Detail publikačního výsledku

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.

Originální název

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

Anglický název

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

Druh

Kapitola, resp. kapitoly v odborné knize

Originální abstrakt

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.

Anglický abstrakt

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.

Klíčová slova

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

Klíčová slova v angličtině

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

Autoři

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

Rok RIV

2021

Vydáno

01.01.2020

ISBN

978-981-13-8949-8

Kniha

Neural Approaches to Dynamics of Signal Exchanges

Strany od

431

Strany do

441

Strany počet

11

URL

https://doi.org/10.1007/978-981-13-8950-4_38

BibTex

@inbook{BUT159735,
  author="GÓMEZ-RODELLAR, A. and ÁLVAREZ-MARQUINA, A. and MEKYSKA, J. and PALACIOS-ALONSO, D. and MEGHRAOUI, D. and GÓMEZ-VILDA, P.",
  title="Performance of Articulation Kinetic Distributions Vs MFCCs in Parkinson’s Detection from Vowel Utterances",
  booktitle="Neural Approaches to Dynamics of Signal Exchanges",
  year="2020",
  pages="431--441",
  doi="10.1007/978-981-13-8950-4\{_}38",
  isbn="978-981-13-8949-8",
  url="https://doi.org/10.1007/978-981-13-8950-4_38"
}