臺灣博碩士論文加值系統

聲音辨識的研究在學術界與業界均行之有年，許多研究人員努力的辨識出更複雜的聲音。聲音辨識往往是利用關聯或規則，尋找出聲音資訊中所含的意義。電腦有了聲音辨識的技術之後，便可以由人的聲音當作指令再經過電腦的判斷，來完成人類所交待的事項。只不過這些聲音的研究大多在於人類的語音或音樂，對於人們生活周遭中必定會遇到的，救護車鳴笛聲辨識卻是屈屈可數。
本論文提出一種辨識救護車聲音的方法，該方法以Support Vector Machine做為分類的基礎，分為訓練過程與辨識過程。訓練過程中，由乾淨的救護車鳴笛聲萃取進行訓練，並以救護車鳴笛聲低頻600-750Hz、高頻900-1050Hz為聲音的特徵，結合Support Vector Machine作為聲音辨識方法。在辨識過程中，使用在道路上錄製的聲音檔，分別有汽、機車及救護車混合的聲音和單純汽、機車的聲音。將聲音檔以0.1秒切割成一個frame，使用快速傅利葉轉換將時域資料轉為頻域資料，截取聲音中我們所要的頻率特徵，利用訓練所得到的分類模型，來判斷是否為救護車鳴笛聲。

Study the implementation of voice recognition for a long time, many researchers to identify more complex sound. Use of voice recognition is usually associated with, or rules, to find out the meaning of the sound. Computer voice recognition techniques, the computer can use voice control. However, almost all of these voices voice or music, for the road will have to face sound of ambulance siren is very little recognition.
This paper presents an ambulance voice recognition method to Support Vector Machine as the basis of classification, the process is divided into the training process and the identification process. Training process, from the clean sound of an ambulance train whistle. Ambulance siren sound low frequency 600-750Hz, high-frequency 900-1050Hz for voice features, combined with Support Vector Machine as a voice recognition method. In the identification process, the use of recorded sound on the road. Cars ambulance siren sound mixing, and pure cars sound. 0.1 seconds the sound file to cut a frame, using the FFT to time domain data into frequency domain data. The frequency of interception we want to use the training received classify model, identify whether there is an ambulance siren sound.

目錄
中文摘要 I
Abstract II
誌謝 III
目錄 IV
第一章、緒論 1
1.1、研究背景與文獻回顧 1
1.2、研究動機與目的 7
1.3、論文架構 9
第二章、研究方法描述 10
2.1、SVM簡介 10
2.2、線性可分SVM 11
2.2.1、最佳分類超平面(Optimal Separating Hyper-plane) 17
2.2.2、Soft-Margin SVM 20
2.3、非線性SVM 21
2.4、二次最佳化問題 24
2.4.1、Karush-Kuhn-Tucker 24
2.4.2、Lagrange multipliers and optimization problems 25
2.4.3、SVM優點 27
第三章、實驗方法 29
3.1、音框處理 29
3.2、傅氏轉換與濾波 30
3.3、特徵萃取 35
第四章、實驗結果 37
4.1、取樣 37
4.2、條件設定及實驗結果 38
第五章、結論 46
參考文獻 48
圖目錄
圖 1:二類別間可能的超平面 12
圖 2:任意一個超平面 12
圖 3:最佳分類超平面 13
圖 4:二維空間資料點示意圖 14
圖 5:最佳分類超平面及Support Hyper-plane示意圖 16
圖 6:分類最佳化示意圖 19
圖 7:加入ξ函數 21
圖 8:分類錯誤 21
圖 9:非線性映射函數 轉換示意圖 22
圖 10 :SVM分類問題處理架構 28
圖 11:訊號長度1秒 29
圖 12:訊號長度為0.1秒 30
圖 13: 低頻(L)及高頻(H)的頻譜變化對照圖(continue) 35
圖 14:救護車鳴笛訊號長度1秒 36
圖 15:救護車鳴笛訊號長度為1秒的高低頻分佈 36
圖 16 :SVM訓練流程圖 40
圖 17 :SVM辨識流程圖 40
圖 18:乾淨救護車鳴笛聲訓練結果 41
圖 19:距離5公尺辨識結果 41
圖 20:距離10公尺辨識結果 42
圖 21:距離25公尺辨識結果 42
圖 22: 距離30公尺辨識結果 43
圖 23: 距離40公尺辨識結果 43
圖 24: 距離50公尺辨識結果 44
圖 25: 距離60公尺辨識結果 44
圖 26:單純汽、機車雜音辨識結果 45
表目錄
表 1:常見核心函數類型 23
表 2:不同距離下辨識準確率 39

[1]. P. Fan, “Improving Broadcasting Performance by Clustering with Stability for Inter-Vehicle Communication,” in Proceedings of IEEE 65th Vehicular Technology Conference, Dublin, Ireland, Apr. 2007, pp. 2491-2495.

[2]. Y. Gunter, B. Wiegel, and H. P. Grossmann, “Cluster-based Medium Access Scheme for VANETs,” in Proceedings of IEEE Intelligent Transportation Systems Conference, Seattle, Washington, U.S.A., Sept. – Oct. 2007, pp. 343-348.

[3]. M. Kafsi, P. Papadimitratos, O. Dousse, T. Alpcan, J. P. Hubaux, “VANET Connectivity Analysis,” in Proceedings of IEEE Workshop on Automotive Networking and Applications, New Orleans, LA, U.S.A., Dec. 2008, pp. 1-10.

[4]. T. D. C. Little, A. Agarwal, “An information propagation scheme for VANETs,” in Proceedings of IEEE Intelligent Transportation Systems, Vienna, Austria, Sept. 2005, pp. 155-160.

[5]. T. H. Ho and S. J. Chung, “A compact 24 GHz radar sensor for vehicle sideway-looking applications,” Microwave Conference, European, Oct. 2005, pp. 351-354.

[6]. J. Song, P. Hsu, R. Wiese, and T. Talty, “Modeling Signal Strength Range of TPMS in Automobiles”, IEEE Transactions on Antennas and Propagation Society Symposium, Vol. 3, 2004, pp. 3167-3170.

[7]. 陳禎福，「汽車底盤控制技術的現狀和發展趨勢」，汽車工程，第28卷，第2期，2006，第105-113頁。

[8]. W. P. B. Broeders ,“How to organize a national RDS/TMC service in The Netherlands”, IEEE Conference Proceeding, Vol.7, 1996, pp. 111-117.

[9]. 黃全淯，車載感測網路於大範圍環境監測二氧化碳之應用，碩士論文，國立交通大學資訊科技產學專班，新竹，2008。

[10]. Laws & Regulations Database of The Republic of China, retrieved form http://law.moj.gov.tw/LawClass/LawAll.aspx?PCode=K0040013, 2010.

[11]. S. T. Roweis, “One Microphone Source Separation,” in Proceeding of Neural Information Processing Systems, Seattle, Washington, U.S.A., Apr. 2000, pp. 793-799.

[12]. F. R. Bach and M. I. Jordan, “Blind One-Microphone Speech Separation: A Spectral Learning Approach,” in Proceedings of Neural Information Processing Systems, Vol. 17, Vancouver, British Columbia, Canada, Dec. 2005, pp. 65-72.

[13]. L. Bonaroya and F. Bimbot, “Wiener Based Source Separation with HMM/GMM Using a Single Sensor,” International Symposium on Independent Component Analysis and Blind Signal Separation, Nara, Japan, Apr. 2003, pp. 957-961.

[14]. L. Bonaroya, F. Bimbot, and R. Gribonval, “Audio Source Separation with a Single Sensor,” Journal of IEEE Transactions on Audio, Speech, and Language Processing, Vol. 14, No. 1, 2006, pp. 191-199.

[15]. V. Vapnik, S. Golowich, and A. J. Smola, “Support vector method for function approximation, regression estimation, and signal processing,” in Proceedings of the 9th Neural Information Processing Systems, Denver, Colorado, U.S.A., Dec. 1997, pp. 281-287.

[16]. C. Cortes and V. Vapnik, “Support vector networks,” Machine Learning, Vol. 20, No. 3, 1995, pp. 273-297.

[17]. V. Vapnik, The Nature of Statistical Learning Theory. Springer Verlag, New York, 1995.

[18]. V. Vapnik, Statistical Learning Theory. Wiley, New York, 1998.

[19]. B. Schölkopf, S. Mika, C. Burges, P. Knirsch, K.-R. Müller, G. Rätsch, and A. Smola, “Input space vs. feature space in kernel-based methods,” Journal of IEEE Transactions on Neural Networks, Vol. 10, No. 5, 1999, pp. 1000-1017.

[20]. E. Osuna, R. Freund, and F. Girosi, “Support vector machines: Training and applications,” Technical Report, AIM-1602, MIT A.I. Lab.,1996.

[21]. C. J. C. Burges, “A tutorial on support vector machines for pattern recognition,” Journal of Data Mining and Knowledge Discovery, Vol. 2, No. 2, 1998, pp. 121-167.

[22]. A. J. Smola and B. Schölkopf, “A tutorial on support vector regression,” Journal of Statistics and Computing, Vol. 14, No. 3, 2004, pp. 199-222.

[23]. J. C. Burges and B. Schölkopf, “Improving the accuracy and speed of support vector learning machines,” in Proceedings of the 9th Neural Information Processing Systems, Denver, Colorado, U.S.A., Dec. 1997, pp. 375-381.

[24]. G. Fung, O. L. Mangasarian, and J. Shavlik, “Knowledge-based support vector machine classifiers,” in Proceedings of the 14th Neural Information Processing, Cornell University, New York, U.S.A., Dec. 2002, pp. 213-221.

[25]. T. Joachims, “Text categorization with support vector machines: learning with many relevant features,” in Proceedings of 10th European Conference on Machine Learning, Chemnitz, Germany, Apr. 1998, pp. 137-142.

[26]. K. Crammer and Y. Singer, “On the learnability and design of output codes for multiclass problems,” in Proceedings of Computational Learning Theory, Stanford University, California, U.S.A., Jun, 2000, pp. 35-46.

[27]. K.-R. Müller, A. Smola, G. Rätsch, B. Schölkopf, J. Kohlmorgen, and V. Vapnik, “Predicting time series with support vector machines,” in Proceedings of Artificial Neural Networks, Lausanne, Switzerland, Oct. 1997, pp. 999-1004.

[28]. S. Mukherjee, E. Osuna, and F. Girosi, “Nonlinear prediction of chaotic time series using support vector machines,” in Proceedings of IEEE Workshop on Neural Networks for Signal Processing, Florida, U.S.A., Sept. 1997, pp. 511-519.

[29]. F. E. H. Tay and L. Cao, “Application of support vector machines in financial time series forecasting,” Omega, Vol. 29, No. 4, pp. 309-317, 2001.

[30]. L. J. Cao, K. S. Chua, and L. K. Guan, “c-ascending support vector machines for financial time series forecasting,” in Proceedings of International Conference on Computational Intelligence for Financial Engineering, Hong Kong, China, Mar. 2003, pp. 317-323.

[31]. H. Drucker, C. J. C. Burges, L. Kaufman, A. Smola, and V. Vapnik, “Support vector regression machines,” in Proceedings of the 9th Neural Information Processing Systems, Denver, Colorado, U.S.A., Dec. 1997, pp. 155.

[32]. National Fire Agency, Ministry of The Interior R.O.C. (Taiwan), retrieved form http://www.stat.gov.tw/, 2009.

[33]. F. Beritelli, S. Casale, A. Russo, and S. Serrano, “An Automatic Emergency Signal Recognition System for The Hearing Impaired,” in Proceedings of 12th Digital Signal Processing Workshop and 4th Signal Processing Education Workshop, Jackson Lake Lodge Grand Teton National Park, Wyoming, U.S.A., Sept. 2006, pp. 179-182.

[34]. M. A. Hearst, “Support vector machines,” IEEE Intelligent Systems, Vol. 13, No. 4, Janu. 1998, pp. 18-28.


[35]. T. Joachims, “A statistical learning model of text classification with support vector machines,” In Proceedings of 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, New Orleans, U.S.A., Sept. 2001, pp. 128-136.

[36]. T. Joachims, Learning to Classify Text Using Support Vector Machines. Kluwer academic Publishers, Massachusetts, 2001.

[37]. S. R. Gunn, “Support Vector Machine for Classification and Regression,” Technical Report, University of southampton, Department of Electronics and Computer Science, Southampton, Hampshire, UK, 10, May, 1998.

[38]. M. Klaus-Robert, M. Sebastian, R. Gunnar, T. Koji and S. Bernhard, “A Introduction to Kernel-Based Learning Algorithms,” Journal of IEEE Transaction on Neural Network, Vol. 12, No. 2, 2001, pp. 181-201.

[39]. J. Nocedal and S. J. Wright, Numerical Optimization Springer Series in Operations Research. Springer Verlag, New York, 1999, pp. 491-527.

[40]. R. Fletcher, “A general quadratic programming algorithm,” Journal of the Institute of Mathematics and its Applications, Vol. 7, 1971, pp. 76-91.

[41]. T. Joachims, “Learning to Classify Text Using Support Vector Machines: Methods, Theory, and Algorithms,” Kluwer academic Publishers, Vol. 29, No. 4, 2002, pp. 656-664.

[42]. N. V. Viadimir, Statistical Learning Theory. Wiley-Interscience Publication, New York, 1998.

[43]. N. V. Viadimir, “An Overview of Statistical Learning Theory,” Journal of IEEE Transcation on Neural Networks, Vol. 10, No. 5, Sept. 1999, pp. 988-999.


[44]. T. Joachims, Learning to Classify Text Using Support Vector Machines. Kluwer academic Publishers, Feb. 2001.

[45]. B. E. Boser, I. M. Guyon, and V. N. Vapnik, “A training algorithm for optimal margin classifiers,” in Proceedings of the Fifth Annual Workshop on Computational Learning Theory, Pittsburgh, Pennsylvania, U.S.A., 1992, pp. 144-152.

[46]. J. W. Cooley and J. W. Tukey, “An algorithm for the machine calculation of complex Fourier series,” Mathematics Computation, Vol. 19, April 1965, pp. 297-301.