Classification of spontaneous speech of individuals with dementia based on automatic prosody analysis using support vector machines (SVM)

Auteurs Roelant Ossewaarde, Roel Jonkers, Fedor Jalvingh, Yvonne Bastiaanse
Gepubliceerd in Proceedings of the Thirty-Second International Florida Artificial Intelligence Research Society Conference
Publicatiedatum 2019
Lectoraat Artificial Intelligence
Soort publicatie Lezing

Samenvatting

Analysis of spontaneous speech is an important tool for clinical linguists to diagnose various types of neurodegenerative disease that affect the language processing areas. Prosody, fluency and voice quality may be affected in individuals with Parkinson's disease (PD, degradation of voice quality, unstable pitch), Alzheimer's disease (AD, monotonic pitch), and the non-fluent type of Primary Progressive Aphasia (PPA-NF, hesitant, non-fluent speech). In this study, the performance of a SVM classifier is evaluated that is trained on acoustic features only. The goal is to distinguish different types of brain damage based on recorded speech. Results show that the classifier can distinguish some dementia types (PPA-NF, AD), but not others (PD).

Aan deze publicatie werkten mee

Taal Engels
Gepubliceerd in Proceedings of the Thirty-Second International Florida Artificial Intelligence Research Society Conference
Trefwoorden Speech, Aphasiology
Paginabereik 241-244

Roelant Ossewaarde

Roelant Ossewaarde | onderzoeker | Intelligent Data Systems

Roelant Ossewaarde

  • Onderzoeker
  • Lectoraat: Artificial Intelligence