Analysis of Pathological Speech Signals
Tomás Arias-Vergara
Diese Publikation zitieren
Tomás Arias-Vergara, Analysis of Pathological Speech Signals (2022), Logos Verlag, Berlin, ISBN: 9783832584184
1
Accesses
Accesses
Beschreibung / Abstract
This book addresses the automatic analysis of speech disorders resulting from a clinical condition (Parkinson's disease and hearing loss) or the natural aging process.
For Parkinson's disease, the progression of speech symptoms is evaluated by considering speech recordings captured in the short-term (4 months) and long-term (5 years). Machine learning methods are used to perform three tasks:
(1) automatic classification of patients vs. healthy speakers.
(2) regression analysis to predict the dysarthria level and neurological state.
(3) speaker embeddings to analyze the progression of the speech symptoms over time.
For hearing loss, automatic acoustic analysis is performed to evaluate whether the duration and onset of deafness (before or after speech acquisition) influence the speech production of cochlear implant users.
Additionally, articulation, prosody, and phonemic analyses show that cochlear implant users present altered speech production even after hearing rehabilitation
For Parkinson's disease, the progression of speech symptoms is evaluated by considering speech recordings captured in the short-term (4 months) and long-term (5 years). Machine learning methods are used to perform three tasks:
(1) automatic classification of patients vs. healthy speakers.
(2) regression analysis to predict the dysarthria level and neurological state.
(3) speaker embeddings to analyze the progression of the speech symptoms over time.
For hearing loss, automatic acoustic analysis is performed to evaluate whether the duration and onset of deafness (before or after speech acquisition) influence the speech production of cochlear implant users.
Additionally, articulation, prosody, and phonemic analyses show that cochlear implant users present altered speech production even after hearing rehabilitation
Inhaltsverzeichnis
- BEGINN
- 1 Introduction
- 1.1 Motivation
- 1.2 Speech disorders in selected populations
- 1.3 Hypotheses
- 1.4 Objectives
- 1.5 Contribution of this thesis
- 1.6 Structure of the thesis
- 2 Speech production process
- 2.1 Speech chain
- 2.2 Impact of Parkinson’s disease on speech motor control
- 2.3 Auditory system and speech control
- 3 State-of-the-art
- 3.1 Severity estimation of Parkinson’s disease from speech
- 3.2 Speech analysis of cochlear implant users
- 3.3 Aging and speech
- 3.4 Smartphone-based applications for health care
- 4 Automatic analysis of pathological speech signals
- 4.1 Speech processing techniques-an overview
- 4.2 Pathological speech modeling
- 4.3 Machine learning methods
- 4.4 Speaker models
- 5 Data collection
- 5.1 Parkinson’s disease
- 5.2 Cochlear implants
- 5.3 Supporting datasets
- 6 Experiments and results
- 6.1 Models for speech analysis
- 6.2 Parkinson’s disease patients
- 6.3 Cochlear Implant users
- 6.4 Aging and speech
- 6.5 Smartphone-based applications for health care