Convolutional Neural Networks and a Transfer Learning Strategy to Classify Parkinson’s Disease from Speech in Three Different Languages

  • Juan Camilo Vásquez-CorreaEmail author
  • Tomas Arias-Vergara
  • Cristian D. Rios-Urrego
  • Maria Schuster
  • Jan Rusz
  • Juan Rafael Orozco-Arroyave
  • Elmar Nöth
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11896)


Parkinson’s disease patients develop different speech impairments that affect their communication capabilities. The automatic assessment of the speech of the patients allows the development of computer aided tools to support the diagnosis and the evaluation of the disease severity. This paper introduces a methodology to classify Parkinson’s disease from speech in three different languages: Spanish, German, and Czech. The proposed approach considers convolutional neural networks trained with time frequency representations and a transfer learning strategy among the three languages. The transfer learning scheme aims to improve the accuracy of the models when the weights of the neural network are initialized with utterances from a different language than the used for the test set. The results suggest that the proposed strategy improves the accuracy of the models in up to 8% when the base model used to initialize the weights of the classifier is robust enough. In addition, the results obtained after the transfer learning are in most cases more balanced in terms of specificity-sensitivity than those trained without the transfer learning strategy.


Parkinson’s disease Speech processing Convolutional neural networks Transfer learning 



The work reported here was financed by CODI from University of Antioquia by grant Numbers 2017–15530 and PRG2018–23541. This project has received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie Grant Agreement No. 766287. T. Arias-Vergara is also under grants of Convocatoria Doctorado Nacional-785 financed by COLCIENCIAS.


  1. 1.
    Hornykiewicz, O.: Biochemical aspects of Parkinson’s disease. Neurology 51(2 Suppl 2), S2–S9 (1998)CrossRefGoogle Scholar
  2. 2.
    Tykalova, T., Rusz, J., Klempir, J., Cmejla, R., Ruzicka, E.: Distinct patterns of imprecise consonant articulation among Parkinson’s disease, progressive supranuclear palsy and multiple system atrophy. Brain Lang. 165, 1–9 (2017)CrossRefGoogle Scholar
  3. 3.
    Moretti, R., et al.: Speech initiation hesitation following subthalamic nucleus stimulation in a patient with Parkinson’s disease. Eur. Neurol. 49(4), 251–253 (2003)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Sakar, B.E., et al.: Collection and analysis of a Parkinson speech dataset with multiple types of sound recordings. IEEE J. Biomed. Health Inform. 17(4), 828–834 (2013)CrossRefGoogle Scholar
  5. 5.
    Villa-Cañas, T., Arias-Londoño, J.D., Orozco-Arroyave, J.R., Vargas-Bonilla, J.F., Nöth, E.: Low-frequency components analysis in running speech for the automatic detection of Parkinson’s disease. In: Proceedings of the Sixteenth Annual Conference of the International Speech Communication Association, pp. 100–104 (2015)Google Scholar
  6. 6.
    Orozco-Arroyave, J.R., et al.: New Spanish speech corpus database for the analysis of people suffering from Parkinson’s disease. In: Proceedings of the Ninth International Conference on Language Resources and Evaluation, pp. 342–347 (2014)Google Scholar
  7. 7.
    Novotnỳ, M., Rusz, J., et al.: Automatic evaluation of articulatory disorders in Parkinson’s disease. IEEE/ACM Trans. Audio Speech Lang. Process. 22(9), 1366–1378 (2014)CrossRefGoogle Scholar
  8. 8.
    Orozco-Arroyave, J.R.: Analysis of Speech of People with Parkinson’s Disease. Logos Verlag, Berlin (2016)Google Scholar
  9. 9.
    Moro-Velazquez, L., et al.: A forced gaussians based methodology for the differential evaluation of Parkinson’s disease by means of speech processing. Biomed. Signal Process. Control 48, 205–220 (2019)CrossRefGoogle Scholar
  10. 10.
    Rusz, J., Cmejla, R., et al.: Imprecise vowel articulation as a potential early marker of Parkinson’s disease: effect of speaking task. J. Acoust. Soc. Am. 134(3), 2171–2181 (2013)CrossRefGoogle Scholar
  11. 11.
    Grósz, T., Busa-Fekete, R., Gosztolya, G., Tóth, L.: Assessing the degree of nativeness and Parkinson’s condition using Gaussian processes and deep rectifier neural networks. In: Proceedings of the Sixteenth Annual Conference of the International Speech Communication Association, pp. 919–923 (2015)Google Scholar
  12. 12.
    Vásquez-Correa, J.C., Orozco-Arroyave, J.R., Nöth, E.: Convolutional neural network to model articulation impairments in patients with Parkinson’s disease. In: Proceedings of the Eighteenth Annual Conference of the International Speech Communication Association, pp. 314–318 (2017)Google Scholar
  13. 13.
    Tu, M., Berisha, V., Liss, J.: Interpretable objective assessment of dysarthric speech based on deep neural networks. In: Proceedings of the Eighteenth Annual Conference of the International Speech Communication Association, pp. 1849–1853 (2017)Google Scholar
  14. 14.
    Cummins, N., Baird, A., Schuller, B.: Speech analysis for health: current state-of-the-art and the increasing impact of deep learning. Methods 151, 41–54 (2018)CrossRefGoogle Scholar
  15. 15.
    Wang, D., Zheng, T.F.: Transfer learning for speech and language processing. In: Proceedings of the Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA), pp. 1225–1237. IEEE (2015)Google Scholar
  16. 16.
    Naseer, A., et al.: Refining Parkinson’s neurological disorder identification through deep transfer learning. Neural Comput. Appl. 1–16 (2019)Google Scholar
  17. 17.
    Goetz, C.G., et al.: Movement disorder society-sponsored revision of the unified Parkinson’s disease rating scale (MDS-UPDRS): scale presentation and clinimetric testing results. Mov. Disord. 23(15), 2129–2170 (2008)CrossRefGoogle Scholar
  18. 18.
    Skodda, S., Visser, W., Schlegel, U.: Vowel articulation in Parkinson’s disease. J. Voice 25(4), 467–472 (2011)CrossRefGoogle Scholar
  19. 19.
    Rusz, J.: Detecting speech disorders in early Parkinson’s disease by acoustic analysis. Habilitation thesis, Czech Technical University in Prague (2018)Google Scholar
  20. 20.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of International Conference on Learning Representations (ICLR), pp. 1–15 (2015)Google Scholar
  21. 21.
    Vásquez-Correa, J.C., Orozco-Arroyave, J.R., Bocklet, T., Nöth, E.: Towards an automatic evaluation of the dysarthria level of patients with Parkinson’s disease. J. Commun. Disord. 76, 21–36 (2018)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Juan Camilo Vásquez-Correa
    • 1
    • 2
    Email author
  • Tomas Arias-Vergara
    • 1
    • 2
    • 3
  • Cristian D. Rios-Urrego
    • 2
  • Maria Schuster
    • 3
  • Jan Rusz
    • 4
  • Juan Rafael Orozco-Arroyave
    • 1
    • 2
  • Elmar Nöth
    • 1
  1. 1.Pattern Recognition LabFriedrich-Alexander UniversitätErlangen-NürnbergGermany
  2. 2.Faculty of EngineeringUniversidad de Antioquia UdeAMedellínColombia
  3. 3.Department of Otorhinolaryngology, Head and Neck SurgeryLudwig-Maximilians UniversitätMunichGermany
  4. 4.Department of Circuit Theory, Faculty of Electrical EngineeringCzech Technical University in PraguePragueCzech Republic

Personalised recommendations