|
|
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 %.
|
|
|
Vibration and noise of electric vehicles
Winter, Josef ; Prokop, Aleš (referee) ; Řehák, Kamil (advisor)
This bachelor thesis deals with problematics with noises and vibrations else known as Noise, Vibration and Harshness (NVH) at electric vehicles type Battery Electric Vehicle. The attention is drawn to the powertrain system because the powertrain system was electrified. The goal of this thesis is to present sources of noise and vibrations and to show examples of experiments that are done on the vehicles to improve driving comfort of driver and passangers. In the end the measurement and analysis of noises and vibrations were done at electric vehicle by Hyundai from Institute of Automotive Engineering.
|
|
|
Measuring system for acoustic characterisation of materials
Plánka, Mikuláš ; Havránek, Zdeněk (referee) ; Klusáček, Stanislav (advisor)
The diploma thesis deals with the measurement of acoustic parameters of the material using the B\&K 4206 impedance tube, specifically the absorption and reflection coefficients. The theoretical part provides a basic overview of the measurement methodology and a description of measurement quantities related to acoustic materials characterization. The measurement procedure using the PULSE LabShop software is also described in this work. The main focus of this thesis is the design and implementation of a custom open measurement system created in LabVIEW used to determine the aforementioned materials parameters. The results of the measurements using the custom implementation and the PULSE LabShop software are compared and evaluated in this diploma thesis.
|
|
|
Vibration and noise of electric vehicles
Winter, Josef ; Prokop, Aleš (referee) ; Řehák, Kamil (advisor)
This bachelor thesis deals with problematics with noises and vibrations else known as Noise, Vibration and Harshness (NVH) at electric vehicles type Battery Electric Vehicle. The attention is drawn to the powertrain system because the powertrain system was electrified. The goal of this thesis is to present sources of noise and vibrations and to show examples of experiments that are done on the vehicles to improve driving comfort of driver and passangers. In the end the measurement and analysis of noises and vibrations were done at electric vehicle by Hyundai from Institute of Automotive Engineering.
|
|
|
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 %.
|
guest ::
