한국음향학회지 (The Journal of the Acoustical Society of Korea)

  • 제38권3호
  • /
  • Pages.308-313
  • /
  • 2019
  • /
  • 1225-4428(pISSN)
  • /
  • 2287-3775(eISSN)
한국음향학회 (The Acoustical Society of Korea)
권호 표지
DOI QR코드

DOI QR Code

음성 신호와 심층 잔류 순환 신경망을 이용한 파킨슨병 진단

Parkinson's disease diagnosis using speech signal and deep residual gated recurrent neural network

  • 신승수 (광운대학교 전자융합공학과) ;
  • 김지연 (광운대학교 전자융합공학과) ;
  • 구본미 (광운대학교 SSK 정신건강과 지역사회 연구센터) ;
  • 김형국 (광운대학교 전자융합공학과)
  • 투고 : 2019.02.25
  • 심사 : 2019.04.19
  • 발행 : 2019.05.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

노년기 3대 질환 중 하나인 파킨슨병은 환자의 70 % 이상이 음성 장애를 앓고 있으며 최근 음성 신호를 통한 파킨슨병의 진단 방법들이 고안되고 있다. 본 논문에서는 음성 특징을 이용한 심층 잔류 순환 신경망 기반의 파킨슨병 진단 방식을 제안한다. 제안하는 방식에서는 파킨슨병 진단을 위한 음성 특징을 선택하고 이를 심층 잔류 순환 신경망에 적용하여 파킨슨병 환자를 식별한다. 제안하는 심층 잔류 순환 신경망은 심층 순환 신경망에 잔류 학습 방식을 결합한 알고리즘으로 파킨슨병 진단에서 기존의 식별 알고리즘보다 더 높은 인식률을 보인다.

Parkinson's disease, one of the three major diseases in old age, has more than 70 % of patients with speech disorders, and recently, diagnostic methods of Parkinson's disease through speech signals have been devised. In this paper, we propose a method of diagnosis of Parkinson's disease based on deep residual gated recurrent neural network using speech features. In the proposed method, the speech features for diagnosing Parkinson's disease are selected and applied to the deep residual gated recurrent neural network to classify Parkinson's disease patients. The proposed deep residual gated recurrent neural network, an algorithm combining residual learning with deep gated recurrent neural network, has a higher recognition rate than the traditional method in Parkinson's disease diagnosis.

키워드

GOHHBH_2019_v38n3_308_f0001.png 이미지

Fig. 1. Framework of training and testing procedure for proposed system.

GOHHBH_2019_v38n3_308_f0002.png 이미지

Fig. 2. Block diagram of DRGRNN.

Table 1. List of extracted speech features from speech signal.

GOHHBH_2019_v38n3_308_t0001.png 이미지

Table 2. Results of Parkinson’s patient classification through speech features.

GOHHBH_2019_v38n3_308_t0002.png 이미지

참고문헌

  1. M. A. Little, P. E. McSharry, E. J. Hunter, J. Spielman, and L. O. Ramig, "Suitability of dysphonia measurements for telemonitoring of Parkinson's disease," IEEE Trans. on Biomedical Engineering, 56, 1015-1022 (2009). https://doi.org/10.1109/TBME.2008.2005954
  2. T. K. Karikari, A. Charway-Felli, K. Hoglund, K. Blennow, and H. Zetterberg, "Commentary: global, regional, and national burden of neurological disorders during 1990-2015: a systematic analysis for the Global Burden of Disease Study 2015," Front. Neurol. 9, 1-2 (2018). https://doi.org/10.3389/fneur.2018.00001
  3. J. Jankovic, "Parkinson's disease: clinical features and diagnosis," J. Neurol. Neurosurg. Psychiatry, 79, 368-376 (2008). https://doi.org/10.1136/jnnp.2007.131045
  4. M. R. McNeil, Clinical Management of Sensorimotor Speech Disorders (Thieme, New York, 2009), pp. 166-186.
  5. L. Hartelius and P. Svensson, "Speech and swallowing symptoms associated with Parkinson's disease and multiple sclerosis: a survey," Folia Phoniatr Logop, 46, 9-17 (1994). https://doi.org/10.1159/000266286
  6. H. H. Kim, M. S. Lee, S. W. Kim, S. H. Choi, and W. Y. Lee, "An auditory-perceptual rating scale of dysarthric speech of patients with parkinsonism" (in Korean), Phonetics and Speech Sciences, 11, 39-49 (2004). https://doi.org/10.13064/KSSS.2019.11.3.039
  7. M. Shahbakhti, D. T. Far, and E. Tahami, "Speech analysis for diagnosis of Parkinson' disease using genetic algorithm and support vector machine," J. Biomedical Science and Engineering, 7, 147-156 (2014). https://doi.org/10.4236/jbise.2014.74019
  8. R. J. Holmes, J. M. Oates, D. J. Phyland, and A. J. Hughes, "Voice characteristics in the progression of Parkinson's disease," International Journal of Language & Communication Disorders, 35, 407-418 (2000). https://doi.org/10.1080/136828200410654
  9. Y. A. Kang, K. C. Yoon, C. J. Seong, and H. Y. Park, "A preliminary study of the automated assessment of prosody in patients with Parkinson's disease" (in Korean), The Korean Academy of Speech-Language Pathology and Audiology, 17, 234-248 (2012).
  10. Y. M. Go, D. Y. Kim, Y. L. Choi, and H. H. Choi, "Speech rate and pause characteristics in patients with Parkinson's disease" (in Korean), Phonetics and Speech Sciences, 2, 173-184 (2010).
  11. J. W. Chung, "Performance comparison of algorithm through classification of Parkinson's Disease according to the speech feature" (in Korean), J. Korea Multimedia Society, 19, 209-214 (2016). https://doi.org/10.9717/kmms.2016.19.2.209
  12. D. Gupta, A. Julka, S. Jain, T. Aggarwal, A. Khanna, N. Arunkumar, and V. H. C. de Albuquerque, "Optimized cuttlefish algorithm for diagnosis of Parkinson's disease," Cogn. Syst. Res. 52, 36-48 (2018). https://doi.org/10.1016/j.cogsys.2018.06.006
  13. B. Yue, J. Fu, and J. Liang, "Residual recurrent neural networks for learning sequential representations," Information, 9, 56;doi:10.3390 (2018). https://doi.org/10.3390/info9030056
  14. K. Zhang, W. Zuo, S. Member, Y. Chen, D. Meng, and L. Zhang, "Beyond a gaussian denoiser: residual learning of deep CNN for image denoising," IEEE Trans. on Image Processing, 26, 3142-3155 (2017). https://doi.org/10.1109/TIP.2017.2662206
  15. O. Levy, K. Lee, N. FitzGerald, and L. Zettlemoyer, "Long short-term memory as a dynamically computed element-wise weighted sum," ACL, 2, 732-739 (2018).
  16. Y. Wu, P. Chen, Y. Yao, X. Ye, Y. Xiao, L. Liao, M. Wu, and J. Chen, "Dysphonic voice pattern analysis of patients in Parkinson's Disease using minimum interclass probability risk feature selection and bagging ensemble learning methods," J. Comput. Math Methods Med. 4201984, 11 (2017).
  17. R. A. Shirvan and E. Tahami, "Voice analysis for detecting Parkinson' disease using genetic algorithm and KNN classification method," 18th ICBME, 278-283 (2011).