|
|
Cross-platform performance testing of open source PBX FreeSWITCH
Melichar, Ondřej ; Kováč, Dominik (referee) ; Šilhavý, Pavel (advisor)
This bachelor’s thesis deals with the open source private branch exchange FreeSWITCH. The thesis describes the process of installation and consecutive configuration of the telephone system on various distributions of platforms Windows and Linux. Emphasis is placed on comparison of the performance between these systems and also the quality of calls as well as transcoding functionality. Specifically, the performance of the telephone system is tested while using the SIP protocol. Thesis also contains an introduction into the subject and a brief description of the FreeSWITCH architecture and its functions and capabilities.
|
|
|
Smart Home Control by Utilizing AllJoyn Platform
Resler, Tomáš ; Kováč, Dominik (referee) ; Hošek, Jiří (advisor)
This bachelor work concerns with system Alljoyn which tries to standardize the interface for communication in the frame of intelligent house. The basic principles and the structure of the framework Alljoyn including the recent proposal of the modules Lighting framework and Gateway Agent have been described in the theoretical oriented part of the work. The practical oriented part stars with the description of the getting the Alljoyn framework including the Lighting controller and the Gateway Agent to work on the hardware router provided with operating system OpenWRT. The following parts present own testing connector for the Alljoyn Gateway which have been written to allow the remote control of the lights via cloud service Twitter. The functionality of the router have been tested with software simulator of the Alljoyn lights Luminaire and an own ligths driving program developed utilizing the experimental Lighting SDK for mobile devices with operating system Android.
|
|
|
XML Data Compression
Jelen, Michal ; Polák, Josef (referee) ; Kováč, Dominik (advisor)
This master’s thesis is dealing with problems of XML data compression. It describes a characterization and important concepts of XML language as well as AIXM as XML data format. It documents contemporary compression methods of XML and divides them into appropriate groups. Thereinafter a testing of XML data compression using mentioned methods and evaluation of results is implemented. With a consideration of processed data there is created and presented an application which enables lossy and lossless compression of AIXM with the help of particular elements data analysis. All of it with user selection options of AIXM objects and way of resultant compression.
|
|
|
Impact of resolution change on subjective QoE measurement of streaming video
Nevřelová, Monika ; Pokorný, Jiří (referee) ; Kováč, Dominik (advisor)
This thesis deals with the process of development of web application for subjective evaluation of streaming video. The thesis describes the adaptive streaming technique, streaming services and both subjective and objective evaluation of streaming video. Methods for measuring of subjective evaluation (namely laboratory method and crowdsourcing method) are described in more detail. A special web-based tool for subjective evaluation of streaming video was created with use of HTML, PHP and MySQL languages. To simulate the network changes, such as changes of the bandwidths, there´re created scenarios where the player selects the quality of the streamed video. The process of collecting data via Laboratory method and Crowdsourcing method is described in the thesis. Collected data are then analyzed.
|
|
|
Analysis of impact of noise in recordings on the automated detection of hypokinetic dysarthria
Havelková, Nikola ; Galáž, Zoltán (referee) ; Kováč, Daniel (advisor)
This thesis deals with the automated detection of hypokinetic dysarthria by analysing the influence of noise present in recordings. Appropriate single-channel methods, specifically the spectral subtraction and Kalman filter, are selected and implemented in the MATLAB R2022a to enhance speech. These methods are also used for noise-free recordings, to which additive white noise was added. Afterwards, the effectiveness of these methods is objectively evaluated by using signal-to-noise ratio values. After enhancing of speech, interferences are extracted from the recordings. The effect of the presence of noise, as well as its subsequent suppression by individual methods, is then evaluated by statistical analysis, specifically using the Kruskal-Wallis test and the post hoc Dunn’s test. The probability of distributing parameters of clean, noisy and enhanced recordings, for which the effect of noise is significant, according to statistical tests, are plotted using violin and box graphs. Finally, the classification was done by logistic regression with the help of machine learning, where the effect of the presence of noise and subsequent speech enhancement on automated detection of hypokinetic dysarthria was described according to the area values under the ROC curve.
|
|
|
Mobile applications for subjective measurement QoE of streaming video
Šeda, Pavel ; Hošek, Jiří (referee) ; Kováč, Dominik (advisor)
This thesis is focused on the subjective measurement of the quality of experience on streaming video through a mobile application. After wide analysis of possibilities how to realize subjective measurement of quality of experience, the mobile and web application were created. These tools enable to obtain user ratings of streaming videos and then evaluate them. The user ratings are stored to the central database via secured REST API.
|
|
| |
|
|
Measurement of data network quality parameters
Ripper, David ; Kováč, Dominik (referee) ; Zeman, Václav (advisor)
The aim of this thesis was studying and describing known methods for testing transmission parameters in data networks based on protocol stack TCP/IP. Firstly were individual transmission parameters specified and determined their impact on service quality. Another aim was to carry out a comparison of the different methodologies of measurement of transmission parameters, performed their qualifications on the basis of these findings and methodology for measuring service quality from the user's perspective was proposed. It was a web application where users measured basic transmission parameters, then the users judged videos according to the evaluation scale MOS (Mean Opinion Score) and with the help of these data was analysis, classification connection and impact of connection on MOS evaluation.
|
|
|
Differential analysis of multilingual corpus in patients with neurodegenerative diseases
Kováč, Daniel ; Zvončák, Vojtěch (referee) ; Mekyska, Jiří (advisor)
This diploma thesis focuses on the automated diagnosis of hypokinetic dysarthria in the multilingual speech corpus, which is a motor speech disorder that occurs in patients with neurodegenerative diseases such as Parkinson’s disease. The automatic speech recognition approach to diagnosis is based on the acoustic analysis of speech and subsequent use of mathematical models. The popularity of this method is on the rise due to its objectivity and the possibility of working simultaneously on different languages. The aim of this work is to find out which acoustic parameters have high discriminative power and are universal for multiple languages. To achieve this, a statistical analysis of parameterized speech tasks and subsequent modelling by machine learning methods was used. The analyses were performed for Czech, American English, Hungarian and all languages together. It was found that only some parameters enable the diagnosis of the hypokinetic disorder and are, at the same time, universal for multiple languages. The relF2SD parameter shows the best results, followed by the NST parameter. When classifying speakers of all the languages together, the model achieves accuracy of 59 % and sensitivity of 72 %.
|
|
|
Automatic speech recordings segmentation tool
Santa, Roman ; Zvončák, Vojtěch (referee) ; Kováč, Daniel (advisor)
Nástroj pre automatickú segmentáciu spracováva nahrávky reči a extrahuje hovorené slovo z nahrávok. Je dôležité, aby pokročilá analýza pracovala iba s rečovými časťami z nahrávky. Nástroj na segmentáciu má ulahčiť spracovanie nahrávok pre analýzu rozdielov medzi hláskami pacientov s parkinsonovou chorobou a tými zdravými. Cieľ tejto práce je navrhnúť a otestovať detektory reči s Google WebRTC detektorom a vybrať ten najvhodnejší detektor reči s minimálnym počtom chýb. Ďalej, vytvoriť nástroj na segmentáciu nahrávok a otestovať rozpoznávanie reči pomocou dynamic time warping. Bola použitá databáza poskytnutá laboratóriom pre analýzu mozgových ochorení. Obsahuje české a maďarské nahrávky s rovnakým počtom mužských a ženských pacientov a aj rovnakým počtom zdravých pacientov a pacientov s parkinsonovou chorobou. Najlepšie výsledky v testoch dosiahol detektor na základe energie reči. Nebol zistený žiaden rozdiel v presnosti detektoru pri spracovaní mužských a ženských nahrávok alebo nahrávok zdravých či chorých pacientov. Nahrávky s nízkym odstupom signálu od šumu boli náročnejšie na spracovanie s frekvenciou chýb od 12%. Na základe výsledkov, bol navrhnutý nový detektor pre spracovanie úplnej nahrávky. Na záver bol testovaný algoritmus pre rozpoznávanie podobnosti reči na základe melovských kepstrálnych koeficientov.
|
guest ::
RSS feed.