Journal of Biomedical Engineering Research (대한의용생체공학회:의공학회지)

The Korean Society of Medical and Biological Engineering (대한의용생체공학회)
권호 표지
DOI QR코드

DOI QR Code

Development of a Mobile Application for Disease Prediction Using Speech Data of Korean Patients with Dysarthria

한국인 구음장애 환자의 발화 데이터 기반 질병 예측을 위한 모바일 애플리케이션 개발

  • Changjin Ha (Department of Software Engineering, Jeonbuk National University) ;
  • Taesik Go (Division of Biomedical Engineering, Jeonbuk National University)
  • 하창진 (전북대학교 공과대학 소프트웨어공학과) ;
  • 고태식 (전북대학교 공과대학 바이오메디컬공학부)
  • Received : 2023.12.05
  • Accepted : 2023.12.05
  • Published : 2024.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Communication with others plays an important role in human social interaction and information exchange in modern society. However, some individuals have difficulty in communicating due to dysarthria. Therefore, it is necessary to develop effective diagnostic techniques for early treatment of the dysarthria. In the present study, we propose a mobile device-based methodology that enables to automatically classify dysarthria type. The light-weight CNN model was trained by using the open audio dataset of Korean patients with dysarthria. The trained CNN model can successfully classify dysarthria into related subtype disease with 78.8%~96.6% accuracy. In addition, the user-friendly mobile application was also developed based on the trained CNN model. Users can easily record their voices according to the selected inspection type (e.g. word, sentence, paragraph, and semi-free speech) and evaluate the recorded voice data through their mobile device and the developed mobile application. This proposed technique would be helpful for personal management of dysarthria and decision making in clinic.

Keywords

Acknowledgement

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (No. 2021R1C1C1010063, RS-2023-00236157).

References

  1. Gentil M, Pollak P, Perret J. Parkinsonian dysarthria. Rev Neurol. 1995;151(2):105-112. 
  2. Rudzicz F. Articulatory knowledge in the recognition of dysarthric speech. IEEE Trans Audio Speech Lang Process. 2011;19(4):947-960.  https://doi.org/10.1109/TASL.2010.2072499
  3. Joshy AA, Rajan R. Dysarthria severity classification using multi-head attention and multi-task learning. Speech Commun. 2023;147:1-11.  https://doi.org/10.1016/j.specom.2022.12.004
  4. Schlenck KJ, Bettrich R, Willmes K. Aspects of disturbed prosody in dysarthria. Clin Linguist Phon. 1993;7(2):119-128.  https://doi.org/10.3109/02699209308985549
  5. Rampello L, Rampello L, Patti F, Zappia M. When the word doesn't come out: A synthetic overview of dysarthria. J Neurol Sci. 2016;369:354-360.  https://doi.org/10.1016/j.jns.2016.08.048
  6. Kent RD, Weismer G, Kent JF, Vorperian HK, Duffy JR. Acoustic studies of dysarthric speech: Methods, progress, and potential.J Commun Disord. 1999;32(3):141-186.  https://doi.org/10.1016/S0021-9924(99)00004-0
  7. Robertson SJ. Robertson dysarthria profile. Buckinghamshire: Winslow. 1982. 
  8. Enderby P. Frenchay dysarthria assessment. Int J Lang Commun Disord. 1980;15(3):165-173.  https://doi.org/10.3109/13682828009112541
  9. Drummond SS. Dysarthria examination battery. Tucson: Communication Skill Builders. 1993. 
  10. Shriberg LD, Kwiatkowski J. Phonological disorders III: A procedure for assessing severity of involvement. Journal of speech and Hearing Disorders. 1982;47(3): 256-270.  https://doi.org/10.1044/jshd.4703.256
  11. Kim YH, Kim WH, Kim HG. A study on acoustic characteristics of dysarthria in relation to the underlying etiology. Journal of Korean Academy of Rehabilitation Medicine. 1994;18(4):773-779. 
  12. Lee JS, Lee JY, Kim SH. Effect of articulation abilities on the articulator strength training by IOPI of spasticity dysarthric speech. Therapeutic Science for Rehabilitation. 2020;9(1):91-99.  https://doi.org/10.22683/TSNR.2020.9.1.091
  13. Esteva A, Robicquet A, Ramsundar B, Kuleshov V, DePristo M, Chou K, Cui C, Corrado G, Thrun S, Dean J. A guide to deep learning in healthcare. Nat Med. 2019;25(1):24-29.  https://doi.org/10.1038/s41591-018-0316-z
  14. Song YH, Ryu GH. The innovative medical devices using big data and artificial intelligence: Focusing on the cases of Korea, the United States, and Europe. J Biomed Eng Res. 2023;44(4):264-274. 
  15. Lee YH, Kim YJ, Kim KG. A performance comparison study of lesion detection model according to gastroscopy image quality. J Biomed Eng Res. 2023;44(2):118-124. 
  16. Kadi KL, Selouani SA, Boudraa B, Boundraa M. Discriminative prosodic features to assess the dysarthria severity levels. Proceedings of the World Congress on Engineering. 2013;3:1-5. 
  17. Kadi KL, Selouani SA, Boudraa B, Boundraa M. Fully automated speaker identification and intelligibility assessment in dysarthria disease using auditory knowledge. Biocybern Biomed Eng. 2016;36(1):233-247.  https://doi.org/10.1016/j.bbe.2015.11.004
  18. Narendra NP, Alku P. Dysarthric speech classification using glottal features computed from non-words, words and sentences. Interspeech. 2018; 3403-3407. 
  19. Rudzicz F, Namasivayam AK, Wolff T. The TORGO database of acoustic and articulatory speech from speakers with dysarthria. Lang Resour Eval. 2012;46:523-541  https://doi.org/10.1007/s10579-011-9145-0
  20. Kim H, Hasegawa-Johnson M, Perlman A, Gunderson J, Huang TS, Watkin K, Frame S. Dysarthric speech database for universal access research. Ninth Annual Conference of the International Speech Communication Association. 2008. 
  21. Bhat C, Strik H. Automatic assessment of sentence-level dysarthria intelligibility using BLSTM. IEEE J Sel Top Signal Process. 2020;14(2):322-330.  https://doi.org/10.1109/JSTSP.2020.2967652
  22. Joshy AA, Rajan R. Automated dysarthria severity classification: A study on acoustic features and deep learning techniques. IEEE Trans Neural Syst Rehabil Eng. 2022;30:1147-1157.  https://doi.org/10.1109/TNSRE.2022.3169814
  23. Gupta S, Patil AT, Purohit M, Parmar M, Patel M, Patil HA, Guido RC. Residual neural network precisely quantifies dysarthria severity-level based on short-duration speech segments. Neural Netw. 2021;139:105-117.  https://doi.org/10.1016/j.neunet.2021.02.008
  24. Suhas BN, Mallela J, Illa A, Yamini BK, Atchayaram N, Yadav R, Gope D, Ghosh PK. Speech task based automatic classification of ALS and Parkinson's Disease and their severity using log Mel spectrograms. 2020 international conference on signal processing and communications(SPCOM). 2020; 1-5. 
  25. https://aihub.or.kr/aihubdata/data/view.do?dataSetSn=608. Accessed on 27 Dec 2023. 
  26. Douglas O' Shaughnessy, Speech Communication: human and machine. Wesley-IEEE Press. 1987. 
  27. Yacouby R, Axman D. Probabilistic extension of precision, recall, and f1 score for more thorough evaluation of classification models. Proceedings of the first workshop on evaluation and comparison of NLP systems. 2020; 79-91.