Journal of Internet Computing and Services (인터넷정보학회논문지)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Personal Credit Evaluation System through Telephone Voice Analysis: By Support Vector Machine

  • Received : 2018.08.29
  • Accepted : 2018.11.20
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The human voice is one of the easiest methods for the information transmission between human beings. The characteristics of voice can vary from person to person and include the speed of speech, the form and function of the vocal organ, the pitch tone, speech habits, and gender. The human voice is a key element of human communication. In the days of the Fourth Industrial Revolution, voices are also a major means of communication between humans and humans, between humans and machines, machines and machines. And for that reason, people are trying to communicate their intentions to others clearly. And in the process, it contains various additional information along with the linguistic information. The Information such as emotional status, health status, part of trust, presence of a lie, change due to drinking, etc. These linguistic and non-linguistic information can be used as a device for evaluating the individual's credit worthiness by appearing in various parameters through voice analysis. Especially, it can be obtained by analyzing the relationship between the characteristics of the fundamental frequency(basic tonality) of the vocal cords, and the characteristics of the resonance frequency of the vocal track.In the previous research, the necessity of various methods of credit evaluation and the characteristic change of the voice according to the change of credit status were studied. In this study, we propose a personal credit discriminator by machine learning through parameters extracted through voice.

인간의 목소리는 사람간의 정보 전달을 위한 가장 쉬운 방법 중 하나이다. 음성의 특징은 사람마다 다를 수 있으며 발성 속도, 발성기관의 형태와 기능, 피치 톤, 언어 습관 및 성별에 따라 다르게 나타난다. 목소리는 사람의 의사소통 핵심 요소이다. 제 4 차 산업 혁명의 시대에 목소리는 사람과 사람, 사람과 기계, 기계 와 기계 사이의 주요한 의사소통 수단이 된다. 그 이유 때문에 사람들은 자신의 의도를 다른 사람들에게 명확하게 전달하려고 노력한다. 그리고 이 과정에서 목소리는 언어 정보와 함께 다양한 추가 정보가 포함되게 된다. 예를 들어 감정 상태, 건강 상태, 신뢰도와 관련되거나, 거짓말의 여부, 음주로 인한 목소리의 변화 등 다양한 언어 및 비언어 정보를 포함하며, 다양한 분석 파라미터로 나타나게 된다. 이를 활용하면 개인의 신용도를 평가하는 척도로 사용할 수 있다. 특히 성대의 기본 주파수의 특성과 성도의 공진 주파수 특성의 관계를 분석함으로써 얻을 수 있다. 이전의 연구에서 다양한 신용 상태의 변화에 따른 목소리 분석 및 특성 변화를 연구 하였다. 본 연구에서는 음성을 통해 추출 된 매개 변수를 통해 기계 학습을 통한 개인 신용 판별 기를 제안한다.

Keywords

OTJBCD_2018_v19n6_63_f0001.png 이미지

(Figure 1) Voice Generation flow diagram [11]

OTJBCD_2018_v19n6_63_f0002.png 이미지

(Figure 2) Block diagram of proposed method

OTJBCD_2018_v19n6_63_f0003.png 이미지

(Figure 3) Pitch contour of speeches

OTJBCD_2018_v19n6_63_f0004.png 이미지

(Figure 4) Formant and formant slope of normal

OTJBCD_2018_v19n6_63_f0005.png 이미지

(Figure 5) Formant and formant slope of default

OTJBCD_2018_v19n6_63_f0006.png 이미지

(Figure 6) Cepstrum analysis of normal voice

OTJBCD_2018_v19n6_63_f0007.png 이미지

(Figure 7) Cepstrum analysis of default voice

(Table 1) Pitch variation of normal debtor

OTJBCD_2018_v19n6_63_t0001.png 이미지

(Table 2) Pitch variation of default occurred

OTJBCD_2018_v19n6_63_t0002.png 이미지

(Table 3) Some data for SVM learning

OTJBCD_2018_v19n6_63_t0003.png 이미지

(Table 4) Variable table

OTJBCD_2018_v19n6_63_t0004.png 이미지

References

  1. H.W. Park, "A Study on Personal Credit Evaluation System through Voice Analysis: By Machine Learning Method," KSII, The 9th International Conference on Internet (ICONI), Vientiane Laos 2017.12.
  2. Sangmin Lee, "Evaluation of Mobile Application in User's Perspective: Case of P2P Lending Apps in FinTech Industry." KSII Transactions on Internet & Information Systems vol.11, No. 2, 2017.
  3. J.W. Park, H.W Park and S.Mm Lee, “An Analysis on Reliability Parameter Extraction Using Formant of Voice over Telephone,” Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, Vol. 7, No. 3, pp. 183-190, 2015.
  4. H.W Park, M.J Bae, “Analysis of Confidence and Control through Voice of Kim Jung-un's,” INFORMATION, Vol. 19, No. 5, pp. 1469-1474, 2016.
  5. Kun Han, Dong Yu, Ivan Tashev, "Speech Emotion Recognition Using Deep Neural Network and Extreme Learning Machine," INTERSPEECH,, pp. 223-227, 2014.
  6. YI-LIN LIN, GANG WEI, "SPEECH EMOTION RECOGNITION BASED ON HMM AND SVM," Proceedings of the Fourth International Conference on Machine Learning and Cybernetics, Guangzhou, pp. 4898-4901, August 2005.
  7. Fundamentals of Telephone Communication Systems. Western Electric Company. p. 2.1, 1969.
  8. Mathworks, eBook of Matlab and machine learning, 2017. https://kr.mathworks.com/campaigns/products/offer/machine-learning-with-matlab.html
  9. C.W. Kim and W.G. Yun, Support vector machine and manufacturing application, Chaos book, 2015.
  10. MyungJin Bae, Sanghyo Lee, Digital Voice Analysis, Dongyoung press, 1987.
  11. L.R. Ribiner, R.W. Schafer, Theory and Applications of Digital Speech Processing, PEARSON, 2011.
  12. H.W. Park, M.S. Kim, M.-J. Bae, "Improving pitch detection through emphasized harmonics in time-domain," Communications in Computer and Information Science(CCIS), Vol. 352, pp. 184-189, 2012.
  13. Andreas Vlachos, "Active Learning with Support Vector Machines," Master thesis, University of Edinburgh, 2004.
  14. Suykens, Johan AK, and Joos Vandewalle. "Least squares support vector machine classifiers." Neural processing letters Vol. 9, No. 3, pp. 293-300, 1999. https://doi.org/10.1023/A:1018628609742
  15. Fung, Glenn M., and Olvi L. Mangasarian. "Multicategory proximal support vector machine classifiers." Machine learning Vol. 59 No. 2, pp. 77-97, 2005. https://doi.org/10.1007/s10994-005-0463-6
  16. Yoon, Sang-Hoon, and Myung-Jin Bae. "Analyzing characteristics of Natural Seismic Sounds and Artificial Seismic Sounds by using Spectrum Gradient." Journal of the Institute of Electronics Engineers of Korea SP, Vol. 46, No. 1, pp. 79-86, 2009.
  17. Huang, Guang-Bin, et al. "Extreme learning machine for regression and multiclass classification." IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) Vol. 42,No. 2, pp. 513-529, 2012. https://doi.org/10.1109/TSMCB.2011.2168604
  18. Lu, Zheng, et al. "Integrating Granger Causality and Vector Auto-Regression for Traffic Prediction of Large-Scale WLANs." KSII Transactions on Internet and Information Systems (TIIS) Vol. 10, No. 1, pp. 136-151, 2016. https://doi.org/10.3837/tiis.2016.01.008
  19. Lee, DoYeob, DongKyoo Shin, and DongIl Shin. "A Finger Counting Method for Gesture Recognition." Journal of Internet Computing and Services Vol. 17, No. 2, 2016, pp. 29-37. https://doi.org/10.7472/jksii.2016.17.2.29
  20. Su, Ching-Liang. "Ear Recognition by Major Axis and Complex Vector Manipulation." KSII Transactions on Internet & Information Systems Vol. 11, No. 3, 2017. https://doi.org/10.3837/tiis.2017.03.022
  21. Haruma Ishidaa, Yu Oishib, Keitaro Moritac, Keigo Moriwakic, Takashi Y. Nakajimab, "Development of a support vector machine based cloud detection method for MODIS with the adjustability to various conditions," remote sensing of environment Vol. 205, pp. 390-407, 2018. https://doi.org/10.1016/j.rse.2017.11.003