|
|
Acoustic analysis of emotionally affected sentences in patients with Parkinson's disease
Gavlasová, Radka ; Kováč, Daniel (referee) ; Mekyska, Jiří (advisor)
This thesis focuses on Parkinson's disease and its effect on emotional expression in speech. The aim was to conduct a literature search on acoustic emotional analysis of PD patients and to implement acoustic parameters to distinguish between healthy and diseased individuals. The database used contained recordings of 100 patients with PD and 52 healthy controls for various speech tasks. For this analysis, 7 emotionally coloured sentences and 11 acoustic parameters were selected and implemented in Python. From the statistical analysis, it was found that the most significant parameters include pauses in speech and intensity variability. The XGBoost algorithm with 10-fold stratified cross-validation was used for classification. A total of 10 models were implemented to analyze all tasks together and each task separately. Optimization was performed using randomized search. For the combination of all tasks, the significant parameter was the variability in intensity or speech rate. For the individual speech tasks, variability in intonation and formant areas was highly significant. The best model achieved a 63% success rate (BACC) and 85% sensitivity. The results suggest that emotional prosody affects classification, confirming previous findings and pointing to the need for further investigation in this area.
|
|
|
Automated segmentation of the diadochokinetic task for remote monitoring of hypokinetic dysarthria
Svojanovský, Jan ; Mekyska, Jiří (referee) ; Kováč, Daniel (advisor)
The study describes health problems associated with Parkinson’s disease, especially hypokinetic dysarthria. It also points out the subjective and objective methods used to determine the severity of the disease. One of these methods is a diadochokinetic (DDK) task based on rapid syllable repetition to test the functionality of the articulatory apparatus (e.g., tongue, lips, or vocal cords). Correct speech production can also be examined by a speech therapist in the 3F test, which scores the severity of disorders in different areas of speech production. Next, the approaches of other authors, also dealing with the automated search of syllables in the speech signal, are described. The thesis also discusses some features of human speech that are needed for training a machine learning model. These features were computed for each of the 30 ms segments of a DDK task. The main goal is the automated detection and classification of [Pa]-[Ta]-[Ka] syllables in the recordings. For this purpose, an algorithm using a logistic regression was applied. The resulting average accuracy of syllable detection in the recordings was 89.4 %, average sensitivity 59.0 % and average specificity 93.79 %. The identification of individual syllable types was successful with an average accuracy of 90.78 %, an average sensitivity of 59.0 % and an average specificity of 95.39 %. Considering that the predicted onset was not located directly on the manually annotated onset, but in its close vicinity (up to ±3 segments), the average detection sensitivity and average syllable type classification sensitivity were 96.9 % and 85.1 % respectively, with an average difference between manually annotated and automatically segmented syllable onsets of 10.35 ms. The average accuracy of classification of speakers into healthy and PN patients using logistic regression (with speech parameters obtained after automated segmentation) was only 43.92 %, sensitivity 70.0 % and specificity 30.61 % (threshold 70 %). Using linear regression, the clinical scores of the 3F test were predicted. For faciokinesis, the root mean square error (RMSE) was 2.764 after manual syllable annotation and 3.271 after automated segmentation. The RMSE values for phonetics were 3.657 (manual) and 0.753 (automated). The developed algorithm can detect syllables in DDK tasks with relative success, and thus it is possible to determine parameters quantifying speech disorders with low differences with manual segmentation. If the recordings of DDK tasks meet the conditions for computing all these parameters, the algorithm could be used to classify speakers into healthy subjects and PN patients, for whom it could additionally assess the severity of dysarthria.
|
|
|
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.
|
guest ::
RSS feed.