本論文改進傳統的語音濾波器無法消除中低頻雜訊與濾波器參數調整過高時會損害語音特色的缺憾，並將其應用在語音辨識上，然後以雙旋轉翼直昇機的音控來驗證設計結果。我們提出結合卡爾曼濾波器和模糊邏輯理論形成一個新型的模糊邏輯卡爾曼濾波器(Fuzzy Logic Kalman Filter, FLKF)來消除背景噪音並保留語音特色。當應用於吵雜環境時，本系統將特別有效，因系統會將卡爾曼濾波器的輸出訊號及誤差訊號變化量當作模糊邏輯系統的輸入，調變卡爾曼濾波器的 Q參數，以達到消除背景雜訊及語音強化的效果，來提升訊噪比與語音辨識率。
本論文設計一個語音辨識系統來控制雙旋轉翼直昇機。實作驗證內容計有(1)語音辨識的訊號前置處理效果；(2)使用波形分析與訊噪比計算，深入探討濾波器性能；(3)雙旋轉翼直昇機語音辨識音控驗證。經比較驗證本文所設計的新式模糊邏輯卡爾曼濾波器有較佳的雜訊消除能力與語音強化的效果，不但提高訊噪比，且可應用於設計語音辨識器的音控系統。

This thesis presents an improved speech filter ability to remove mid-low frequency noise and reserve the original speech characteristics. A speech recognition system is then designed to control the twin rotor helicopter system with voice input. A new fuzzy logic Kalman filter is proposed (FLKF) to filter out the noisy background and preserve speech characteristics. This system is particularly effective in collecting speech in a noisy environment. The parameter Q of the Kalman filter is tuned to achieve the strengthening effect of eliminating background noise and to promote the SNR and speech recognition rate.
A speech recognition system is designed to illustrate the twin rotor helicopter speech control function. The practical tests includes (1) the signal’s leading processing effect on speech recognition, (2) using wave analysis and signal noise ratio calculation to confer the filter’s function, and (3) verification of the speech recognition voice control for a twin rotor helicopter speech recognition controller. It is shown that the new Fuzzy Logic Kalman filter can perform better noise eliminating ability and speech enhancement function. In summary, the proposed method can improve the signal noise rate and have application in a speech recognition voice control system.

參考文獻

[1] 王小川，“語音訊號處理”，全華科技圖書公司，台灣、台北，2005年2月。
[2] 王立新，“自適應模糊系統與控制”，國防工業出版社，中國，北京，pp98-102，1995年10月。
[3] 余玉田，“雙自由度主動噪音控制之設計與實作”，國立中興大學機械工程研究所，碩士論文，2000年6月。
[4] 卓大靖、王聖鋐，“適應性模糊強跟蹤卡爾曼濾波器於導航系統之設計”，國立台灣海洋大學，通訊與導航工程系，碩士論文，2005年6月。
[5] 林士能，“具有線上輔助修正之前饋主動噪音控制器的設計與實作”，中興大學機械工程研究所，碩士論文，2001年6月。
[6] 林明鋒，“模型直昇機姿態控制”，碩士論文，國立中央大學電機工程研究所，2001年6月。
[7] 林鎮洲、徐偉群，“模糊卡爾曼濾波器應用於載具姿態判定”，國立臺灣海洋大學，機械與輪機工程學系，碩士論文，2003年6月。

[8] 楊憲東，“自動飛行控制原理與實務”，全華科技圖書，2000年5月。
[9] 楊鎮光，“Visual Basic 與語音辨識”，文魁資訊股份有限公司，臺灣、臺北，2002年6月。
[10] 葉智偉，“控制路徑頻譜整形於主動噪音控制之應用探討”， 國立中興大學機械工程研究所，碩士論文，2002年6月。
[11] 趙家賢，“結合第二路徑頻譜整形器之適應混合前饋式主動噪音控制”，國立中興，大學機械工程研究所，碩士論文，2003年6月。
[12] 顏坤銘、宋開泰，“家用機器人之語音辨識系統”，國立交通大學電機與控制工程學系，碩士論文，2002年7月。
[13] 羅子良，“含內部模式之 設計一維聲管主動噪音控制之應用與控制實作”，國立中興大學機械工程研究所，碩士論文，1998年6月。
[14] 羅華強，“訊號處理---MATLAB的應用”， 全華科技圖書公司，pp3-41，2003年8月。
[15] A. Harada, K. Nishikawa, H. Kiya, “A pipelined architecture for the normalized LMS adaptive digital filters,” IEEE Asia-Pacific Conference on Circuits and Systems, pp.73 -76, Nov, 1998.

[16] A. Subramanya, Z. Zhang, Z. Liu, A. Acero, “Speech Modeling with Magnitude-Normalized Complex Spectra and Its Application to Multisensory Speech Enhancement,” 2006 IEEE International Conference on Multimedia and Expo, pp.1157 -1160, July, 2006.

[17] A.S. Abutaleb, “Adaptive line enhancement using a random AR model,” IEEE Transactions on Acoustics, Speech, and Signal Processing, vol 38, No.7, pp.1211- 1215, July, 1990.

[18] B.T. Lilly, K.K. Paliwal, “Effect of speech coders on speech recognition performance,” ICSLP 96 Proceedings, Fourth International Conference on Spoken Language, vol. 4, pp. 2344 - 2347, Oct,1996.

[19] B. Widrow, S.D. Stearns, “Adaptive Signal Processing,” Englewood Cliffs, NJ: Prentice-Hall, 1984.
[20] C.L. Shih, M.L. Chen, J.Y. Wang, “Mathematical and Set-point Stabilizing Controller Design of a Twin Rotor MIMO System,” Asia Journal of Control, vol. 10, No. 1, February, 2008.
[21] C.L. Shih, M.L. Chen, “Mathematical Model and Stabilizing Controller Design of a Twin Rotor MIMO System,” IEEE ICSS2005 International Conference on Systems & Signals, pp934 - 939, April, 2005.
[22] C.T. Lin, “Single-channel speech enhancement in variable noise-level environment,” IEEE Transactions on Systems, Man and Cybernetics, vol. 33, No. 1, Part A, pp.137 - 143, Jan, 2003.
[23] D. Burshtein, S. Gannot, “Speech Enhancement Using a Mixture-Maximum Model,” IEEE Transaction on Vol. 10, No. 6, Speech And Audio Processing, pp. 326-332, September, 2002.
[24] E. Zavarehei, S.Vaseghi, Q. Yan, “Noisy Speech Enhancement Using Harmonic-Noise Model and Codebook-Based Post-Processing,” Audio vol 15, No. 4, pp.1194 - 1203, May, 2007.

[25] G. Chen, J. Wang, L.S. Shieh, “Interval Kalman filtering,” IEEE Transactions on Aerospace and Electronic Systems, vol. 33, No. 1, pp. 250 - 259, Jan, 1997.

[26] G. Kitagawa, W. Gersch, “A smoothness prior’s long AR model method for spectral estimation,” IEEE Transactions on Automatic Control, vol. 30, No. 1, pp.57 - 65, Jan, 1985.

[27] G. Sreenu, P. N. Girija, M. N. Prasad and M. Nagamani, “A Human Machine Speaker Dependent Speech Interactive System,” India Annual Conference, Proceedings of the IEEE INDICON, Dec, pp. 349 - 351, 2004.

[28] H. G.Hirsch, C. Ehrlicher, “Noise estimation techniques for robust speech recognition,” in Proc. 20th IEEE ICASSP’95, pp.153-156, May, 1995.
[29] H. Sorenson, Kalman Filtering, “Theory and Application,” IEEE Press, 1985.
[30] H. Suzuki, H. Zen, Y. Nankaku, C. Miyajima, K. Tokuda, and T. Kitamure, “Speech Recognition Using Voice-Characteristic Dependent Acoustic Models,” IEEE International Conference on Acoustics, Speech, and Signal Processing, vol .1, pp.I-740 - I-743, April, 2003.

[31] H. Y. Chang, N. K. Soo, S.Rahardja, “Kalman filtering speech enhancement incorporating masking properties for mobile communication in a car environment,” IEEE International Conference on Multimedia and Expo, vol. 2, pp.1343 - 1346, June, 2004.
[32] H.X. Li, G. Chen, “Fuzzy-PID Controller is a Quasi-Sliding Mode Controller with Dual Features, ” International Journal of Fuzzy Systems, vol. 5, No. 2, pp. 131-140, June, 2003.
[33] H.Y. Chang, S. Rahardja, N. K. soo, “Autoregressive Parameter Estimation for Kalman Filtering Speech Enhancement,” Acoustics, IEEE International Conference on Speech and Signal Processing, ICASSP 2007, vol. 4, pp.IV-913 - IV-916, April, 2007.
[34] I. Cohen, B. Berdugo, “Noise Estimation by Minima Controlled Recursive Averaging for Robust Speech Enhancement,” IEEE Signal Processing letters, vol. 9, No. 1, pp.12-15, January, 2002.
[35] I. Kokkinos, P. Maragos, “Nonlinear Speech Analysis Using Models for Chaotic System,” IEEE Transactions on Speech and Audio Processing, vol. 13, No. 6, pp.1098 - 1109, Nov, 2005.
[36] I. Mann, S. McLaughlin, “Synthesizing natural-sounding vowels using a nonlinear dynamical model,” Signal Process, vol. 81, pp. 1743 -1756, 2001.
[37] I. Cohen, B. Berdugo, “A Multi-Microphone Post-Filtering Approach for Speech Enhancement,” IEEE Signal Processing Letters, pp.312-322, March, 2002.
[38] I. Cohen, “Speech Enhancement Using a No causal A Priori SNR Estimator,” IEEE Signal Processing Letters, vol.11, No. 9, pp. 32 - 40, September, 2004.
[39] J. Huang, J. Zhao, Y. Xie, “Source classification using pole method of AR model,” 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP-97, vol. 1, April, pp.567 – 570, 1997.

[40] J. S. Lim, A. V. Oppenheim, “Enhancement and bandwidth compression of noisy speech,” Proc. IEEE, vol. 67, pp. 1586 -1604, Dec, 1979.
[41] J. S. Robert, L. H. Sandra, “Fundamentals of Digital Signal Processing Using MATLAB,” United States, Thomson, Feb, 2005.
[42] J. Wang, T. Zhang, “Degradation prediction method by use of autoregressive Algorithm”, IEEE International Conference on Industrial Technology, pp. 1 - 6, April, 2008.
[43] J.S. Hu, “Active Noise Cancellation in Ducts Using Internal Model-Based Control Algorithms,” IEEE Transactions on Control Systems Technology, vol.4, pp. 163-170, March, 1996.

[44] J.W. Pitton, K. Wang, B.H. Juang, “Time-frequency analysis and auditory modeling for automatic recognition of speech,” Proceedings of the IEEE, vol.84, No. 9, pp. 1199 - 1215, Sept, 1996.
[45] J.Z. Sasiadek, J. Khe, “ Sensor fusion based on fuzzy Kalman filter,” 2001 Proceedings of the Second International Workshop on Robot Motion and Control, pp.275 - 283, Oct,2001.

[46] J.T. Chien, P.Y. Lai, “Microphone Array Signal Processing for Far-Talking Speech Recognition,” Wireless Communications, 2001 IEEE Third Workshop on Signal Processing Advances, pp.322 - 325, March, 2001.

[47] J.Y. Wang, M.L. Chen, C.L. Shih, “Generalized Predictive Control in Flying Shear Equipment,” Journal of Advanced Computational Intelligence and Intelligent Informatics, vol.11 No.9, pp.1144 -1148, Nov, 2007.
[48] L. Singh, S. Sridharan, “Speech enhancement using pre-processing,” Speech and Image Technologies for Computing and Telecommunications’. Proceedings of IEEE vol. 2, pp.755 - 758, Dec, 1997.

[49] L.B. Fah, A. Hussain, S.A. Samad, “Speech enhancement by noise cancellation using neural network,” TENCON 2000. Proceedings vol.1, pp.39 - 42, Sept, 2000.

[50] L.X. Wang, J.M. Mendel, “Fuzzy Adaptive Filters, with Application to Nonlinear Channel Equalization,” IEEE Transactions on Fuzzy System, vol.1, No. 3, August 1993.
[51] L.X. Wang, “Self-Adaptive Fuzzy System Control,” national defense industry publisher, China Beijing, pp. 98 -102, Sept,1995.
[52] M. Arnold, “Reasoning about Non-Linear AR models using expectation maximization,” J. Forecast, vol.22, pp.479 - 490, Jan,2003.
[53] M. Banbrook, S. McLaughlin, and I. Mann, “Speech characterization and synthesis by nonlinear methods,” IEEE Transactions on Speech Audio Processing, vol.7, No.1, pp.1-17, Jan, 1999.
[54] M. Birgmeier, “A fully Kalman-trained radial basis function network for nonlinear speech modeling,” in Proc. Int. Conf. Neural Networks, pp.254 - 259, Nov, 1995
[55] M. Hayes, “Statistical Digital Signal Processing and Modeling,” John Wiley and Sons, 1996.
[56] M. K. Steven, “Modern Spectral Estimation: Theory and Application,” Prentice Hall, 1988.
[57] M. Montazeri, P. Duhamel, “A set of algorithms linking NLMS and block RLS algorithms,” IEEE Transactions on Signal Processing, vol. 43, No. 2, pp.444 -453, Feb, 1995.

[58] M. S. Brandstein, D. B. Ward, Eds., “Microphone Arrays: Signal Processing Techniques and Applications,” Springer-Verlag, Berlin, 2001.
[59] M.E. Dajer, J.C. Pereira, C.D. Maciel, “Nonlinear Dynamical Analysis of Normal Voices,” Seventh IEEE International Symposium on Multimedia, Dec, 2005.

[60] M. Ning, M. Bouchard, R. A. Goubran, “Speech enhancement using a masking threshold constrained Kalman filter and its heuristic implementations,” IEEE Transitions on Audio, Speech & Language Processing, vol. 14, No. 1, pp.19 -32, Jan, 2006.
[61] M. L. Chen, J. Y. Wang, C. L. Shih, “Dynamic system model predict and adaptive controller design,” Journal of Information & Optimization Sciences (EI), vol. 29, No.1, pp. 175-189, 2008.
[62] M. K. Hasan, M. R. Khan, “A Modified A Priori SNR for Speech Enhancement Using Spectral Subtraction Rules,” IEEE Signal Processing Letters, vol.11, No. 4, April, 2004
[63] N. Virag, “Single channel speech enhancement based on masking properties of the Human auditory system,” IEEE Transitions on Speech and Audio Processing, vol.7, No.2, pp. 126-137, 1999.
[64] P. Maragos, T. F. Quatieri, “Energy Separation in Signal Modulations with Application to Speech Analysis,” IEEE Transitions on Signal Processing, vol. 41, No. 10, October, 1993.
[65] P. C Loizou, “Signal processing for cochlear implants and low-rate speech coding,” IEEE Workshop on Speech Coding, Sept, pp. 68-78, 2000.

[66] P.M.T. Broersen; S. de Waele, “Automatic identification of time-series models from long autoregressive models,” IEEE Transactions on Instrumentation and Measurement, vol. 54, No. 5, pp. 1862 - 1868, Oct, 2005
[67] Q. Fan, K. Nonami, M. Nnkano, “Active Noise Control of Exhaust Duct Using Two-Degree-of-Freedom Control System with Model Matching,” JSME International Journal, Series C, Mechanical systems, machine elements and manufacturing, vol.40, No.2, 1997.
[68] R. Flynn, E. Jones, “Robust connected digit recognition using speech enhancement and an auditory model front-end,” 2007,6th International Conference on Information, Communications & Signal Processing, pp.1-4, Dec, 2007
[69] R. Martin, “Noise power spectral density estimation based on optimal smoothing and minimum statistics,” IEEE transactions on speech and audio signal processing, vol. 9, No. 5, pp.504 -512, July, 2001.
[70] R. C. Hendriks, R. Heusdens, J. Jensen, “Adaptive Time Segmentation for Improved Speech Enhancement,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 14, No. 6, pp. 2064 - 2074, Nov, 2006.

[71] R. G. Brown, P.Y.C. Hwang, “Introduction to random signals and applied Kalman filtering,” 3rd Edition, Wiley, New York, 1997.

[72] S. Haykin, “Adaptive Filter Theory,” Fourth Edition, PRENTICE HALL, Information and System Sciences Series, 2002.
[73] S. Gazor, Wei Zhang; “Speech enhancement employing Laplacian-Gaussian mixture,” IEEE Transactions on Speech and Audio Processing, vol. 13, No. 5, Part 2, pp.896 - 904, Sept, 2005
[74] S. Haykin, “Adaptive Filter Theory,” Englewood Cliffs, NJ: Prentice-Hall, 1996.
[75] S. K. Katsikas, S. D. Likothanassis, D. G. Lainiotis, “AR model identification with unknown process order,” IEEE Transactions on Acoustics, Speech and Signal Processing, vol. 38, No. 5, pp.872 - 876, May 1990.
[76] S. K. Tso, Y. H. Fung, “Methodological development of fuzzy-logic controllers from multivariable linear control,” IEEE Transactions on Systems, Man and Cybernetics, vol. 27, No. 3, pp. 566 -572, 1997.
[77] S. M. Kuo, D. R. Morgan, “Action Noise Control System: Algorithms and DSP Implementations,” 605 Third Avenue, New York, pp. 0012 - 0158, 1996.
[78] S. Yeldener, J. H. Rieser, “A background noise reduction technique based on sinusoidal speech coding systems,” IEEE International Conference on Acoustics, Speech, and Signal Processing , vol. 3, pp. 1391 - 1394, June, 2000.

[79] S. Gazor, W. Zhang, “Speech Enhancement Employing Laplacian-Gaussian Mixture,” IEEE Transactions on Speech and Audio Processing, vol. 13, No. 5,Part 2, pp. 896 - 904, Sept, 2005.
[80] S. T. Zhang, X. Y. Wei, “Fuzzy adaptive Kalman filtering for DR/GPS,” 2003 International Conference on Learning and Cybernetics Machine, vol. 5, Nov, pp. 2634 - 2637, Sept, 2003.

[81] T. Matsuura, H. Togiishi, “Two dimensional AR model of signing process and its application to on-line signature verification,” IEEE International Conference on Electronics, Circuits and Systems vol. 2, pp. 545 - 548, Sept,1998.

[82] T. Yamamoto, S. Omatu, M. Kaneda, “A Design Method of Self-Tuning PID controllers,” American Control Conference, vol. 3, 29 July, pp.3263 - 3267, 1994.
[83] T. H. Li, J. D. Gibson, “Speech Analysis and Segmentation by Parametric Filtering,” IEEE Transactions on Speech and Audio Processing, vol. 4, No.3, pp. 203 - 213, May, 1996.
[84] T. W. Lee, K. Yao, “Speech Enhancement By Perceptual Filter with Sequential Noise Parameter Estimation,” 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. 693-699, May,2004.

[85] Twin Rotor MIMO System--Advanced Teaching Manual 1, Feedback Instruments Ltd, UK,2001.
[86] V. G. Reju, T. Y. Chow, “A Computationally Efficient Noise Estimation Algorithm for Speech Enhancement,” The IEEE Asia-Pacific Conference on Circuits and Systems, December, 2004.
[87] V. Stahl, A. Fischer, R. Bippus, “Quartile based noise estimation for spectral subtraction and Wiener filtering,” IEEE International Conference on Acoustics, Speech and Signal Processing, vol.3, pp. 1875-1878, May,2000.
[88] W. Jin, M. S. Scordilis, “Speech Enhancement by Kalman Filtering with Residual Noise Clipping,” SoutheastCon, Proceedings. IEEE, April, pp.225 -228, 2005.

[89] W. Qiao, M. Mizumoto, “PID type fuzzy controller and parameters adaptive method,” Fuzzy Sets and Systems, vol. 78, pp. 23-35, 1996.
[90] W. H. Lan, C. L. Shih, M. L. Chen, “A Patter Free Algorithm to Inspect Open-Shorts of a Flex Circuit,” the 13th throughout the country automation science and technology workshop, pp.17-18, June, 2004.
[91] W. R. Wu, P. C. Chen,“Adaptive AR modeling in white Gaussian noise,” IEEE Transactions on Signal Processing, vol. 45, No. 5, pp.1184 - 1192, May, 1997.
[92] X. Cui, A. Alwan, “Noise Robust Speech Recognition Using Feature Compensation Based on Polynomial Regression of Utterance SNR,” IEEE Transitions on Speech and Audio Processing, vol.13, No.6, pp.324-334, May, 2006.
[93] X. Hu, A. q. Hu, L. Zhao, “A robust adaptive speech enhancement system,” Neural Networks and Signal Processing, Proceedings of the 2003 International Conference on vol. 1, Dec, pp. 814 - 817, 2003.

[94] X. Huang, A. Acero, and H. W. Hon, “Spoken language Processing, a guide to theory, algorithm and system development,” Prentice Hall, 2001.
[95] Y. Cai, “A Forecasting procedure for nonlinear autoregressive time series models,” J. Forecast, vol. 24, pp335 - 351, May, 2005.
[96] Y. Ephraim, D. Malah, “Speech enhancement using a minimum mean-square error short-time spectral amplitude estimator,” IEEE Transitions on Accost, speech, signal Proc, vol.1, No.1, pp. 1109-1121, 1984.
[97] Y. Hu, C. L. Philipos, “Speech Enhancement Based on Wavelet Thresholding the Multitaper Spectrum,” IEEE Transitions on Speech and Audio Processing, vol. 12, No.1, pp. 312-412, January, 2004.
[98] Y. Itoh, “A matching algorithm between arbitrary sections of two speech data sets for speech retrieval,” 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2001. Proceedings, vol. 1, pp. 593 - 596, May,2001.

[99] Y. Li, “Some Results of Fuzzy Turing Machines,” 2006.WCICA The Sixth World Congress On Intelligent Control and Automation, vol. 1, pp. 3406 -3409, 2006.

[100] Y. Nagata, T. Fujioka, M. Abe, “Speech enhancement based on auto gain control,” IEEE Transactions on Audio, Speech and Language Processing, vol. 14, No. 1, pp.177 - 190, Jan, 2006.

[101] Y. Tsuda, T. Shimamura, “An improved NLMS algorithm for channel equalization,” IEEE International Symposium on Circuits and Systems, vol. 5, pp. V-353 - V-356, May, 2002.

[102] Y. Hu, P. C. Loizou, “A subspace approach for enhancing speech corrupted by colored noise,” Signal Processing Letters, IEEE, vol. 9, No.7, pp. 204 - 206, July, 2002.
[103] Y. Zheng, Z. Lin, “Time-varying autoregressive system identification using wavelets,” Acoustics, Speech, and Signal Processing, vol. 1, pp.572 - 575, June, 2000.

[104] Y. J. Chen, C. C. Wang, G. J. Jong, and B. W. Wang, “The Separation System of the Speech Signals Using Kalman Filter with Fuzzy Algorithm,” Proceedings of the First International Conference on Innovative Computing, Information and Control, pp.321-329, 2006.
[105] Y. Lee, “Channel Prediction with Cascade AR Modeling,” Telecommunications, International Conference on Internet and Web Applications and Services/Advanced, pp.40-48, Feb, 2006.

[106] Y. Lee, “Channel Prediction with Cascade AR Modeling,” AICT-ICIW '06. International Conference on Internet and Web Applications and Services/Advanced International Conference on Telecommunications, pp.40-50, Feb, 2006.

[107] Z. Goh, K. C. Tan, B.T.G Tan, “Kalman-filtering speech enhancement method based on a voiced-unvoiced speech model,” IEEE Transactions on Speech and Audio Processing, vol. 7, No. 5, pp.510 - 524, Sept, 1999.
[108] Z. Wang, X. Zhang, “A high performance speech enhancement algorithm based on double-channel adaptive noise canceling,” IEEE International Symposium on Microwave, Antenna, Propagation and EMC Technologies for Wireless Communications Proceedings, pp.983 - 986, 2005.