DOI QR코드

DOI QR Code

Sustained Vowel Modeling using Nonlinear Autoregressive Method based on Least Squares-Support Vector Regression

최소 제곱 서포트 벡터 회귀 기반 비선형 자귀회귀 방법을 이용한 지속 모음 모델링

  • Published : 2007.12.25

Abstract

In this paper, Nonlinear Autoregressive (NAR) method based on Least Square-Support Vector Regression (LS-SVR) is introduced and tested for nonlinear sustained vowel modeling. In the database of total 43 sustained vowel of Benign Vocal Fold Lesions having aperiodic waveform, this nonlinear synthesizer near perfectly reproduced chaotic sustained vowels, and also conserved the naturalness of sound such as jitter, compared to Linear Predictive Coding does not keep these naturalness. However, the results of some phonation are quite different from the original sounds. These results are assumed that single-band model can not afford to control and decompose the high frequency components. Therefore multi-band model with wavelet filterbank is adopted for substituting single band model. As a results, multi-band model results in improved stability. Finally, nonlinear sustained vowel modeling using NAR based on LS-SVR can successfully reconstruct synthesized sounds nearly similar to original voiced sounds.

본 연구에서는 비선형 지속 모음 모델링을 위한 최소 제곱 서포트 벡터 회귀 기반 비선형 자귀회귀 방법을 소개하고 분석하였다. 비주기적인 파형 특성을 갖는 양성 후두 질환자 43명의 지속 모음을 대상으로 한 실험에서 제안된 비선형 합성기는 거의 완벽하게 혼란한 지속 모음을 생성하고 선형 예측 코딩은 할 수 없는 주파수 변동과 같은 자연스러운 음의 특성 또한 보존할 수 있었다. 하지만 일부 모음의 합성 결과 실제 원음과 다른 차이점을 보였다. 이러한 결과들은 단일 밴드 모델이 음의 고주파 성분을 조정, 분해 못하기 때문에 발생한 것이라 가정된다. 그러므로 웨이블릿 필터 뱅크를 이용한 멀티 밴드 모델을 단일 밴드 모델과 대치하여 실험을 수행한 결과 향상된 안정성을 보였다. 결과적으로 최소 제곱 서포트 벡터 회귀 기반 비선형 자귀회귀 방법은 성공적으로 원음에 가까운 합성음을 생성할 수 있다는 것을 확인 할 수 있었다.

Keywords

References

  1. Giovanni A, Robert D, Estubier N, Teston B: Objective evaluation of dysphonia: Preliminary results of a device allowing simultaneous acoustics and aerodynamics measurements. Folia, Phon. Logop
  2. Banci G, Monini S, Falaschi A, Sario N: Vocal fold disorder evaluation by digital speech analysis, J. Phonetics,1986, vol.14, pp.495-499
  3. Gavidia-Ceballos L, Hansen L: Direct speech feature estimation using an iterative EM algorithm for vocal fold pathology detection, IEEE Tr. on Biomedical Eng., 1996, vol. 43, pp.373-383 https://doi.org/10.1109/10.486257
  4. Laver J, Hiller S, Mackenzie J, Rooney E: An acoustic screening system for the detection of laryngeal pathology. J.Phonetics, vol.14, pp.517 -524
  5. J.C. Principe, A. Rathie, J.M. Kuo, Prediction of chaotic time series with neural networks and the issue of dynamic modeling, Int. J. Bifurcation Chaos, 1992, vol.2, pp. 989 - 996 https://doi.org/10.1142/S0218127492000598
  6. C.S. Blackburn, Articulatory Methods for Speech Production and Recognition, PhD Thesis, Cambridge University Engineering Department, 1996
  7. Rabiner L. and Juang B. H., Fundamentals of speech recognition, Prentence Hall, NJ, 1993
  8. Klatt, D, Review of text-to-speech conversion for english, J. of Acoust Socof Am., 1987, vol.82, pp. 737-793 https://doi.org/10.1121/1.395275
  9. V. Vapnik, The Nature of Statistical Learning Theory, Springer Verlag, New York, 1995
  10. Golub, G.H. and C.F. Van Loan, Matrix Computations. John Hopkins University Press, 1989
  11. J. Mercer, Functions of positive and negative type and their connection with the theory of integral equations, Philos. Trans. Roy. Soc. London 1909
  12. B. Schlkopf, A. J. Smola, Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, MIT Press, 2001
  13. H. Yasukawa, Signal restoration of broad band speech using nonlinear processing, Proceedings of EUSIPCO'96, Trieste, Italy, Sept. 1996
  14. R.E. Crochiere, L.R. Rabiner, Multirate Digital Signal Processing, Prentice-Hall, Englewood CliLs, NJ, 1983
  15. N.J. Fleige, Multirate Digital Signal Processing (Multirate systems, Filter Banks, Wavelet), Wiley, New York, 1994
  16. M.R. Petraglia, S.K. Mitra, Performance analysis of adaptive filter structures based on subband decomposition, Proceedings of the IEEE International Symposium on Circuit and Systems, Chicago, IL, 1993, pp. 60 - 63

Cited by

  1. Modeling of Winter Time Apartment Heating Load in District Heating System Using Reduced LS-SVM vol.27, pp.6, 2015, https://doi.org/10.6110/KJACR.2015.27.6.283