Parkinson’s Disease Detection from Speech Using Convolutional Neural Networks

  • Evaldas Vaiciukynas
  • Adas Gelzinis
  • Antanas Verikas
  • Marija Bacauskiene
Conference paper
Part of the Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering book series (LNICST, volume 233)


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.


Parkinson’s disease Audio signal processing Convolutional neural network Information fusion 



Funding for this work was provided by a grant (No. MIP-075/2015) from the Research Council of Lithuania. The dataset was collected by the Department of Otorhinolaryngology at Lithuanian University of Health Sciences.


  1. 1.
    de Rijk, M., Launer, L., Berger, K., Breteler, M., Dartigues, J., Baldereschi, M., Fratiglioni, L., Lobo, A., Martinez-Lage, J., Trenkwalder, C., Hofman, A.: Prevalence of Parkinson’s disease in Europe: a collaborative study of population-based cohorts. Neurologic diseases in the elderly research group. Neurology 54(11 Suppl 5), S21–S23 (2016)Google Scholar
  2. 2.
    Orozco-Arroyave, J.R., Hönig, F., Arias-Londoño, J.D., Vargas-Bonilla, J.F., Daqrouq, K., Skodda, S., Rusz, J., Nöth, E.: Automatic detection of Parkinson’s disease in running speech spoken in three different languages. J. Acoust. Soc. Am. 139(1), 481–500 (2016)CrossRefGoogle Scholar
  3. 3.
    Hinton, G., Deng, L., Yu, D., Dahl, G.E., Mohamed, A.R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T.N., Kingsbury, B.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82–97 (2012)CrossRefGoogle Scholar
  4. 4.
    Abdel-Hamid, O., Mohamed, A.R., Jiang, H., Deng, L., Penn, G., Yu, D.: Convolutional neural networks for speech recognition. IEEE/ACM Trans. Audio Speech Lang. Process. 22(10), 1533–1545 (2014)CrossRefGoogle Scholar
  5. 5.
    Sainath, T.N., Kingsbury, B., Saon, G., Soltau, H., Mohamed, A.R., Dahl, G., Ramabhadran, B.: Deep convolutional neural networks for large-scale speech tasks. Neural Netw. 64, 39–48 (2015). Special Issue on “Deep Learning of Representations”CrossRefGoogle Scholar
  6. 6.
    Zhang, H., McLoughlin, I., Song, Y.: Robust sound event recognition using convolutional neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 559–563, April 2015Google Scholar
  7. 7.
    Thomas, S., Ganapathy, S., Saon, G., Soltau, H.: Analyzing convolutional neural networks for speech activity detection in mismatched acoustic conditions. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2519–2523, May 2014Google Scholar
  8. 8.
    Han, Y., Lee, K.: Acoustic scene classification using convolutional neural network and multiple-width frequency-delta data augmentation. Computing Research Repository (CoRR) arXiv:1607.02383 (2016)
  9. 9.
    Dennis, J., Tran, H.D., Li, H.: Spectrogram image feature for sound event classification in mismatched conditions. IEEE Signal Process. Lett. 18(2), 130–133 (2011)CrossRefGoogle Scholar
  10. 10.
    Deng, L., Abdel-Hamid, O., Yu, D.: A deep convolutional neural network using heterogeneous pooling for trading acoustic invariance with phonetic confusion. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6669–6673, May 2013Google Scholar
  11. 11.
    Adi, Y., Keshet, J., Goldrick, M.: Vowel duration measurement using deep neural networks. In: 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1–6, September 2015Google Scholar
  12. 12.
    Godino-Llorente, J.I., Gomez-Vilda, P.: Automatic detection of voice impairments by means of short-term cepstral parameters and neural network based detectors. IEEE Trans. Biomed. Eng. 51(2), 380–384 (2004)CrossRefGoogle Scholar
  13. 13.
    Dibazar, A.A., Narayanan, S., Berger, T.W.: Feature analysis for automatic detection of pathological speech. In: Proceedings of the 2th Joint EMBS/BMES Conference, Houston, USA, pp. 182–183 (2002)Google Scholar
  14. 14.
    Verikas, A., Gelzinis, A., Vaiciukynas, E., Bacauskiene, M., Minelga, J., Hållander, M., Uloza, V., Padervinskis, E.: Data dependent random forest applied to screening for laryngeal disorders through analysis of sustained phonation: acoustic versus contact microphone. Med. Eng. Phys. 37(2), 210–218 (2015)CrossRefGoogle Scholar
  15. 15.
    Muhammad, G.: Voice pathology detection using vocal tract area. In: 2013 European Modelling Symposium, pp. 164–168, November 2013Google Scholar
  16. 16.
    Hrúz, M., Kunešová, M.: Convolutional neural network in the task of speaker change detection. In: Ronzhin, A., Potapova, R., Németh, G. (eds.) SPECOM 2016. LNCS (LNAI), vol. 9811, pp. 191–198. Springer, Cham (2016). CrossRefGoogle Scholar
  17. 17.
    Faundez-Zanuy, M., Monte-Moreno, E.: State-of-the-art in speaker recognition. IEEE Aerosp. Electron. Syst. Mag. 20(5), 7–12 (2005)CrossRefGoogle Scholar
  18. 18.
    Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)CrossRefzbMATHGoogle Scholar

Copyright information

© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018

Authors and Affiliations

  1. 1.Department of Electrical Power SystemsKaunas University of TechnologyKaunasLithuania
  2. 2.Department of Information SystemsKaunas University of TechnologyKaunasLithuania
  3. 3.Centre for Applied Intelligent Systems ResearchHalmstad UniversityHalmstadSweden

Personalised recommendations