National Repository of Grey Literature 220 records found  1 - 10nextend  jump to record: Search took 0.01 seconds. 
Web Application for Learning of Guitar Playing
Mikota, Michal ; Černocký, Jan (referee) ; Szőke, Igor (advisor)
Tools for teaching musical instruments have been with us for hundreds of years and, like everything else, have gradually adapted to the present day. However, a large number of these applications are overly complex, confusing, and generally unfriendly for their users. At the same time, there are only a handful of apps that have an implemented feature of real-time detection of the played note by the player, which is very desirable and necessary for beginner and moderately advanced guitar players. This bachelor thesis demonstrates and explains the implementation of the various tools needed for teaching using techniques for dominant frequency detection and filtering out unwanted audio artifacts using an algorithm from the field of convolutional neural networks. At the same time, the goal is to focus on the robustness of the algorithm, i.e., it can detect and determine the played tone on the guitar even in noisy environments. The algorithm used by the individual tools developed within this application, combined with a simple user interface, provide the alternative for teaching how to play guitar.
Web Application for Learning of Guitar Playing
Mikota, Michal ; Černocký, Jan (referee) ; Szőke, Igor (advisor)
Tools for teaching musical instruments have been with us for hundreds of years and, like everything else, have gradually adapted to the present day. However, a large number of these applications are overly complex, confusing, and generally user-unfriendly for their users. At the same time, there are only a handful of apps that have an implemented feature of real-time detection of the played note by the player, which is very desirable and necessary for beginner and slightly advanced guitar players. This bachelor thesis demonstrates and explains the implementation of the various tools needed for teaching using techniques for dominant frequency detection and filtering out unwanted audio artifacts using an algorithm from the field of convolutional neural networks. At the same time, the goal is to focus on the robustness of the algorithm, i.e., it can detect and determine the played tone on the guitar even in noisy environments. The algorithm used by the individual tools developed within this application, combined with a simple user interface, provide the alternative for teaching how to play guitar
Adding Flight Trajectory of VHF Communication with Transcription
Rajko, Adam ; Herout, Adam (referee) ; Szőke, Igor (advisor)
The aim of this project is to create an application for adding speech communication between the pilot and ATC (Air Traffic Control) to the flight trajectory of the aircraft. The inspiration for this work is the ATCO2 project. Based on the studied mapping frameworks and services providing aircraft position information, an application design has been performed. Based on the design and used technologies, the application was successfully implemented. The resulting functionality of the application was tested on users using a questionnaire.
Automatic Transcription of Air-Traffic Communication to Text
Balok, Petr ; Karafiát, Martin (referee) ; Szőke, Igor (advisor)
This thesis solves the problem of getting text transcription from audio files containing air-traffic communication and audio files containing speech in two languages. I solved this problem using machine learning, specifically by using toolkits written in Python called NeMo and Whisper. Before fine-tuning, I got a 78 % word error rate on an ATC dataset and a 60 % word error rate on a bilingual dataset. Using these technologies, I managed to lower the word error rate to 24 % in transcriptions of air-traffic communication. I also got a 19 % word error rate for bilingual speech. The results of this thesis allow automatic transcription of air-traffic communication with a low rate of errors in the transcript. Furthermore, models trained on bilingual dataset allow transcribing audio files containing both English and Czech speech in one file.
Conference System for Excel@FIT
Kobelka, Martin ; Szőke, Igor (referee) ; Veigend, Petr (advisor)
The main goal of this thesis is to initially conduct a detailed analysis of the issues related to organizing scientific conferences while focusing on the workflow of the Excel@FIT conference and subsequently mapping the workflow of several other conferences organized in the field of information technology in the theoretical part. Then, in the practical part, the task is to design an information system specifically for the Excel@FIT conference and implement it in the form of a web application. The resulting web application for conference administration is developed using the programming languages PHP and TypeScript. The client side is designed as a single-page web application that communicates with the server side through REST API. The application ensures efficient and smooth conference management, registering and reviewing papers and generating exports for evaluation committees. The output is a fully functional application that has been tested on data from previous years and can be easily extended with new functionalities if needed.
The Best Possible Speech Recognizer on Your Own Data
Sýkora, Tomáš ; Veselý, Karel (referee) ; Szőke, Igor (advisor)
Denno-denne vzniká množstvo špičkových objavov v oblasti strojového učenia. Prispôsobením týchto sýstémov tak, aby čo najlepšie fungovali iba na obmedzenej podmnožine všeobecných dát, môžu byť dosiahnuté výrazné zlepšenia v prenosti. Prispôsobením automatického rozpoznávača reči na doménovo špecifické dáta je možné vytvoriť produkt dosahujúci omnoho lepšie výsledky ako rozpoznávač reči natrénovaný na všeobecných dátach. Táto práca prezentuje 17-percentné zlepšenie chybovosti prepísaných slov oproti automatickému rozpoznávaču reči ponúkaného službou Google Speech. Toto zlepšenie bolo dosiahnuté precíznou anotáciou a prípravou doménových dát a kombináciou špičkových techník a algoritmov v oblasti automatického rozpoznávania reči. Popísaný systém bol úspešne nasadený do výrobného prostredia transkripčnej spoločnosti Parrot, ktorej súčasťou som od jej začiatku. Nasadený systém výrazne zvýšil efektivitu zamestancov používajúcich výstup popísaného rozpoznávača.
Answer Correctness Estimation on a Question
Ligocký, Marián ; Kesiraju, Santosh (referee) ; Szőke, Igor (advisor)
Odhad správnosti odpovede na otázku je kritický pre aplikácie na výučbu jazyka, kde sa očakáva odpoveď v podobe vety. Možný prístup je spočítať sémantickú podobnosť vstupnej vety a vopred definovných správnych odpovedí. Skóre podobnosti študentovej a správnej odpovede môže byť vypočítané pomocou hlbokých jazykových modelov, založených na architektúre transformerov. Pre získanie podobnosti viet (STS) sme preskúmali rôzne modely. Najlepší model stsb-TinyBERT-L-4 (cross-encoder) vylepšuje pôvodný model o 27.8% (stredná kvadratická chyba) na reálnych odpovediach študentov, oskórovaných učiteľom a kalibrovaných lineárnou regresiou. Označenia NLI môžu zlepšiť výsledky, ale je nutný ďalší výskum.
Automatic Speech Detection for VHF Channel
Nováková, Mária ; Veselý, Karel (referee) ; Szőke, Igor (advisor)
Výskyt hluku a šumu v pozadí audio leteckej komunikácie je problémom, ktorému denne čelia operanti riadenia letovej prevádzky. Aby bola zaistená bezpečná letecká preprava, komunikácia medzi vežou a lietatlom musí byť čo najefektívnejšia. Hlavnú rolu vo vylepšovaní kvality komunikácie hrá detekcia hlasovej aktivity. Správna detekcia reči je nevyhnutá pre rozpoznanie začiatku komunikácie pre systémy. Začiatok komunikácie začína stlačením tlačítka push-to-talk pomocou rádiového systému. Na rozpoznávanie reči existujú rôzne prístupy a implementácie. Za pomoci neurónových sietí sa dá detekcia reči upresniť. Výhodou používania umelej inteligencie je jej adaptácia na nové podnety. Táto práca ponúka riešenie na detekciu reči a push-to-talk udalostí v leteckej komunikácií. Navrhnuté riešenia budú evaluované a porovnané. Na záver, dostupná implementácia GPVAD je prepracovaná na riešenie tohto problému. Strojové učenie má zas a znova príležitosť predviesť svoje schopnosti.
Call Sign Detection and Recognition in VHF Communication
Dedič, Juraj ; Kocour, Martin (referee) ; Szőke, Igor (advisor)
This work explores the processing of data from air traffic communication in order to detect and recognize the~call signs it contains. Particularly it involves recognizing these call signs in human made and automated text transcripts of the communication between pilots and air traffic controllers. The thesis compares various ways of solving this and describes their problems. It implements a system for the identification of these call signs using a suitable technology based on large language models. One of the outputs of this work is a service that is able to distinguish the call signs, which enables indexation and sorting of this data in an efficient way.
Conference System for Excel@FIT
Kobelka, Martin ; Szőke, Igor (referee) ; Veigend, Petr (advisor)
he main goal of this work is to analyze the scientific conference in the theoretical part, and to describe the issues of organizing a scientific conference. Further map the workflow of several conferences organized in information technology. Furthermore, the Excel @ FIT conference had to be analyzed in detail. In the practical part for this conference to design an information system, and implement this system as a web application. The resulting web application for conference administration is programmed using PHP and TypeScript programming languages. The client part is designed as a one-page web application communicating with the server part using the REST API. The application enables efficient and seamless conference management, article writing and review, and export creation for commissions. The result is a fully functional application tested on previous years' data, which can be easily extended with new functionality if required.

National Repository of Grey Literature : 220 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.