2017 INTERSPEECH INTERSPEECH 2017

Rhythmic Characteristics of Parkinsonian Speech: A Study on Mandarin and Polish

Abstract

Previous studies on Italian speech showed that the percentage of vocalic portion in the utterance (%V) and the duration of the interval between two consecutive vowel onset points (VtoV) were larger for parkinsonian (PD) than for healthy controls (HC). Especially, the values of %V were distinctly separated between PD and HC. The present study aimed to further test the finding on Mandarin and Polish. Twenty-five Mandarin speakers (13 PD and 12 HC matched on age) and thirty-one Polish speakers (18 PD and 13 HC matched on age) read aloud a passage of story. The recorded speeches were segmented into vocalic and consonantal intervals, and then %V and VtoV were calculated. For both languages, VtoV overlapped between HC and PD. For Polish, %V was distinctly higher in PD than in HC, while for Mandarin there was no significant difference. It suggests that %V could be used for automatic diagnosis of PD for Italian and Polish, but not for Mandarin. The effectiveness of the rhythmic metric appears to be language-dependent, varying with the rhythmic typology of the language.

🧭 Keyword Pioneer — vocalic interval
🐝 Cross-Pollinator — Artificial Intelligence, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Speech & Audio