An Exploratory Study on Pause Features in Spontaneous Speech for Parkinson’s Disease Detection

Background/Objectives: Dysprosody is a common feature of Parkinson’s disease (PD), yet pause-related abnormalities in Mandarin spontaneous speech remain undercharacterized. This study examined whether spontaneous speech reveals more pronounced prosodic differences than structured reading. Methods: Speech recordings were obtained from 33 Mandarin speakers (16 PD, 17 HC) during short-sentence reading, long-sentence reading, and free-speech tasks. Prosodic features describing pitch, intensity, and pausing were extracted and compared between groups using a nonparametric framework. Subject-level classification was performed as an exploratory validation, comprising single-task classification, decision-level fusion of task probabilities, feature ablation contrasting pause-only and non-pause feature subsets, and cross-corpus evaluation against a Spanish PD corpus. Results: Mean pause duration, pause-duration variability, and pause-to-speech ratio were significantly higher in the PD group after false-discovery-rate correction in both corpora. Free speech was more discriminative than structured reading, multi-task fusion did not clearly improve performance over free speech alone, and pause-only features retained strong discriminative performance. Conclusions: Pause-related measures from spontaneous speech are therefore candidate research markers of PD with preliminary cross-linguistic consistency, whereas the classification results remain exploratory. Larger independent cohorts with detailed clinical and cognitive measures are needed to confirm these findings before clinical applicability can be considered.

Authors

Institutions

Publication Details

Journal
Brain Sciences
Published
2026-11-13
DOI
https://doi.org/10.3390/brainsci16111241
Primary Topic
Voice and Speech Disorders
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

An Exploratory Study on Pause Features in Spontaneous Speech for Parkinson’s Disease Detection

Alex Mihailidis, Yan Hong Fu, Yuyan Wang, Baiyu Shao et al.
Brain Sciences
Voice and Speech Disorders
article

An Exploratory Study on Pause Features in Spontaneous Speech for Parkinson’s Disease Detection

Alex Mihailidis, Yan Hong Fu, Yuyan Wang, Baiyu Shao, Le Chang, Bing Ye
article en

Abstract

Background/Objectives: Dysprosody is a common feature of Parkinson’s disease (PD), yet pause-related abnormalities in Mandarin spontaneous speech remain undercharacterized. This study examined whether spontaneous speech reveals more pronounced prosodic differences than structured reading. Methods: Speech recordings were obtained from 33 Mandarin speakers (16 PD, 17 HC) during short-sentence reading, long-sentence reading, and free-speech tasks. Prosodic features describing pitch, intensity, and pausing were extracted and compared between groups using a nonparametric framework. Subject-level classification was performed as an exploratory validation, comprising single-task classification, decision-level fusion of task probabilities, feature ablation contrasting pause-only and non-pause feature subsets, and cross-corpus evaluation against a Spanish PD corpus. Results: Mean pause duration, pause-duration variability, and pause-to-speech ratio were significantly higher in the PD group after false-discovery-rate correction in both corpora. Free speech was more discriminative than structured reading, multi-task fusion did not clearly improve performance over free speech alone, and pause-only features retained strong discriminative performance. Conclusions: Pause-related measures from spontaneous speech are therefore candidate research markers of PD with preliminary cross-linguistic consistency, whereas the classification results remain exploratory. Larger independent cohorts with detailed clinical and cognitive measures are needed to confirm these findings before clinical applicability can be considered.

Brain SciencesVol. 16(11)
University Health Network (CA), University of Toronto (CA), Toronto Rehabilitation Institute (CA), KITE Research Institute (CA), Huazhong University of Science and Technology (CN)
Good health and well-being
Voice and Speech Disorders
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon