|
|
On-Line Speech Recognition Implementation with API and Android Demo app
Gabčo, Jakub ; Schwarz, Petr (referee) ; Szőke, Igor (advisor)
In modern times, people try everything to relieve. This may fulfill speechrecognition. Local speech recognition is computationally demanding, because of that many companies are trying to create a remote network speech recognition. In this thesis, we are focusing on creating a server for speech recognition, Android application and selecting appropriate protocol for communication between client and server. HTTP and Websocket protocol are analyzed her and differences and advantages between them.
|
|
|
Voice recognition of standard PILOT-CONTROLLER control commands
Kufa, Tomáš ; Polách, Petr (referee) ; Honzík, Petr (advisor)
The subject of this graduation thesis is an application of speech recognition into ATC commands. The selection of methods and approaches to automatic recognition of ATC commands rises from detailed air traffic studies. By the reason that there is not any definite solution in such extensive field like speech recognition, this diploma work is focused just on speech recognizer based on comparison with templates (DTW). This recognizor is in this thesis realized and compared with freely accessible HTK system from Cambrige University based on statistic methods making use of Hidden Markov models. The usage propriety of both methods is verified by practical testing and results evaluation.
|
|
|
Module for a Lecture Browser for Correcting the Output of Speech Recognizer
Srb, Pavel ; Schwarz, Petr (referee) ; Fapšo, Michal (advisor)
The core of my work is a browser upgrade, which contains user based transcript-correction from speech recognizer, including creation of transcription storage and sharing server. Introduction of my work mentions motivation for multimodal usage in computer science sphere. Further in text is list of speech recognition reasearch categories from Faculty of Information Technology. The main attention is given to description of multimodal browser used for browser technology testing and presentation. In future, the multimodal browser is supposed to be used as a study-utility or common user multimodal player. Required features of this player, concepts, realization description and whole C++, wxWidgets, XML, HTTP based architecture is defined.
|
|
|
Module for a Lecture Browser for Correcting the Output of Speech Recognizer
Srb, Pavel ; Schwarz, Petr (referee) ; Fapšo, Michal (advisor)
The core of my work is a browser upgrade, which contains user based transcript-correction from speech recognizer, including creation of transcription storage and sharing server. Introduction of my work mentions motivation for multimodal usage in computer science sphere. Further in text is list of speech recognition reasearch categories from Faculty of Information Technology. The main attention is given to description of multimodal browser used for browser technology testing and presentation. In future, the multimodal browser is supposed to be used as a study-utility or common user multimodal player. Required features of this player, concepts, realization description and whole C++, wxWidgets, XML, HTTP based architecture is defined.
|
|
|
On-Line Speech Recognition Implementation with API and Android Demo app
Gabčo, Jakub ; Schwarz, Petr (referee) ; Szőke, Igor (advisor)
In modern times, people try everything to relieve. This may fulfill speechrecognition. Local speech recognition is computationally demanding, because of that many companies are trying to create a remote network speech recognition. In this thesis, we are focusing on creating a server for speech recognition, Android application and selecting appropriate protocol for communication between client and server. HTTP and Websocket protocol are analyzed her and differences and advantages between them.
|
|
|
Voice recognition of standard PILOT-CONTROLLER control commands
Kufa, Tomáš ; Polách, Petr (referee) ; Honzík, Petr (advisor)
The subject of this graduation thesis is an application of speech recognition into ATC commands. The selection of methods and approaches to automatic recognition of ATC commands rises from detailed air traffic studies. By the reason that there is not any definite solution in such extensive field like speech recognition, this diploma work is focused just on speech recognizer based on comparison with templates (DTW). This recognizor is in this thesis realized and compared with freely accessible HTK system from Cambrige University based on statistic methods making use of Hidden Markov models. The usage propriety of both methods is verified by practical testing and results evaluation.
|
guest ::
