovať informácie a implementovať ho do chatbota. Tieto informácie možno nájsť na webových stránkach reálneho zákazníka. Práca rovnako poskytuje prehľad súčasnej situácie chatbotov ako aj Microsoft technológií pre ich vývoj. Technické detaily na ktorých tieto technológie pracujú, predovšetkým spracovanie prirodzeného jazyka, sú taktiež zahrnuté. Práca popisuje implementáciu algoritmu ako aj chatbota samotného spolu s procesom testovania v skutočnom priemyselnom prostredí.
|
|
|
Artificial Poet
Bančák, Michal ; Szőke, Igor (referee) ; Beneš, Karel (advisor)
The paper presents a work on automatic poetry generation using the Long Short-TermMemory recurrent neural network. The aim of this work is to create an application thatimitates the writing of poems. This is a character-level language modeling in the Slovaklanguage. The neural network model used in the work consists of three layers of LSTM,with 400 hidden units. A collection of poems in the Slovak language with a size of 900k characters was also created for this work. . The final model is generating text that has poemelements. Achieved accuracy of generation is 41.85%.
|
|
|
Finite State Grammars and Language Models for Automatic Speech Recognition
Beneš, Karel ; Glembek, Ondřej (referee) ; Hannemann, Mirko (advisor)
Tato práce se zabývá transformací bezkontextových gramatik na váhované konečně stavové převodníky. Je vybrána podmnožina bezkontextových gramatik, kterou lze tranformovat přesně. Je představen test, zda daná gramatika naleží do této podmnožiny, i algoritmus převodu. Dále je popsán vlastní nástroj, který tyto postupy implementuje, včetně způsobu zpracování vstupu a výstupu. S použitím toho nástroje byl vytvořen systém rozpoznání řeči pro kokpit letadla. Jsou představeny výsledky ukazující, že systém založený na takto získaném modelu jazyka podává výrazně lepší výkon, než je dosažen při použití obecného modelu.
|
|
|
Neural Network Training Progress Visualization
Němcová, Silvie ; Baskar, Murali Karthick (referee) ; Beneš, Karel (advisor)
Tato práce se zabývá studiem průběhu trénování modelu neuronové sítě. Cílem je zobrazit a zkoumat trénovací proces modelu neuronové sítě. Pro tyto účely jsem zvolila implementaci v jazyce Python. Implementace úspěšně replikuje vizualizaci průběhu trénování pommocí lineární interpolace, identifikaci robustních a ambient vrstev a zobrazení plochy, vytvořené účelovou funkcí okolo natrénovaného modelu. V této práci je navržena a představena metoda zobrazovaní průběhu trénování pomocí kvadratické interpolace parametrů. Výsledek práce je znázorněn grafy a diskuzí nad dopady změn parametrů modelu na jeho trénování.
|
|
|
Modelling Music Waveforms Using Wavenet
Slanináková, Terézia ; Landini, Federico Nicolás (referee) ; Beneš, Karel (advisor)
This thesis focuses on exploring the possibilities of modelling music and speech with WaveNet, a deep neural network for generating raw audio waveforms. Using existing implementations, WaveNet was trained on multiple datasets and produced several audio files. Multiple experiments were carried out with various hyperparameter setups of WaveNet to find the optimal settings for the best results. Furthermore, multiple generation schemes were used, each having varying impact on the quality of generated audio. This quality was evaluated using human assessment via a questionnaire, where the musical samples were rated with a score 2-3.1818 on a 5 point scale, which is comparable to the rating of referential audio from the original WaveNet paper (3.1818).
|
|
|
Algorithmic Trading Using Artificial Neural Networks
Poláček, Samuel ; Beneš, Karel (referee) ; Szőke, Igor (advisor)
Algorithmic trading of many kinds of assets is not a new field at all. Domain of neural networks provides many tools, which are usefull in this field. This bachelor thesis discusses cryptocurrency trading algorithms using artificial neural network. In theoretical section of this thesis the basic theory and terms the stock market trading is based on is discussed. After the basic idea of cryptocurrencies is defined and used technical tools are introduced, the practical section starts. Sufficient configuration of neural network topology and hyperparameters values are obtained by many experiments. Subsequently after many experiments with indicators of technical analysis, acceptable neural network input configuration is obtained. Created neural network model combined with defined trading strategy generates profit.
|
|
|
Chatbot Based on Artificial Neural Networks
Richtarik, Lukáš ; Beneš, Karel (referee) ; Szőke, Igor (advisor)
This work deals with the issue of chatbots, which are based on artificial neural networks and generative models. It also describes options and process of designing the chatbot as well as an implementation and testing using BLEU metrics. The work contains multiple experiments with different models of chatbots, their performance evaluation and comparison, user experience and several suggestions for future enhancements.
|
guest ::
RSS feed.