臺灣博碩士論文加值系統

在居家的生活環境中有許多不同類型的聲音，透過人類的聽覺能辨識出聲音
的獨特性，進一步判斷周遭環境的狀況。將聲音辨識技術應用於居家環境的異常
聲響監控系統上，可以大大提升日常生活的安全性。
本研究提出一個應用於居家環境中的異常聲音辨識系統，我們將所收集到的
異常聲響，包含尖叫聲、嬰兒哭聲、咳嗽聲、玻璃破碎聲、笑聲和門鈴聲音等六
種，從中擷取出時間域及頻率域的多個特徵來做分析，接著利用循序前進浮動搜
尋演算法（Sequential Floating Forward Selection, SFFS）來選取較有鑑別度的數個
特徵來訓練各種異常聲音的支援向量機（Support Vector Machine, SVM）。實驗結果
顯示，此居家環境中的異常聲音辨識系統，能夠有效的辨識各類異常聲響，達到
監控居家安全的效果。

In our living environment, there are various types of sounds. According to the
uniqueness of sounds, people can further comprehend the surrounding by the sense of
hearing. Nowadays, voice recognition had been widely applied in various applications.
In this thesis, we proposed an abnormal sound recognition system for monitoring indoor
sounds. Twenty-four features are extracted from each sound frame. The sequential
floating forward selection (SFFS) is then adopted to pick out high discriminative
features. The support vector machine (SVM) is finally used to classify the sounds into
six categories (screaming, baby-cry, cough, glass breaking, laughing and doorbell).
From the experiment results, the proposed system can effectively recognize
different kinds of abnormal sounds with high recognition rate so as to provide the safety
of daily life.

中文摘要 i
ABSTRACT ii
誌謝 iii
目錄 v
表目錄 vii
圖目錄 viii
第1章 緒論 1
1.1 研究動機 1
1.2 文獻探討 2
1.3 研究方法 5
1.4 章節大綱 7
第2章 相關理論 8
2.1 聲音介紹 8
2.1.1 強度（Intensity） 9
2.1.2 音質（Timbre） 10
2.2 快速傅立葉轉換 12
2.3 線性預測倒頻譜係數 16
2.4 梅爾倒頻譜係數 19
2.5 主成份分析 21
2.6 循序前進浮動搜尋演算法 24
2.7 支援向量機 27
第3章 研究方法 35
3.1 系統架構 35
3.2 前處理 36
3.2.1 正規化 38
3.2.2 音框化 39
3.2.3 預強調 40
3.2.1 漢明視窗 41
3.3 快速傅立葉轉換 42
3.4 特徵擷取 44
3.5 特徵選取 49
3.6 訓練階段 49
3.7 測試階段 50
3.8 異常聲音分類 50
第4章 實驗結果與討論 51
4.1 實驗環境與設計 51
4.2 實驗資料庫 53
4.3 未使用特徵選取的系統辨識率 54
4.4 使用特徵選取後的系統辨識率 57
4.5 效能評估與比較結果 59
4.6 執行時間效能評估與比較結果 63
第5章 結論 64
參考文獻 65

[1] G. Tzanetakis and P. Cook, "Musical genre classification of audio signals," IEEE Transactions on Speech and Audio Processing, vol. 10, no. 5, pp. 293-302, 2002.
[2] X. Changsheng, N. C. Maddage, and S. Xi, "Automatic music classification and summarization," IEEE Transactions on Speech and Audio Processing, vol. 13, no. 3, pp. 441-450, 2005.
[3] C. H. Lee, J. L. Shih, K. M. Yu, and H. S. Lin, "Automatic music genre classification based on modulation spectral analysis of spectral and cepstral Features," IEEE Transactions on Multimedia, vol. 11, no. 4, pp. 670-682, 2009.
[4] P. Dhanalakshmi, S. Palanivel, and V. Ramalingam, "Classification of audio signals using SVM and RBFNN," Expert Systems with Applications, vol. 36, no. 3, pp. 6069-6075, 2009.
[5] D. C. Park, "Classification of audio signals using Fuzzy c-Means with divergence-based Kernel," Pattern Recognition Letters, vol. 30, no. 9, pp. 794-798, 2009.
[6] L. Lie, D. Liu, and H. J. Zhang, "Automatic mood detection and tracking of music audio signals," IEEE Transactions on Audio, Speech, and Language Processing, vol. 14, no. 1, pp. 5-18, 2006.
[7] J. C. Wang, J. F. Wang, C. B. Lin, K. T. Jian, and W. H. Kuok, "Content-based audio classification using support vector machines and independent component analysis," Proceeding of the 18th International Conference on Pattern Recognition, pp. 167-160, 2006
[8] B. Shao, M. Ogihara, D. Wang, and T. Li, "Music Recommendation Based on Acoustic Features and User Access Patterns," IEEE Transactions on Audio, Speech, and Language Processing, vol. 17, pp. 1602-1611, 2009
[9] X. Zhu, Y. Y. Shi, H. G. Kim, and K. W. Eom, "An integrated music recommendation system," IEEE Transactions on Consumer Electronics, vol. 52, pp. 917-925, 2006
[10] Z. Ma and A. Leijon, "A probailistic principal component analysis based hidden markov model for audio-visual speech recognition,"Proceeding of the 42nd Asilomar Conference on Signals, Systems and Computers, pp. 2170-217, 2008.
[11] M. Briand, D. Virette, and N. Martin, "Parmetric coding of stereo audio based on princial component analysis," Proceeding of the 9th Int. Conference on Digital Audio Effects, 2006.
[12] J. J. Wells and G. Aldam, "Principal component analysis of rasterised audio for cross synthesis," Proceeding of the 12th International Conference on Digital Audio Effects, 2009.
[13] D. Huron, "The Ramp Archetype and the Maintenance of Passive Auditory Attention," Music Perception, vol. 10, pp. 83-91, 1992.
[14] J. S. R. Jang. Audio Signal Processing and Recognition, Available: http://www.cs.nthu.edu.tw/~jang.
[15] S. Z. Li, "Content-based audio classification and retrieval using the nearest feature line method," IEEE Transactions on Speech and Audio Processing, vol. 8, no. 5, pp. 619-625, 2000.
[16] M. Liu and C. Wan, "A study on content-based classification and retrieval of audio database," International Symposium on Database Engineering and Applications, pp. 339-345, 2001.
[17] J. F. Wang, J. C. Wang, T. H. Huang, and C. S. Hsu, "Home environmental sound recognition based on MPEG-7 features," , IEEE 46th Midwest Symposium on Circuits and Systems, vol. 2, pp. 682-685, 2003.
[18] G. Velius, "Variants of cepstrum based speaker identity verification," Proceeding of the International Conference on Acoustics, Speech, and Signal Processing, pp. 583-586, 1988.
[19] R. J. Mammone, Z. Xiaoyu, and R. P. Ramachandran, "Robust speaker recognition: a feature-based approach," IEEE Signal Processing Magazine, vol. 13, no. 5, pp. 58-71, 1996.
[20] J. C. Wang, J. F. Wang, and Y. S. Wang, "Chip design of mel frequency cepstral coefficients for speech recognition," IEEE International Conference on Acoustics, Speech, and Signal Processing , vol. 6, pp. 3658-3661, 2000.
[21] E. Wong and S. Sridharan, "Comparison of linear prediction cepstrum coefficients and mel-frequency cepstrum coefficients for language identification," Proceeding of 2001 International Symposium on Intelligent Multimedia, Video and Speech Processing, pp. 95-98, 2001.
[22] J. C. Wang, C. H. Lin, W. K. Liao, and W. J. Liao, "A new speech-based emotion identification approach for a modern technology education system," Proceeding of the 3rd WIETE Annual Conference on Engineering and Technology Education Pattaya, 2012.
[23] J. J. P. Campbell, "Speaker recognition: a tutorial," Proceeding of the IEEE, vol. 85, no. 9, pp. 1437-1462, 1997.
[24] N. R. French and J. C. Steinberg, "Factors governing the intelligibility of speech sounds," The Journal of the Acoustical Society of America, vol. 17, no. 1, pp. 90-119, 1947.
[25] P. Pudil, J. Novovicov&;aacute;, and J. Kittler, "Floating search methods in feature selection," Pattern Recognition Letters, vol. 15, no. 11, pp. 1119-1125, 1994.
[26] I. Guyon, S. Gunn, M. Nikravesh, and L. A. Zadeh, Feature Extraction: Foundations And Applications: Springer, 2006.
[27] C. Cortes and V. Vapnik, "Support-vector network," Machine Learning, vol. 20, pp. 273-297, 1995.
[28] C. C. Lin, "Support Vector Machine for Discovering Scientific Equations," National Yunlin University of Science and Technology, Master Thesis, 2003.
[29] C. Y. Chang and H. H. Chang, "Adaptive Color Space Switching Based Approach for Face Tracking," Lecture Notes in Computer Science, Vol. 4233, pp.244-252, 2006.
[30] C. C. Chang and C. J. Lin. LIBSVM: A library for support vector machines, 2001. Available: http://www.csie.ntu.edu.tw/~cjlin/libsvm.
[31] G. Guo and S. Z. Li, "Content-Based Audio Classification and Retrieval by Support Vector Machines," IEEE Transactions on Neural Networks, Vol. 14, No. 1,pp.209-215,2003.
[32] R. S. S. Kumari, D. Sugumar, and V. Sadasivam, "Audio Signal Classification Based on Optimal Wavelet and Support Vector Machine, " Proceeding of International Conference on Computational Intelligence and Multimedia Applications,Vol. 2, pp.544-548,2007.