Skip to main content
SpringerLink
Log in

Fusing Various Audio Feature Sets for Detection of Parkinson’s Disease from Sustained Voice and Speech Recordings

  • Conference paper
  • First Online:
Speech and Computer (SPECOM 2016)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 9811))

Included in the following conference series:

Abstract

The aim of this study is the analysis of voice and speech recordings for the task of Parkinson’s disease detection. Voice modality corresponds to sustained phonation /a/ and speech modality to a short sentence in Lithuanian language. Diverse information from recordings is extracted by 22 well-known audio feature sets. Random forest is used as a learner, both for individual feature sets and for decision-level fusion. Essentia descriptors were found as the best individual feature set, achieving equal error rate of 16.3 % for voice and 13.3 % for speech. Fusion of feature sets and modalities improved detection and achieved equal error rate of 10.8 %. Variable importance in fusion revealed speech modality as more important than voice.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Bogdanov, D., Wack, N., Gómez, E., Gulati, S., Herrera, P., Mayor, O., Roma, G., Salamon, J., Zapata, J., Serra, X.: Essentia: an audio analysis library for music information retrieval. In: International Society for Music Information Retrieval Conference (ISMIR), pp. 493–498. Curitiba, Brazil, 4–8 November 2013. http://essentia.upf.edu

  2. Breiman, L.: Random forests. Mach. Learn. 45, 5–32 (2001)

    Article  MATH  Google Scholar 

  3. Brümmer, N., de Villiers, E.: The BOSARIS toolkit: Theory, algorithms and code for surviving the new DCF. arXiv 1304(2865v1), 1–23, Presented at the NIST SRE 2011 Analysis Workshop, Atlanta, December 2011. http://sites.google.com/site/bosaristoolkit/

  4. Crysandt, H., Tummarello, G., Piazza, F.: MPEG-7 encoding and processing: MPEG7AUDIOENC + MPEG7AUDIODB. In: 3rd MUSICNETWORK Open Workshop: MPEG AHG on Music Notation Requirements. Munich, Germany, 13–14 March 2004. http://mpeg7audioenc.sf.net

  5. de Rijk, M.C., Launer, L.J., Berger, K., Breteler, M.M.B., Dartigues, J.F., Baldereschi, M., Fratiglioni, L., Lobo, A., Martínez-Lage, J.M., Trenkwalder, C., Hofman, A.: Prevalence of Parkinson’s disease in Europe: a collaborative study of population-based cohorts. Neurology 54(11 Supply 5), S21–S23 (2000). Neurologic Diseases in the Elderly Research Group

    Google Scholar 

  6. Ellis, D.P.W.: PLP and RASTA (and MFCC, and inversion) in Matlab (2005). Matlab implementation of popular speech recognition feature extraction including MFCC and PLP (as defined by Hermansky and Morgan), http://www.ee.columbia.edu/~dpwe/resources/matlab/rastamat/, http://www.ee.columbia.edu/%7Edpwe/resources/matlab/rastamat/

  7. Eyben, F., Weninger, F., Gross, F., Schuller, B.: Recent developments in openSMILE, the Munich open-source multimedia feature extractor. In: Proceedings of the 21st ACM International Conference on Multimedia (MM), pp. 835–838. ACM Press, Barcelona, Spain, 21–25 October 2013. http://audeering.com/research/opensmile/

  8. Gelzinis, A., Verikas, A., Bacauskiene, M.: Automated speech analysis applied to laryngeal disease categorization. Comput. Methods Programs Biomed. 91(1), 36–47 (2008)

    Article  Google Scholar 

  9. Guyon, I.: Practical Feature Selection: from Correlation to Causality, NATO Science for Peace and Security Series D: Information and Communication Security, vol. 19, Chap. 3, pp. 27–43. IOS Press (2008)

    Google Scholar 

  10. Jaiantilal, A.: Random forest (regression, classification and clustering) implementation for Matlab (and standalone) (2012). http://code.google.com/archive/p/randomforest-matlab/

  11. Mathieu, B., Essid, S., Fillon, T., Prado, J., Richard, G.: YAAFE, an easy to use and efficient audio feature extraction software. In: Proceedings of the 11th International Society for Music Information Retrieval Conference (ISMIR), pp. 441–446. Utrecht, Netherlands, 9–13 August 2010. http://yaafe.sf.net

  12. McEnnis, D., McKay, C., Fujinaga, I.: jAudio: Additions and improvements. In: Proceedings of the 7th International Conference on Music Information Retrieval (ISMIR), pp. 385–386. University of Victoria, Victoria, British Columbia, Canada, 8–12 October 2006. http://github.com/dmcennis/jAudioGIT

  13. Nilsson, R., Peña, J.M., Björkegren, J., Tegnér, J.: Evaluating feature selection for svms in high dimensions. In: Fürnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 719–726. Springer, Heidelberg (2006)

    Chapter  Google Scholar 

  14. 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)

    Article  Google Scholar 

  15. Sakar, C.O., Kursun, O.: Telediagnosis of Parkinson’s disease using measurements of dysphonia. J. Med. Syst. 34(4), 591–599 (2010)

    Article  Google Scholar 

  16. Sáenz-Lechón, N., Godino-Llorente, J.I., Osma-Ruiz, V., Gómez-Vilda, P.: Methodological issues in the development of automatic systems for voice pathology detection. Biomed. Signal Process. Control 1(2), 120–128 (2006). Voice Models and Analysis for Biomedical Applications

    Article  MATH  Google Scholar 

  17. Tsanas, A.: Accurate telemonitoring of Parkinson’s disease symptom severity using nonlinear speech signal processing and statistical machine learning. Ph.D. thesis, Oxford Centre for Industrial and Applied Mathematics, University of Oxford, Oxford, United Kingdom, http://people.maths.ox.ac.uk/tsanas/software.html

  18. Tsanas, A., Little, M.A., McSharry, P.E., Spielman, J.L., Ramig, L.O.: Novel speech signal processing algorithms for high-accuracy classification of Parkinson’s disease. IEEE Trans. Biomed. Eng. 59(5), 1264–1271 (2012)

    Article  Google Scholar 

  19. Verikas, A., Gelzinis, A., Vaiciukynas, E., Bacauskiene, M., Minelga, J., Hallander, 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)

    Article  Google Scholar 

  20. Xu, H., Caramanis, C., Mannor, S.: Sparse algorithms are not stable: a no-free-lunch theorem. IEEE Trans. Pattern Anal. Mach. Intell. 34(1), 187–193 (2012)

    Article  MathSciNet  Google Scholar 

Download references

Acknowledgments

This research was funded by a grant (No. MIP-075/2015) from the Research Council of Lithuania.

Author information

Authors and Affiliations

  1. Department of Electrical Power Systems, Kaunas University of Technology, Kaunas, Lithuania

    Evaldas Vaiciukynas, Antanas Verikas, Adas Gelzinis, Marija Bacauskiene & Kestutis Vaskevicius

  2. Department of Information Systems, Kaunas University of Technology, Kaunas, Lithuania

    Evaldas Vaiciukynas

  3. Intelligent Systems Laboratory, Centre for Applied Intelligent Systems Research, Halmstad University, Halmstad, Sweden

    Antanas Verikas

  4. Department of Otolaryngology, Lithuanian University of Health Sciences, Kaunas, Lithuania

    Virgilijus Uloza & Evaldas Padervinskis

  5. Department of Neurology, Lithuanian University of Health Sciences, Kaunas, Lithuania

    Jolita Ciceliene

Authors
  1. Evaldas Vaiciukynas
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Antanas Verikas
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Adas Gelzinis
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Marija Bacauskiene
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Kestutis Vaskevicius
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Virgilijus Uloza
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Evaldas Padervinskis
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jolita Ciceliene
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Evaldas Vaiciukynas .

Editor information

Editors and Affiliations

  1. SPIIRAS , Saint-Petersburg, Russia

    Andrey Ronzhin

  2. Moscow State Linguistic University , Moscow, Russia

    Rodmonga Potapova

  3. Budapest University of Technology and Economics, Budapest, Hungary

    Géza Németh

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing Switzerland

About this paper

Cite this paper

Vaiciukynas, E. et al. (2016). Fusing Various Audio Feature Sets for Detection of Parkinson’s Disease from Sustained Voice and Speech Recordings. In: Ronzhin, A., Potapova, R., Németh, G. (eds) Speech and Computer. SPECOM 2016. Lecture Notes in Computer Science(), vol 9811. Springer, Cham. https://doi.org/10.1007/978-3-319-43958-7_39

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-43958-7_39

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-43957-0

  • Online ISBN: 978-3-319-43958-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation