About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Smart Objects and Technologies for Social Good. Third International Conference, GOODTECHS 2017, Pisa, Italy, November 29-30, 2017, Proceedings

Research Article

Parkinson’s Disease Detection from Speech Using Convolutional Neural Networks

Download(Requires a free EAI acccount)
418 downloads
Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-319-76111-4_21,
        author={Evaldas Vaiciukynas and Adas Gelzinis and Antanas Verikas and Marija Bacauskiene},
        title={Parkinson’s Disease Detection from Speech Using Convolutional Neural Networks},
        proceedings={Smart Objects and Technologies for Social Good. Third International Conference, GOODTECHS 2017, Pisa, Italy, November 29-30, 2017, Proceedings},
        proceedings_a={GOODTECHS},
        year={2018},
        month={3},
        keywords={Parkinson’s disease Audio signal processing Convolutional neural network Information fusion},
        doi={10.1007/978-3-319-76111-4_21}
    }
    
  • Evaldas Vaiciukynas
    Adas Gelzinis
    Antanas Verikas
    Marija Bacauskiene
    Year: 2018
    Parkinson’s Disease Detection from Speech Using Convolutional Neural Networks
    GOODTECHS
    Springer
    DOI: 10.1007/978-3-319-76111-4_21
Evaldas Vaiciukynas,*, Adas Gelzinis1,*, Antanas Verikas,*, Marija Bacauskiene1,*
  • 1: Kaunas University of Technology
*Contact email: evaldas.vaiciukynas@ktu.lt, adas.gelzinis@ktu.lt, antanas.verikas@hh.se, marija.bacauskiene@ktu.lt

Abstract

Application of deep learning tends to outperform hand-crafted features in many domains. This study uses convolutional neural networks to explore effectiveness of various segments of a speech signal, – text-dependent pronunciation of a short sentence, – in Parkinson’s disease detection task. Besides the common Mel-frequency spectrogram and its first and second derivatives, inclusion of various other input feature maps is also considered. Image interpolation is investigated as a solution to obtain a spectrogram of fixed length. The equal error rate (EER) for sentence segments varied from 20.3% to 29.5%. Fusion of decisions from sentence segments achieved EER of 14.1%, whereas the best result when using the full sentence exhibited EER of 16.8%. Therefore, splitting speech into segments could be recommended for Parkinson’s disease detection.

Keywords
Parkinson’s disease Audio signal processing Convolutional neural network Information fusion
Published
2018-03-08
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-319-76111-4_21
Copyright © 2017–2025 EAI
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL