|
|
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.
|
|
|
Use of 5G for control of Unmanned Aerial Vehicles
Nguyen, Van Phi ; Kyselák, Martin (referee) ; Číka, Petr (advisor)
Tato diplomová práce zkoumá možnost využití technologií 5G v rámci privátní 5G sítě Univerzity obrany (UNOB) v Brně, Česká republika, pro řízení bezpilotních létajících prostředků (UAVs). Výzkum poskytuje podrobnou analýzu leteckých komunikací u UAVs se zaměřením na aplikaci technologií 5G. Klíčovou součástí studie je návrh koncepčního designu pro testovací sestavy UAV a poskytnutí komplexního přehledu o provedení testovacích scénářů. Hodnocení každého scénáře je založeno na specifických měřených parametrech a metodologiích použitých pro tato měření. Dále práce hodnotí schopnosti dálkového ovládání UAV s podporou 5G z pozemní řídicí stanice prostřednictvím privátní 5G sítě, přičemž se zaměřuje na zpracování aplikačních dat přenášených touto sítí. Studie také zahrnuje hodnocení bezpečnostních rizik komunikace UAVs a potenciálních bezpečnostních důsledků privátní 5G sítě.
|
|
|
Speech Recognition for Air Traffic Communication
Žmolíková, Kateřina ; Burget, Lukáš (referee) ; Veselý, Karel (advisor)
This thesis deals with speech recognition. The aim is to build a speech recognition system based on neural networks and test it on recordings of air traffic communication. Final acoustic model will be used in project A-PiMod. The system reached word error rate 29.5%. Next task of this thesis was to experiment with neural networks which are part of acoustic model. First experiments explored its simplification and acceleration and its impact on error rate. Next experiments dealt with activation function rectifier and convolutional neural networks. Experiments with convolutional neural networks achieved 1.5% improvement, so the final result was 0.4% better than fully connected network with the same architecture.
|
|
|
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.
|
|
|
Speech Recognition for Air Traffic Communication
Žmolíková, Kateřina ; Burget, Lukáš (referee) ; Veselý, Karel (advisor)
This thesis deals with speech recognition. The aim is to build a speech recognition system based on neural networks and test it on recordings of air traffic communication. Final acoustic model will be used in project A-PiMod. The system reached word error rate 29.5%. Next task of this thesis was to experiment with neural networks which are part of acoustic model. First experiments explored its simplification and acceleration and its impact on error rate. Next experiments dealt with activation function rectifier and convolutional neural networks. Experiments with convolutional neural networks achieved 1.5% improvement, so the final result was 0.4% better than fully connected network with the same architecture.
|
guest ::
