16th Annual Conference of the International Speech Communication Association

Dresden, Germany
September 6-10, 2015

Automatic Recognition of Unified Parkinson's Disease Rating from Speech with Acoustic, i-Vector and Phonotactic Features

Guozhen An (1), David Guy Brizan (1), Min Ma (1), Michelle Morales (1), Ali Raza Syed (1), Andrew Rosenberg (2)

(1) CUNY Graduate Center, USA
(2) CUNY Queens College, USA

Parkinson's Disease is a neurodegenerative disease affecting millions of people globally, most of whom present difficulties producing speech sounds. In this paper, we describe a system to identify the degree to which a person suffers from the disease. We use a number of automatic phone recognition-based features and we augment these with i-vector features and utterance-level acoustic aggregations. On the Interspeech 2015 ComParE challenge corpus, we find that these features allow for prediction well above the challenge baseline, particularly under cross-validation evaluation.

Full Paper

Bibliographic reference.  An, Guozhen / Brizan, David Guy / Ma, Min / Morales, Michelle / Syed, Ali Raza / Rosenberg, Andrew (2015): "Automatic recognition of unified parkinson's disease rating from speech with acoustic, i-vector and phonotactic features", In INTERSPEECH-2015, 508-512.