ISCA Archive Interspeech 2013
ISCA Archive Interspeech 2013

Using text and acoustic features to diagnose progressive aphasia and its subtypes

Kathleen C. Fraser, Frank Rudzicz, Elizabeth Rochon

This paper presents experiments in automatically diagnosing primary progressive aphasia (PPA) and two of its subtypes, semantic dementia (SD) and progressive nonfluent aphasia (PNFA), from the acoustics of recorded narratives and textual analysis of the resultant transcripts. In order to train each of three types of classifier (naive Bayes, support vector machine, random forest), a large set of 81 available features must be reduced in size. Two methods of feature selection are therefore compared . one based on statistical significance and the other based on minimumredundancy- maximum-relevance. After classifier optimization, PPA (or absence thereof) is correctly diagnosed across 87.4% of conditions, and the two subtypes of PPA are correctly classified 75.6% of the time.


doi: 10.21437/Interspeech.2013-514

Cite as: Fraser, K.C., Rudzicz, F., Rochon, E. (2013) Using text and acoustic features to diagnose progressive aphasia and its subtypes. Proc. Interspeech 2013, 2177-2181, doi: 10.21437/Interspeech.2013-514

@inproceedings{fraser13_interspeech,
  author={Kathleen C. Fraser and Frank Rudzicz and Elizabeth Rochon},
  title={{Using text and acoustic features to diagnose progressive aphasia and its subtypes}},
  year=2013,
  booktitle={Proc. Interspeech 2013},
  pages={2177--2181},
  doi={10.21437/Interspeech.2013-514}
}