Quantification of speech disfluency as a marker of medication-induced cognitive impairment: An application of computerized speech analysis in neuropharmacology

Serguei V.S. Pakhomov; Susan E. Marino; Angela K. Birnbaum

doi:10.1016/j.csl.2012.04.002

Quantification of speech disfluency as a marker of medication-induced cognitive impairment: An application of computerized speech analysis in neuropharmacology

Serguei V.S. Pakhomov, Susan E. Marino, Angela K. Birnbaum

Research output: Contribution to journal › Article › peer-review

2 Scopus citations

Abstract

We present the results of a study investigating the use of speech and language characteristics extracted from spontaneous spoken discourse to assess changes in cognitive function. Specifically, we investigated the use of automatic speech recognition technology to characterize spontaneous speech disfluency induced by topiramate, an anti-epileptic medication with language-related side-effects. We audio recorded spontaneous speech samples from 20 participants during several picture description tasks and analyzed the recordings automatically and manually to extract a range of spoken fluency measurements including speech discontinuities (e.g.; filled pauses, false starts, and repetitions), silent pause duration, speaking rate and vowel lengthening. Our results indicate that some of these paralinguistic speech characteristics are (a) sensitive to the effects of topiramate, (b) are associated with topiramate concentrations in the blood, and (c) complement standard neuropsychological tests typically used to investigate cognitive effects of medications. This work demonstrates the use of computational linguistic tools to assess cognitive effects in a more sensitive, objective, and reproducible manner than is currently available with standard tests.

Original language	English (US)
Pages (from-to)	116-134
Number of pages	19
Journal	Computer Speech and Language
Volume	27
Issue number	1
DOIs	https://doi.org/10.1016/j.csl.2012.04.002
State	Published - Jan 2013

Bibliographical note

Funding Information:
This work was supported by the United States National Institute of Neurological Disorders and Stroke (NINDS) Grant R01-AG026390 (Birnbaum); a Faculty Research Development Grant from the University of Minnesota Academic Health Center (Pakhomov, Marino and Birnbaum). We would also like to thank Chamika Hawkins-Taylor for help with study coordination and administering neuropsychological tests, the staff of the University of Minnesota Clinical and Translational Science Institute (CTSI) for help with study logistics, University of Minnesota student Eden Kaiser and Dustin Chacon for help with speech transcription. Last but not least, we would like to thank the reviewers of this manuscript for their detailed and constructive critiques that helped improve the manuscript.

Keywords

Cognitive assessment
Speech disfluency
Speech recognition
Topiramate

Access

10.1016/j.csl.2012.04.002

OpenUrl availability

Full text

Cite this

@article{e61856ef84cc4aa2943f3dcd622085a3,

title = "Quantification of speech disfluency as a marker of medication-induced cognitive impairment: An application of computerized speech analysis in neuropharmacology",

abstract = "We present the results of a study investigating the use of speech and language characteristics extracted from spontaneous spoken discourse to assess changes in cognitive function. Specifically, we investigated the use of automatic speech recognition technology to characterize spontaneous speech disfluency induced by topiramate, an anti-epileptic medication with language-related side-effects. We audio recorded spontaneous speech samples from 20 participants during several picture description tasks and analyzed the recordings automatically and manually to extract a range of spoken fluency measurements including speech discontinuities (e.g.; filled pauses, false starts, and repetitions), silent pause duration, speaking rate and vowel lengthening. Our results indicate that some of these paralinguistic speech characteristics are (a) sensitive to the effects of topiramate, (b) are associated with topiramate concentrations in the blood, and (c) complement standard neuropsychological tests typically used to investigate cognitive effects of medications. This work demonstrates the use of computational linguistic tools to assess cognitive effects in a more sensitive, objective, and reproducible manner than is currently available with standard tests.",

keywords = "Cognitive assessment, Speech disfluency, Speech recognition, Topiramate",

author = "Pakhomov, {Serguei V.S.} and Marino, {Susan E.} and Birnbaum, {Angela K.}",

note = "Funding Information: This work was supported by the United States National Institute of Neurological Disorders and Stroke (NINDS) Grant R01-AG026390 (Birnbaum); a Faculty Research Development Grant from the University of Minnesota Academic Health Center (Pakhomov, Marino and Birnbaum). We would also like to thank Chamika Hawkins-Taylor for help with study coordination and administering neuropsychological tests, the staff of the University of Minnesota Clinical and Translational Science Institute (CTSI) for help with study logistics, University of Minnesota student Eden Kaiser and Dustin Chacon for help with speech transcription. Last but not least, we would like to thank the reviewers of this manuscript for their detailed and constructive critiques that helped improve the manuscript.",

year = "2013",

month = jan,

doi = "10.1016/j.csl.2012.04.002",

language = "English (US)",

volume = "27",

pages = "116--134",

journal = "Computer Speech and Language",

issn = "0885-2308",

publisher = "Academic Press Inc.",

number = "1",

}

TY - JOUR

T1 - Quantification of speech disfluency as a marker of medication-induced cognitive impairment

T2 - An application of computerized speech analysis in neuropharmacology

AU - Pakhomov, Serguei V.S.

AU - Marino, Susan E.

AU - Birnbaum, Angela K.

N1 - Funding Information: This work was supported by the United States National Institute of Neurological Disorders and Stroke (NINDS) Grant R01-AG026390 (Birnbaum); a Faculty Research Development Grant from the University of Minnesota Academic Health Center (Pakhomov, Marino and Birnbaum). We would also like to thank Chamika Hawkins-Taylor for help with study coordination and administering neuropsychological tests, the staff of the University of Minnesota Clinical and Translational Science Institute (CTSI) for help with study logistics, University of Minnesota student Eden Kaiser and Dustin Chacon for help with speech transcription. Last but not least, we would like to thank the reviewers of this manuscript for their detailed and constructive critiques that helped improve the manuscript.

PY - 2013/1

Y1 - 2013/1

N2 - We present the results of a study investigating the use of speech and language characteristics extracted from spontaneous spoken discourse to assess changes in cognitive function. Specifically, we investigated the use of automatic speech recognition technology to characterize spontaneous speech disfluency induced by topiramate, an anti-epileptic medication with language-related side-effects. We audio recorded spontaneous speech samples from 20 participants during several picture description tasks and analyzed the recordings automatically and manually to extract a range of spoken fluency measurements including speech discontinuities (e.g.; filled pauses, false starts, and repetitions), silent pause duration, speaking rate and vowel lengthening. Our results indicate that some of these paralinguistic speech characteristics are (a) sensitive to the effects of topiramate, (b) are associated with topiramate concentrations in the blood, and (c) complement standard neuropsychological tests typically used to investigate cognitive effects of medications. This work demonstrates the use of computational linguistic tools to assess cognitive effects in a more sensitive, objective, and reproducible manner than is currently available with standard tests.

AB - We present the results of a study investigating the use of speech and language characteristics extracted from spontaneous spoken discourse to assess changes in cognitive function. Specifically, we investigated the use of automatic speech recognition technology to characterize spontaneous speech disfluency induced by topiramate, an anti-epileptic medication with language-related side-effects. We audio recorded spontaneous speech samples from 20 participants during several picture description tasks and analyzed the recordings automatically and manually to extract a range of spoken fluency measurements including speech discontinuities (e.g.; filled pauses, false starts, and repetitions), silent pause duration, speaking rate and vowel lengthening. Our results indicate that some of these paralinguistic speech characteristics are (a) sensitive to the effects of topiramate, (b) are associated with topiramate concentrations in the blood, and (c) complement standard neuropsychological tests typically used to investigate cognitive effects of medications. This work demonstrates the use of computational linguistic tools to assess cognitive effects in a more sensitive, objective, and reproducible manner than is currently available with standard tests.

KW - Cognitive assessment

KW - Speech disfluency

KW - Speech recognition

KW - Topiramate

UR - http://www.scopus.com/inward/record.url?scp=84867330900&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867330900&partnerID=8YFLogxK

U2 - 10.1016/j.csl.2012.04.002

DO - 10.1016/j.csl.2012.04.002

M3 - Article

AN - SCOPUS:84867330900

SN - 0885-2308

VL - 27

SP - 116

EP - 134

JO - Computer Speech and Language

JF - Computer Speech and Language

IS - 1

ER -

Quantification of speech disfluency as a marker of medication-induced cognitive impairment: An application of computerized speech analysis in neuropharmacology

Abstract

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this