|
|
Continously Learning Analyser of Audio-Visual Recordings
Košarko, Ondřej ; Peterek, Nino (advisor) ; Klusáček, David (referee)
This thesis introduces a tool for analysis of audiovisual records. The tool uses the audio and closed captions supplied by the user to prepare text annotation. The annotation contains a transcript of the show which is based on the closed captions. In addition, speaker diarization is performed to mark who spoke when. The diarization is performed by a third party library. The library is evaluated on data from DIALOG corpus. The inner workings of the library are described. To assign the right portions of the text to the right section of the record Kaldi, a speech recognition toolkit, is used. Furthermore the thesis contains an overview describing how closed captions are created; overview of speech corpora creation; and a brief review of literature on record analysis. 1
|
|
|
Frequency Spectrum Monitoring System
Hrach, Jan ; Klusáček, David (advisor) ; Mareš, Martin (referee)
We have created several programs to be used in the field of Software Defined Radio technology: (i) A channelizer, a tool that splits wideband signal into multiple narrowband channels that can be further processed, (ii) A SDR client, an interactive GUI tool that allows exploration of signals, (iii) A scanner. Our channelizer is several times faster than a popular GnuRadio implementation and our SDR software features a network-transparent architecture with one server and multiple concurrent clients. Powered by TCPDF (www.tcpdf.org)
|
|
|
New Methods in Statistical Speech Recognition
Klusáček, David ; Hajič, Jan (advisor) ; Psutka, Josef (referee) ; Černocký, Jan (referee)
Title: New Methods in Statistical Speech Recognition Author: David Klusáček Department: Institute of Formal and Applied Linguistics (ÚFAL), Faculty of Mathematics and Physics in Prague, Malostranské náměstí 25, 118 00 Praha 1. Advisor: Prof. RNDr. Jan Hajič, Dr., Institute of Formal and Applied Linguistics. Abstract: This works aims to identify limits of contemporary speech rec- ognizers and tries to come up with methods that could push back the fron- tiers. After describing the state of the art, the weakest link of the chain has been identified in the acoustic front-end, especially when working in harsh acoustic conditions. NUFIBA front-end, the proposed solution, includes re- verb compensation and speaker/background segmentation as well as contin- uous SNR monitoring which, thru cooperation with acoustic model, hinders from avalanche spreading of recognition errors. Owing to the lack of time, only a phoneme recognizer was finally implemented, although large blocks of originally intended word-based continuous speech recognizer were implemented and tested (such as the MMI-class based language model).
|
|
|
Price Explorer
Čížek, Vítězslav ; Klusáček, David (referee) ; Kocanda, Jiří (advisor)
The present work is focused on the problem of processing huge amount of information on the Internet. This task's importance is constantly growing in present days along with the increasing amount of available information. The goal was to develop an application that would solve this problem for one concrete, frequently used area and simplify the user the time-consuming task of data analysis. The program is designed for searching data occurring in on-line shop databases. The technologies used in this application were chosen in a way to satisfy two conditions: to facilitate usage to the end-user and at the same time to enable program's platform independence.
|
|
|
Automatic processing of law amendments
Mareček, David ; Klusáček, David (referee) ; Zeman, Daniel (advisor)
Law amendments are unreadable for normal people and do not provide the actual wording of the law. The complete versions of laws are usually published after several amendments, if at all. The amendments often contain sentences like "the dot is substituted by comma at the end of the paragraph, and words . . . are added", "after the second sentence, insert the sentence . . .", "the new wording of the paragraph number 12 is . . .". The main goal of this work is to create an application that will be able to read a given law together with its amendments and create the complete version of the law. A few laws were chosen to test the application, and an accuracy of 95% has been achieved.
|
|
|
Game server
Čermák, Miroslav ; Klusáček, David (referee) ; Kocanda, Jiří (advisor)
Main goal of this work is to create new web application "game server" in PHP programming language. Server consists of Main module and extension modules: Chess module and Fun module. It also enables user to share pictures, videos and funny texts, chat and play chess. Part of the application is system of user roles that is used to manage and apply rights for common operations and administrative interface to manage server users and modules. Extension of server functionality can be done by adding new modules. As data storage is used MySQL database.
|
|
|
Furniture design
Pekárek, Filip ; Klusáček, David (referee) ; Kocanda, Jiří (advisor)
The furniture design program is an application, which allows users to design cases in user friendly graphical interface. Designed cases conform to user's requirements. On the basis of these requirements and the list of available materials, program computes the optimal cutting plan. The application also allows to control the user's material store. Generated cutting plans can be edited and also printed. The list of component parts, necessary for designed case mounting, can be generated. This list can be printed.
|
guest ::
