Moderní řečové příznaky používané při diagnóze chorob
| Autor: | Bílý, Ondřej |
|---|---|
| Jazyk: | čeština |
| Rok vydání: | 2011 |
| Předmět: |
jitter
vowel classification parameterization segmentation samohláska selection symptom confusion matrix Speech prozodie hypokinetická dysartrie Matthews correlation coefficient speech signal analysis prosody Artificial neural network formant matice záměn Řeč shimmer klasifikace učící se algoritmy accuracy souhláska umělé neuronové sítě learning algorithms přesnost hypokinetic dysarthria segmentální příznak Matthewůw korelační koeficient algoritmy podpůrných vektorů k nejbližších sousedů. consonant parametrizace support vector machine k nearest-neighbor. analýza řečového signálu segmentation symptom segmentace výběr příznaků Parkinsonova choroba Parkinson's disease |
| Druh dokumentu: | masterThesis |
| Popis: | This work deals with the diagnosis of Parkinson's disease by analyzing the speech signal. At the beginning of this work there is described speech signal production. The following is a description of the speech signal analysis, its preparation and subsequent feature extraction. Next there is described Parkinson's disease and change of the speech signal by this disability. The following describes the symptoms, which are used for the diagnosis of Parkinson's disease (FCR, VSA, VOT, etc.). Another part of the work deals with the selection and reduction symptoms using the learning algorithms (SVM, ANN, k-NN) and their subsequent evaluation. In the last part of the thesis is described a program to count symptoms. Further is described selection and the end evaluated all the result. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|