National Repository of Grey Literature 424 records found  1 - 10nextend  jump to record: Search took 0.01 seconds. 
Transcription and annotation components for web editor in React
Dugovič, Jakub ; Herout, Adam (referee) ; Szőke, Igor (advisor)
Cieľom tejto práci je implementovať modulárne užívateľské rozhranie na prepis zvukových nahrávok a ich anotáciu. Rozširuje dotrajšiu prácu s cieľom umožniť a zjednodušiť prácu s hodiny dlhými nahrávkami rozhovorov. Riešenie je implementované v TypeScripte pomocou Reactu a ďalších knižníc z reactového ekosystému. Aplikujúc princípy naštudované z literatúry, vyhýbajúc sa chybám identifikovaným počas prieskumu obdobnej platformy a overujúc užívateľské rozhranie počas vývoja pomocou kvalitatívneho testovania, vyvýjané rozhranie sa usiluje dosiahnuť vysokú mieru dobrej užívateľskej skúsenosti.
Automatic Transcription of Speech Supporting Code Switching
Bílek, Štěpán ; Karafiát, Martin (referee) ; Szőke, Igor (advisor)
This thesis addresses the issue of automatic speech recognition, focusing on the recognition of audio containing multilingual speech, known as code-switching. The problem of a lack of multilingual data for training is addressed by combining recordings in English and German. To achieve the closest approximation to real bilingual speech, a portion of the datasets is created by merging recordings of similar speakers. The Whisper model is trained and tested on the created data. In its original unadapted version, the model achieves an error rate of up to 70 %. The best models trained on combined datasets achieve error rates slightly above 7 %. The results of this study demonstrate methods for training models to achieve the best possible performance.
Controlling Mobile App by Voice
Cologna, Adam ; Szőke, Igor (referee) ; Herout, Adam (advisor)
The aim of this bachelor's thesis is to explore, analyze, and compare available libraries for controlling mobile applications with voice commands. According to the thesis requirements, I solved the problem primarily for the Android operating system. I have considered not only libraries for keyword detection but also those using the speech recognition technology. For the selected libraries, I conducted accuracy testing for voice command detection and performance testing. To facilitate the integration of the chosen libraries, an application was developed in the modern programming language Kotlin using Jetpack Compose. The main contribution of this work is the experiments carried out and the resulting recommendations regarding the examined libraries. Among the most effective solutions were those from Microsoft Azure and the Android Speech Recognizer class. The main obstacles for each library were the distance between the speaker and the microphone, as well as distracting background music.
Framework for event modeling a prediction in football.
Geffert, Maroš ; Beneš, Karel (referee) ; Szőke, Igor (advisor)
This thesis investigates current methods of predicting football events such as the number of goals in a match, the outcome of a match, or whether both teams will score. The models analyzed were neural network, RandomForest and XGBoost. Extensive historical data on matches and players were collected as part of the work. The main objectives were to determine whether detailed statistics significantly affect prediction, to evaluate the effectiveness of using betting odds as features, to investigate the impact of historical data on the quality of predictions, and to determine whether success can be achieved in the betting market with such models. The results showed that detailed statistics improve the accuracy of the predictions, but the use of odds as features generally degrades the predictions. The results regarding the use of historical data for predictions were inconclusive. RandomForest and neural network models achieved promising results with ROI of 32.38% and 29.04%, respectively.
Data augmentation integration into Pytorch
Vašina, Ladislav ; Polok, Alexander (referee) ; Szőke, Igor (advisor)
This thesis presents a tool that creates a unified, simple, and user-friendly interface on top of the audio augmentation libraries that can be used in conjunction with PyTorch library. The implemented tool offers the possibility to use a wide spectrum of augmentations from different libraries and offers easy application of those augmentations on the datasets. The support of the large range of augmentations could be only achieved by using multiple interfaces of the individual libraries. The tool can receive a list of augmentations from the user with its parameters and then it decides which of the integrated libraries it should use to apply that specific augmentation. The created tool was tested on the task of fine-tuning the automatic speech recognition system called Whisper. The main contribution of this work is that it provides a solution to a large number of libraries for the augmentation of audio data, where each library provides a different number and types of augmentations of audio, while also having different features and interfaces.
Automatic Transcription of Air-Traffic Communication to Text
Nevařilová, Veronika ; Veselý, Karel (referee) ; Szőke, Igor (advisor)
This thesis focuses on fine-tuning Whisper, an automatic speech recognition model developed by OpenAI, on Czech and English recordings of air-traffic communication. It provides a fundamental insight into automatic speech recognition, neural networks and transformer architecture. Further, data collection and annotation is also described and after that it details the process and outcomes of Whisper’s training on two different transcription formats – full, where the model learns to transcribe recordings word by word, and abbreviated, which is more suitable for quick navigation and more natural for air traffic controllers.
Simulace fotovoltaické elektrárny v rodinném domě
Gabrys, Adam ; Zachariáš, Michal (referee) ; Szőke, Igor (advisor)
This work deals with the simulation of a photovoltaic power plant system for a single-family house with subsequent optimization with respect to the return on investment. It emphasizes the visualization of the results and the possibility to include custom photovoltaic assemblies including inverter, photovoltaic panels and battery. The tool works with a three-phase system, where it is able to analyse the consumption of each phase and perform simulations with the power delivered from the solar panels. The optimization of the different components of the power plant is performed using a genetic algorithm. The simulation is implemented in Python based on object-oriented programming principles in order to allow the addition of new modules.
Framework for backtesting of algorithmic trading including the strategy improvement using the evolutionary algorithms.
Kmenta, Martin ; Plchot, Oldřich (referee) ; Szőke, Igor (advisor)
This thesis focuses on the development of an advanced framework for backtesting algorithmic trading strategies, emphasizing the optimization of strategies using evolutionary algorithms. It deals with the analysis and application of technical analysis in the trading context. It also focuses on the design and development of modules for efficient retrieving, processing, visualization, and analysis of various types of market data, allowing users to create and backtest their indicators and trading strategies using a robust framework.
Network Game: Destroy the Submarine
Jašek, Petr ; Mlích, Jozef (referee) ; Szőke, Igor (advisor)
This Bachelor's Thesis describes development of a simple network computer game. This thesis describes basic scheme of computer game development. Also an analysis of various implementation of network is made in this thesis. The output of this work is a computer program written in the C++ language. For implementation of the network the Boost 1.50.0 library was used. Network communication was implemented as client-server architecture with usage of the UDP protocol. For implementation of graphics and sound, the Allegro 5.0.7 library was used.
Smart Sheet Music Reader for Android
Smejkal, Vojtěch ; Herout, Adam (referee) ; Szőke, Igor (advisor)
Oblasti jako automatické otáčení stránek nebo automatický hudební doprovod jsou studovány již několik desetiletí. Tato práce shrnuje současné metody pro počítačové sledování not v reálném čase. Zabývá se také hudebními příznaky jako jsou chroma třídy a syntetizované spektrální šablony. Dále popisuje klíčové části systému jako krátkodobou Fourierovu transformaci a Dynamické borcení času. V rámci projektu byl navrhnut a vyvinut vlastní systém pro sledování pozice hráče v notách, který byl následně implementován jako mobilní aplikace. Výsledný systém dokáže sledovat i skladby s výrazně odlišným tempem, pauzami během hry nebo drobnými odchylkami od předepsaných not.

National Repository of Grey Literature : 424 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.