An SVM-based physical fatigue diagnostic model using speech features

음성 특징 파라미터를 이용한 SVM 기반 육체피로도 진단모델

  • Received : 2016.01.20
  • Accepted : 2016.02.29
  • Published : 2016.06.30


This paper devises a model to diagnose physical fatigue using speech features. This paper presents a machine learning method through an SVM algorithm using the various feature parameters. The parameters used include the significant speech parameters, questionnaire responses, and bio-signal parameters obtained before and after the experiment imposing the fatigue. The results showed that performance rates of 95%, 100%, and 90%, respectively, were observed from the proposed model using three types of the parameters relevant to the fatigue. These results suggest that the method proposed in this study can be used as the physical fatigue diagnostic model, and that fatigue can be easily diagnosed by speech technology.


physical fatigue;diagnosis;speech features;SVM


  1. Lee, C. M., Ko, H. W., & Yun, Y. H. (2000). The study on Korean-version-questionnaire for measurement of mental fatigue during monotonous task. Proceedings of Spring Conference of the Korean Society for Emotion and Sensibility (pp. 195-202). (이창미.고한우.윤용현 (2000). 단조작업시 정신피로도 측정을 위한 한국어판 질문지에 관한 연구. 한국감성과학회 춘계 학술대회 논문집, 195-202.)
  2. Yun, Y. H., Ko, H. W., Kim, D. Y., & Lee, C. M. (1999). Assesment of mental fatigue during monotonous task. Proceedings of Autumn Conference of the Korean Society for Emotion and Sensibility (pp. 222-226). (윤용현.고한우.김동윤.이창미 (1999). 단조작업에 의한 정신피로의 평가-생리신호를 중심으로. 감성공학 추계학술대회 논문집, 222-226.)
  3. Ko, H. W., Yun, Y. H., Kim, D. Y., & Lee, C. M. (2000). Measurement and assessment of mental fatigue using bio-signals during monotonous task. Korean Journal of the Science of Emotion & Sensibility, 3(1), 1-6. (고한우.윤용현.김동윤.이창미 (2000). 생리신호를 사용한 단조 작업 수행시 정신피로도의측정과 평가, 한국감성과학회지, 3(1), 1-6.)
  4. Lin, C. T., Wu, R. C., Jung, T. P., Liang, S. F., & Huang, T. Y. (2005). Estimating driving performance based on EEG spectrum analysis. European Association for Signal Processing (EURASIP) Journal on Applied Signal Processing, 19, 3165-3174.
  5. Kim, S. W. & Park, S. J. (2002). An assessment method of fatigue in a long-term driving. Proceedings of Spring Conference of the Korea Industrial and Systems Engineering (pp. 785-791). (김선웅.박세진 (2002). 장시간 주행에 따른 피로도 평가방법에 관한 연구. 대한산업공학회/한국경영과학회 2002 춘계공동학술대회, 785-791.)
  6. Kim, T. H. & Kwon, C. H. (2015). Correlation between physical fatigue and speech signals. Phonetics and Speech Sciences, 7(1), 11-17. (김태훈.권철홍 (2015). 육체피로와 음성신호와의 상관관계. 말소리와 음성과학, 7(1), 11-17.)
  7. Borg, G. (1982). Psychophysical bases of perceived exertion. Medicine and Science in Sports and Exercise, 14(5), 377-381.
  8. E2-KIT. (2010). KTMED Inc. Retrieved from on January 10, 2016.
  9. Jeong, O. R. (1994). Speech overall evaluation. Proceedings of the 2nd Conference of the Korean Society of Spoken Language (pp. 101-109). (정옥란 (1994). 음성총괄평가. 제2회 대한음성언어학회 학술대회 논문집, 101-109.)
  10. Boersma, P. & Weenink, D. (2016). Praat: doing phonetics by computer [Computer program]. Version 6.0.10. Retrieved from on January 10, 2016
  11. Shue, Y. L., Keating, P., Vicenik, C., Yu, K. (2011). VoiceSauce: A program for voice analysis. Proceedings of the 17th International Congress of Phonetic Sciences (pp. 1846-1849).
  12. Multi-Dimensional Voice Program. (2016). Pentax Medical. Retrieved from January 10, 2016.
  13. Kim, J. I. & Kwon, C. H. (2014). Measuring correlation between mental fatigues and speech features. Phonetics and Speech Sciences, 6(2), 3-8. (김정인.권철홍 (2014). 정신피로와 음성특징과의 상관관계 측정. 말소리와 음성과학, 6(2), 3-8.)
  14. Kim, H. S., Kwon, Y. H., & Cha, S. D. (2003). Efficient masquerade detection based on SVM. Journal of Korea Institute of Information Security and Cryptology, 13(5), 91-104. (김한성.권영희.차성덕 (2003). SVM 기반의 효율적인 신분위장기법 탐지. 한국정보보호학회 정보보호학회 논문지, 13(5), 91-104.)
  15. Lee, S. J. & Lee, M. H. (2011). Development of electrocardiogram identification algorithm using SVM classifier. Journal of Korea Institute of Electrical Engineering, 60(3), 651-661. (이상준.이명호 (2011). SVM 분류기를 이용한 심전도 개인인식 알고리즘개발. 대한전기학회 논문집, 60(3), 651-661.)
  16. Sim, W. S., Sung, S. Y., & Jung, C. K. (2009). Performance analysis of Kernel function for support vector machine. Proceedings of 2009 Symposium on Information and Control Systems (pp. 405-407). (심우성.성세영.정차근 (2009). Supportvector machine 에 대한 커널 함수의 성능 분석. 2009 대한전기학회 정보및제어심포지엄 논문집, 405-407.)
  17. Chang, C. C. & Lin, C. J. (2011). LIBSVM : a library for support vector machines. Association for Computing Machinery(ACM) Transactions on Intelligent Systems and Technology, 2(27), 1-27, Retrieved from on January 10, 2016.
  18. Klatt, D. H. & Klatt, L. C. (1990). Analysis, synthesis, and perception of voice quality variations among female and male speakers. Journal of the Acoustical Society of America, 87(2), 820-857.
  19. Hwang, Y. S. & Seong, C. J. (2008). Comparative study on the acoustic characteristics of the Korean vowel /a/ before and after LMS. Malsori, 67, 33-60. (황연신.성철재 (2008). 후두미세수술전후 /아/의 음향적 특성 비교. 말소리, 67, 33-60.)
  20. Hillenbrand, J. & Houde, R. A. (1996). Acoustic correlates of breathy vocal quality: dysphonic voices and continuous speech. Journal of Speech and Hearing Research, 39, 311-321.
  21. Park, H. S. (2007). An acoustic study of phonation types in vowels following consonant clusters in Korean. Malsori, 64, 53-76. (박한상 (2007). 한국어 자음군의 후행모음에 나타난 발성유형의 음향음성학적 연구. 말소리, 64, 53-76.)
  22. Kim, Y. M. & Choi, K. H. (2000). Mathematical programming application for clustering problems in conjunction with confusing matrix. Proceedings of 2000 Conference of the Korea Industrial and Systems Engineering (pp. 605-608). (김영민.최경현 (2000).혼동 행렬을 이용한 클러스터링 문제의 수리 계획적 접근. 대한산업공학회/한국경영과학회 2000 년도 학술대회 논문집,605-608.)


Supported by : 한국연구재단