Analysis of Speech of People with Parkinson's Disease
Juan Rafael Orozco-Arroyave
Diese Publikation zitieren
Juan Rafael Orozco-Arroyave, Analysis of Speech of People with Parkinson's Disease (2016), Logos Verlag, Berlin, ISBN: 9783832588236
9
Accesses
Accesses
Beschreibung / Abstract
The analysis of speech of people with Parkinson's disease is an interesting and highly relevant topic that has attracted the research community during several years. The advances in digital signal processing and pattern recognition have motivated the research community to work on the development of computational tools to perform automatic analysis of speech. Most of the contributions on this topic are focused on sustained phonation of vowels and only consider recordings of one language. This thesis addresses two problems considering recordings of sustained phonations of vowels and continuous speech signals: (1) the automatic classification of Parkinson's patients vs. healthy speakers, and (2) the prediction of the neurological state of the patients according to the motor section of the Unified Parkinson's Disease Rating Scale (UPDRS). Recordings of three languages are considered: Spanish, German, and Czech. German and Czech data were provided by other researchers, and Spanish data were recorded in Medell 'in, Colombia, during the development of this work. Besides the classical approaches to assess pathological speech, a new method to model articulation deficits of Parkinson's patients is proposed. This new articulation modeling approach shows to be more accurate and robust than others to discriminate between Parkinson's patients and healthy speakers in the three considered languages.
Inhaltsverzeichnis
- BEGINN
- 1 Introduction
- 1.1 Motivation
- 1.2 State-of-the-art
- 1.3 Contributions of the thesis
- 1.4 Structure of this work
- 2 Speech of people with Parkinson†™s disease
- 2.1 Why does Parkinson†™s disease affect speech?
- 2.2 Characteristics of PD speech
- 2.3 Existing scales to assess PD patients
- 2.4 Existing methods and tools for speech therapy in PD patients
- 3 Data collection
- 3.1 Spanish
- 3.2 German
- 3.3 Czech
- 4 Analysis of speech of patients with Parkinson†™s disease
- 4.1 Phonation analysis
- 4.2 Articulation analysis
- 4.3 Prosody analysis
- 4.4 Automatic classification and regression
- 5 Experimental results
- 5.1 Automatic detection of Parkinson†™s disease in three languages
- 5.2 Prediction of the neurological state of Parkinson†™s patients
- 5.3 Analysis of the experimental results
- 6 Outlook
- 7 Summary
- A Speech recording protocol
- B Publications emerging from the development of this thesis
- List of Figures
- List of Tables
- Bibliography