Modeling fundamental frequency dynamics in hypokinetic dysarthria

Mahsa Sadat Elyasi Langarani, Jan Van Santen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

Hypokinetic dysarthria (Hd), which often accompanies Parkinson's Disease (PD), is characterized by hypernasality and by compromised phonation, prosody, and articulation. This paper proposes automated methods for detection of Hd. Whereas most such studies focus on measures of phonation, this paper focuses on prosody, specifically on fundamental frequency (F0) dynamics. Prosody in Hd is clinically described as involving monopitch, which has been confirmed in numerous studies reporting reduced within-utterance pitch variability. We show that a new measure of F0 dynamics, based on a superpositional pitch model that decomposes the F0 contour into a declining phrase curve and (generally, single-peaked) accent curves, performs more accurate Hd vs. Control classification than simpler versions of the model or than conventional variability statistics.

Original languageEnglish (US)
Title of host publication2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages272-276
Number of pages5
ISBN (Electronic)9781479971299
DOIs
StatePublished - Apr 1 2014
Event2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - South Lake Tahoe, United States
Duration: Dec 7 2014Dec 10 2014

Other

Other2014 IEEE Workshop on Spoken Language Technology, SLT 2014
CountryUnited States
CitySouth Lake Tahoe
Period12/7/1412/10/14

Fingerprint

Statistics
Fundamental Frequency
Dysarthria
Modeling
Prosody
Phonation
Accent
Articulation
Conventional
Utterance
Parkinson's Disease

Keywords

  • Hypokinetic dysarthria
  • Parkinson's Disease
  • Pitch decomposition

ASJC Scopus subject areas

  • Computer Science Applications
  • Human-Computer Interaction
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence
  • Language and Linguistics

Cite this

Langarani, M. S. E., & Van Santen, J. (2014). Modeling fundamental frequency dynamics in hypokinetic dysarthria. In 2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings (pp. 272-276). [7078586] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SLT.2014.7078586

Modeling fundamental frequency dynamics in hypokinetic dysarthria. / Langarani, Mahsa Sadat Elyasi; Van Santen, Jan.

2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. p. 272-276 7078586.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Langarani, MSE & Van Santen, J 2014, Modeling fundamental frequency dynamics in hypokinetic dysarthria. in 2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings., 7078586, Institute of Electrical and Electronics Engineers Inc., pp. 272-276, 2014 IEEE Workshop on Spoken Language Technology, SLT 2014, South Lake Tahoe, United States, 12/7/14. https://doi.org/10.1109/SLT.2014.7078586
Langarani MSE, Van Santen J. Modeling fundamental frequency dynamics in hypokinetic dysarthria. In 2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2014. p. 272-276. 7078586 https://doi.org/10.1109/SLT.2014.7078586
Langarani, Mahsa Sadat Elyasi ; Van Santen, Jan. / Modeling fundamental frequency dynamics in hypokinetic dysarthria. 2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 272-276
@inproceedings{9b5819e8d5594c2e8fd969eab69d52b9,
title = "Modeling fundamental frequency dynamics in hypokinetic dysarthria",
abstract = "Hypokinetic dysarthria (Hd), which often accompanies Parkinson's Disease (PD), is characterized by hypernasality and by compromised phonation, prosody, and articulation. This paper proposes automated methods for detection of Hd. Whereas most such studies focus on measures of phonation, this paper focuses on prosody, specifically on fundamental frequency (F0) dynamics. Prosody in Hd is clinically described as involving monopitch, which has been confirmed in numerous studies reporting reduced within-utterance pitch variability. We show that a new measure of F0 dynamics, based on a superpositional pitch model that decomposes the F0 contour into a declining phrase curve and (generally, single-peaked) accent curves, performs more accurate Hd vs. Control classification than simpler versions of the model or than conventional variability statistics.",
keywords = "Hypokinetic dysarthria, Parkinson's Disease, Pitch decomposition",
author = "Langarani, {Mahsa Sadat Elyasi} and {Van Santen}, Jan",
year = "2014",
month = "4",
day = "1",
doi = "10.1109/SLT.2014.7078586",
language = "English (US)",
pages = "272--276",
booktitle = "2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Modeling fundamental frequency dynamics in hypokinetic dysarthria

AU - Langarani, Mahsa Sadat Elyasi

AU - Van Santen, Jan

PY - 2014/4/1

Y1 - 2014/4/1

N2 - Hypokinetic dysarthria (Hd), which often accompanies Parkinson's Disease (PD), is characterized by hypernasality and by compromised phonation, prosody, and articulation. This paper proposes automated methods for detection of Hd. Whereas most such studies focus on measures of phonation, this paper focuses on prosody, specifically on fundamental frequency (F0) dynamics. Prosody in Hd is clinically described as involving monopitch, which has been confirmed in numerous studies reporting reduced within-utterance pitch variability. We show that a new measure of F0 dynamics, based on a superpositional pitch model that decomposes the F0 contour into a declining phrase curve and (generally, single-peaked) accent curves, performs more accurate Hd vs. Control classification than simpler versions of the model or than conventional variability statistics.

AB - Hypokinetic dysarthria (Hd), which often accompanies Parkinson's Disease (PD), is characterized by hypernasality and by compromised phonation, prosody, and articulation. This paper proposes automated methods for detection of Hd. Whereas most such studies focus on measures of phonation, this paper focuses on prosody, specifically on fundamental frequency (F0) dynamics. Prosody in Hd is clinically described as involving monopitch, which has been confirmed in numerous studies reporting reduced within-utterance pitch variability. We show that a new measure of F0 dynamics, based on a superpositional pitch model that decomposes the F0 contour into a declining phrase curve and (generally, single-peaked) accent curves, performs more accurate Hd vs. Control classification than simpler versions of the model or than conventional variability statistics.

KW - Hypokinetic dysarthria

KW - Parkinson's Disease

KW - Pitch decomposition

UR - http://www.scopus.com/inward/record.url?scp=84983189775&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84983189775&partnerID=8YFLogxK

U2 - 10.1109/SLT.2014.7078586

DO - 10.1109/SLT.2014.7078586

M3 - Conference contribution

SP - 272

EP - 276

BT - 2014 IEEE Workshop on Spoken Language Technology, SLT 2014 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -