Long-term Prediction of Speech Signal Using a Neural Network

신경 회로망을 이용한 음성 신호의 장구간 예측

  • 이기승 (건국대학교 정보통신대학 전자공학부)
  • Published : 2002.08.01

Abstract

This paper introduces a neural network (NN) -based nonlinear predictor for the LP (Linear Prediction) residual. To evaluate the effectiveness of the NN-based nonlinear predictor for LP-residual, we first compared the average prediction gain of the linear long-term predictor with that of the NN-based nonlinear long-term predictor. Then, the effects on the quantization noise of the nonlinear prediction residuals were investigated for the NN-based nonlinear predictor A new NN predictor takes into consideration not only prediction error but also quantization effects. To increase robustness against the quantization noise of the nonlinear prediction residual, a constrained back propagation learning algorithm, which satisfies a Kuhn-Tucker inequality condition is proposed. Experimental results indicate that the prediction gain of the proposed NN predictor was not seriously decreased even when the constrained optimization algorithm was employed.

본 논문에서는 선형 예측 후에 얻어지는 잔차 신호 (residual signal)를 신경 회로망에 바탕을 둔 비선형 예측기로 예측하는 방법을 제안하였다. 신경 회로망을 이용한 예측 방법의 타당성을 입증하기 위해, 먼저 선형 장구간 예측기와 신경 회로망이 도입된 비선형 장구간 예측기의 성능을 서로 비교하였다. 그리고 비선형 예측 후의 잔차 신호를 양자화 하는 과정에서 발생하는 양자화 오차의 영향에 대해 분석하였다. 제안된 신경망 예측기는 예측 오차뿐만 아니라 양자화의 영향을 함께 고려하였으며, 양자화오차에 대한강인성을 갖게 하기 위하여 쿤-터커 (Kuhn-Tucker) 부등식 조건을 만족하는 제한조건 역전파 알고리즘을 새로이 제안하였다. 실험 결과, 제안된 신경망 예측기는 제한조건을 갖는 학습 알고리즘을 사용했음에도 불구하고, 예측 이득이 크게 뒤떨어지지 않는 성능을 나타내었다.

Keywords

References

  1. Digital Processing of speech signals L.R.Rabiner;R.W.Schafer
  2. Proc. ICASSP '85 Coded-excited linear prediction (CELP): high-quality speech at very low bit rates M.Schroeder;B.Atal
  3. Proc. ICASSP '94 v.1 Non-linear short-term prediction in speech coding J.Thyssen;H.Nielsen;S.D.Hansen
  4. Proc. ICASSP '95 v.1 Quantization of non-linear predictors in speech coding J.Thyssen;H.Nielsen;S.D.Hansen
  5. Proc. IEEE-SP Workshop on Neural Networks for signal Processing Nonlinear predictive vector quantization with recurrent neural nets L.Wu;M.Niranjan;F.Fallside
  6. IEEE Trans. on Speech and Audio Processing v.2 no.Issue 4 Fully vector-quantized neural network-based code-excited nonlinear predictive speech coding L.Wu;M.Niranjan;F.fallside https://doi.org/10.1109/89.326608
  7. The Volterra and Wiener Theories of Nonlinear Systems M.Schetzen
  8. Proc. EUSIPCO '94 v.1 ADPCM with non linear predictors E.Mumolo;Alberto Carini;Diego Francescato
  9. Proc. ICASSP '95 Nonlinear prediction for speech coding using radial basis function F. Diaz-de-Maria;A. R. Figueiras-Vidal
  10. IEEE ASSP megazine An introduction to computing with neural nets R.P.Lippmann
  11. Neural Networks for Optimization and Signal Processing A.Cichocki;R.Unbehauen
  12. IEEE Trans. on Speech and Audio Processing v.3 no.4 A Mixed excitation LPC vocoder model for low bit rate speech coding A.V.McCree;T.P.Barnwell Ⅲ https://doi.org/10.1109/89.397089