디지털융복합연구 (Journal of Digital Convergence)

  • 제19권12호
  • /
  • Pages.353-358
  • /
  • 2021
  • /
  • 2713-6434(pISSN)
  • /
  • 2713-6442(eISSN)
한국디지털정책학회 (The Society of Digital Policy and Management)
권호 표지
DOI QR코드

DOI QR Code

Wav2vec을 이용한 오디오 음성 기반의 파킨슨병 진단

Diagnosis of Parkinson's disease based on audio voice using wav2vec

  • 윤희진 (장안대학교 IT학부 소프트웨어융합과)
  • Yoon, Hee-Jin (Department of Software convergence, Jangan University)
  • 투고 : 2021.11.05
  • 심사 : 2021.12.20
  • 발행 : 2021.12.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

노년기에 접어들면서 알츠하이머 다음으로 흔한 퇴행성 뇌 질환은 파킨슨병이다. 파킨슨병의 증상은 손 떨림, 행동의 느려짐, 인지기능의 저하 등 일상생활의 삶의 질을 저하시키는 요인이 된다. 파킨슨병은 조기진단을 통하여 병의 진행 속도를 늦출 수 있는 질환이다. 파킨슨병의 조기진단을 위해 오디오 음성 파일 입력으로 wav2vec을 이용하여 특징을 추출하고 딥러닝(ANN)으로 파킨슨병의 유무를 진단하는 알고리즘을 구현하였다. 오디오 음성 파일을 이용하여 파킨슨병을 진단하는 실험 결과 정확도는 97.47%로 나타났다. 기존의 뉴럴네트워크를 이용하여 파킨슨병을 진단하는 결과보다 좋은 결과를 나타냈다. 오디오 음성 파일을 wav2vec 이용으로 간단하게 실험을 과정을 줄일 수 있었으며, 실험 결과 향상된 결과를 얻을 수 있었다.

Parkinson's disease is the second most common degenerative brain disease after Alzheimer's in old age. Symptoms of Parkinson's disease are factors that reduce the quality of life in daily life, such as shaking hands, slowing behavior and cognitive function. Parkinson's disease that can slow the progression of the disease through early diagnosis. To diagnoze Parkinson's disease early, an algorithm was implemented to extract features using wav2vec and to diagnose the presence or absence of Parkinson's disease with deep learning(ANN). As a results of the experiment, the accuracy was 97.47%. It was better than the results of diagnosing Parkinson's disease using the existing neural network. The audio voice file could simply reduce the experiment process and obtain improved results.

키워드

과제정보

This paper was supported by jangan University Research Grant in 2021.

참고문헌

  1. kim, Dong Won, Bae, Eun sook,(2015), Factors Affecting Caregiver Burden in caregivers of Partients with Parkin's Disease, Korean Journal of Adult Nursing, Vol.27 No.3, 283-293 DOI:10.7475/kjan.2015.27.3.283
  2. Doyeon Lee, Yoseob Heo, Keunhwan Kim. (2020). Analysis of Technology Trends and Technology Covergence for Parkinson's Disease Therapeutics : Based on Global Patent Information . Journal of the Korea Convergence Society, 11(3), 135-143. https://doi.org/10.15207/JKCS.2020.11.3.135
  3. Hyo-Lyun Roh, Se-Hyun Jang. (2021). Meta-analysis of the Effects of Untact Convergence Exercise Programs on Balance, Gait, and Falls Efficacy of Parkinson's Disease Patients . Journal of the Korea Convergence Society, 12(5), 39-50. https://doi.org/10.15207/JKCS.2021.12.5.039
  4. Shin, Hee-Baek, Shim, Hee-Jeong et (2018), Characters of voice quality on clear versus casual speech in individuals with Parkinson's disease, pISSN 2586-5854 Vol.10 No.2 00.77-84 DOI:10.13064/KSSS.2018.10.2.077
  5. Martinez-Martin P.(1998) An introduction to the concept of quality of life in Parkinson's disease. J Neural;245 Suppl 1:2-6 DOI:10.1007/p.100007733
  6. Sung Reul Kim, R.N., Sun Ju Chung, M.D., sung Young Hee, M.D(2005), Factors Related to Quality of Life in Patients with Parkinson's Disease, J Korean Neurol assoc vol.23..6.2005. p.770-775 DOI:jkna.org/upload/pdf/20050606.pdf
  7. Seuk Kyung Hong, M.D, Kyung Won Park, M.D, Jae Kwan Cha, M.D, Quality of Life in Patients with Parkinson's Disease, 20(3);227-233, ISSN 1225-7044 DOI:10.1016/j-parkreldis.2004.12.005
  8. Pino, C. Ozsanocak, E. Tripoliti, S. Thobois, P.L.Dowsey, P.Auzou (2004), Treatments for dysarthria in Parkinson's disease, Lancet Neurology,3, pp. 574-56. DOI:10.1016/S1474-4422(04)00854-3
  9. J.R.Duffy, Motor Speech Disorders;substrates, differential diagnosis and management, St Louis:Mosby, 2005
  10. Byung-Chul Cho, Sooyoung Cheon, Kab-Nyun Kim, Hyun-Seung Yuk. (2018). A policy study for the voice recognition technology based on elderly health care. Journal of Digital Convergence, 16(2), 9-17. https://doi.org/10.14400/JDC.2018.16.2.009
  11. Aliaksei Kolesau and Dmitrij Sesok,(2020), Unsupervised Pre-Training for Voice Activation, Sciences 10(23):8643 DOI:10.3390/app10238643
  12. Steffen Schneider, Alexei Baevski, Ronan Collobert, Michael Auli(2019), wav2vec: UNSUPERVISED PRE-TRAINING FOR SPEECH RECOGNITION, computer Science v4 DOI:arXiv-1904.05862[cs.CL]
  13. Giovanni Dimauro(2019), Assessment of Speech Intelligibility in Parkinson's Disease Using a Speech-To-Text System, IEEE DOI:10.21227/aw6b-tg17
  14. Seung-Su, Gee Yeun Kim, Bon Mi Koo,(2019), Parkinson's ddisease diagnosis using speech signal and deep residual gated recurrent network network, Acoustical society of korea, 308-313 DOI:10.7776/ASK.2019.38.3.308