Publication detail

Performance of Articulation Kinetic Distributions Vs MFCCs in Parkinson’s Detection from Vowel Utterances

GÓMEZ-RODELLAR, A. ÁLVAREZ-MARQUINA, A. MEKYSKA, J. PALACIOS-ALONSO, D. MEGHRAOUI, D. GÓMEZ-VILDA, P.

Original Title

Performance of Articulation Kinetic Distributions Vs MFCCs in Parkinson’s Detection from Vowel Utterances

English Title

Performance of Articulation Kinetic Distributions Vs MFCCs in Parkinson’s Detection from Vowel Utterances

Type

book chapter

Language

en

Original Abstract

Speech is a vehicular tool to detect neurological degeneration using certain accepted biomarkers derived from sustained vowels, diadochokinetic exercises, or running speech. Classically, mel-frequency cepstral coefficients (MFCCs) have been used in the organic and neurologic characterization of pathologic phonation using sustained vowels. In the present paper, a comparative study has been carried on comparing Parkinson’s disease detection results using MFCCs and vowel articulation kinematic distributions derived from the first two formants. Binary classification results using support vector machines avail the superior performance of articulation kinematic distributions with respect to MFCCs regarding sensitivity, specificity, and accuracy. The fusion of both types of features could lead to improve general performance in PD detection and monitoring from speech.

English abstract

Speech is a vehicular tool to detect neurological degeneration using certain accepted biomarkers derived from sustained vowels, diadochokinetic exercises, or running speech. Classically, mel-frequency cepstral coefficients (MFCCs) have been used in the organic and neurologic characterization of pathologic phonation using sustained vowels. In the present paper, a comparative study has been carried on comparing Parkinson’s disease detection results using MFCCs and vowel articulation kinematic distributions derived from the first two formants. Binary classification results using support vector machines avail the superior performance of articulation kinematic distributions with respect to MFCCs regarding sensitivity, specificity, and accuracy. The fusion of both types of features could lead to improve general performance in PD detection and monitoring from speech.

Keywords

Mel-frequency cepstral coefficients; Parkinson’s disease; speech articulation kinematics; support vector machines

Released

01.01.2020

ISBN

978-981-13-8949-8

Book

Neural Approaches to Dynamics of Signal Exchanges

Pages from

431

Pages to

441

Pages count

11

URL

BibTex


@inbook{BUT159735,
  author="Jiří {Mekyska}",
  title="Performance of Articulation Kinetic Distributions Vs MFCCs in Parkinson’s Detection from Vowel Utterances",
  annote="Speech is a vehicular tool to detect neurological degeneration using certain accepted biomarkers derived from sustained vowels, diadochokinetic exercises, or running speech. Classically, mel-frequency cepstral coefficients (MFCCs) have been used in the organic and neurologic characterization of pathologic phonation using sustained vowels. In the present paper, a comparative study has been carried on comparing Parkinson’s disease detection results using MFCCs and vowel articulation kinematic distributions derived from the first two formants. Binary classification results using support vector machines avail the superior performance of articulation kinematic distributions with respect to MFCCs regarding sensitivity, specificity, and accuracy. The fusion of both types of features could lead to improve general performance in PD detection and monitoring from speech.",
  booktitle="Neural Approaches to Dynamics of Signal Exchanges",
  chapter="159735",
  doi="10.1007/978-981-13-8950-4_38",
  howpublished="print",
  year="2020",
  month="january",
  pages="431--441",
  type="book chapter"
}