臺灣博碩士論文加值系統

聽覺與視覺同為人類最重要的感官。計算式聽覺場景分析(Computation Auditory Scene Analysis, CASA)透過聽覺心理學中對於人耳特性與心理感知的關連性，定義了一個可能的方向，讓電腦聽覺更為貼近人類感知。本研究目的在於應用聽覺心理學之原則，以影像處理與圖型辨識技術，設計音訊增益、切割、描述等對應之處理，透過相似度計算方式實現智慧家庭之環境中的即時音訊分類。
本研究分為三部分，第一部分為音訊處理，將環境中的聲音轉換成電腦可處理與強化之訊號；第二部分透過CASA原則設計影像處理，以冀於影像上達成音訊處理之結果，並以影像特徵加以描述音訊事件；第三部分定義影像特徵之距離，以K個最近鄰點(K-Nearest Neighbor, KNN)技術針對智慧家庭環境常見之音訊事件，實現即時辨識與分類。實驗結果顯示本論文所提出的音訊分類方法有著不錯的效果，對八種家庭環境常見的聲音辨識正確率可達80-90%，而在雜訊或其他聲音干擾的情況下，辨識結果也維持在70%左右。

Human receive sounds such as language and music through audition. Therefore, audition and vision are viewed as the two most important aspects of human perception. Computational auditory scene analysis (CASA) defined a possible direction to close the gap between computerized audition and human perception using the correlation between features of ears and mental perception in psychology of hearing. In this research, we develop and integrate methods for real-time streaming audio classification based on the principles of psychology of hearing as well as techniques in pattern recognition.
There are three major parts in this research. The first is audio processing, translating sounds into information that can be enhanced by computers; the second part uses the principles of CASA to design a framework for audio signal description and event detection by means of computer vision and image processing techniques; the third part defines the distance of image feature vectors and uses K-Nearest Neighbor (KNN) classifier to accomplish audio recognition and classification in real-time. Experimental results show that the proposed approach is quite effective, achieving an overall recognition rate of 80-90% for 8 types of audio input. The performance degrades only slightly in the presence of noise and other interferences.

第一章 緒論 1
1.1 研究背景 2
1.2 研究目的 3
第二章 相關研究 4
第三章 研究方法 8
3.1 音訊處理 8
3.1.1 聽覺心理學 8
3.1.2 音訊輸入 9
3.1.3 短時傅利葉轉換 10
3.1.4 時間-頻率頻譜圖分析 12
3.1.5 音訊起始點 14
3.1.6 音訊區塊 15
3.2 影像分析 16
3.2.1 雙向濾波器 16
3.2.1.1 高斯濾波器 17
3.2.1.2 雙向濾波器 19
3.2.2 音訊起始點偵測 24
3.2.2.1 音訊起始點偵測實作 26
3.2.2.2 音訊起始點偵測結果 28
3.2.3 閾值設定 30
3.2.3.1 基本全域閾值設定 31
3.2.3.2 雙閾值設定 34
3.2.4 區塊偵測 35
3.2.4.1 鍊碼 36
3.2.5 區域二元化圖型 38
3.2.5.1 Uniform Pattern 40
3.3 相似度搜尋 42
3.3.1 K個最近鄰點分類器 43
3.3.2 距離定義 44
第四章 實作與實驗結果 45
4.1 系統實作 45
4.2 音訊分類 46
4.2.1 分類結果 47
4.2.2 情境環境聲 51
4.2.3 音訊事件同時發生 56
4.2.4 音訊事件發生於不同音場位置 59
4.3 即時性驗證 62
第五章 結論與後續研究方向 65
參考文獻 67
附錄A 音訊起始點偵測-音訊事件發生於環境聲中 70
附錄B 基本全域閾值設定之實驗結果 76
附錄C 雙閾值設定之實驗結果 81
附錄D 音訊事件與音訊區塊用於Uniform Pattern實驗之樣本 84

[1] A. S. Bregman. “Auditory Scene Analysis”. The Perceptual Organization of Sound. Cambridge, MA: MIT Press, 1990.
[2] D. Rosenthal and H. Okuno, Eds.. “Computational Auditory Scene Analysis”. Lawrence Erlbaum Associates, 1998.
[3] D. Ellis. “Prediction-Driven Computational Auditory Scene Analysis”. Ph.D. thesis, MIT, 1996.
[4] 王小川，「語音訊號處理」，全華股份有限公司，2007年4月。
[5] 張智星，「音訊處理與辨識」，http://neural.cs.nthu.edu.tw/jang/books/audioSignalProcessing/ [retrieved July 2009]
[6] Wen-Hung Liao and Yi-Syuan Su. “Analysis and classification of human sounds”. Master’s thesis, Department of Computer Science National Chengchi University, July 2006.
[7] Yan Ke, Derek Hoiem and Rahul Sukthankar. “Computer Vision For Music Identification”. IEEE Conference on Computer Vision and Pattern Recognition, 2005.
[8] J. Haitsma and T. Kalker. “A Highly Robust Audio Fingerprinting System”. in Proceedings of International Conference on Music Information Retrieval, 2002.
[9] G. Hu and D.L. Wang. “Auditory Segmentation Based on Event Detection”. In ISCA Tutorial and Research Workshop on Stat. and Percept. Audio Process., 2004.
[10] S.H. Srinivasan. “Auditory blobs”. in IEEE ICASSP '04, vol. 4, pp. iv–313 – iv–316, 2004.
[11] Valerie Pierson and Nadine Martin. “Comparison of Shape Descriptors For Feature Extraction of A Time- Frequency Image”. CEPHAG-ENSJEG - BP 46 - 38402 ST-MARTIN-D’HERES C&Ex FRANCE.
[12] Ruohua Zhou, Marco Mattavelli, and Giorgio Zoia. “Music Onset Detection Based On Resonator Time Frequency Image”. IEEE Transactions On Audio, Speech, And Language Processing, Vol. 16, No. 8, 2008.
[13] 王駿發，｢多媒體影音檢索系統｣，http://web1.nsc.gov.tw/ct.aspx?xItem=8460&ctNode=40&mp=1[retrieved July 2009]
[14] D. Li, I. Sethi, N. Dimitrova, and T. McGee. “Classification Of General Audio Data For Content-Based Retrieval”. Pattern Recognition Letters, vol. 22(5), pp. 533–544, 2001.
[15] Zhu Liu, Yao Wang and Tsuhan Chen. “Audio Feature Extraction And Analysis For Scene Segmentation And Classification”. Polytechnic University, Brooklyn, NY 11201, Carnegie Mellon University, Pittsburgh, PA 15213.
[16] Silvia Allegro, Michael Büchler and Stefan Launer. “Automatic Sound Classification Inspired By Auditory Scene Analysis”. Signal Processing Department, Phonak AG, Switzerland Department of Otorhinolaryngology, University Hospital Zurich, Switzerland.
[17] T. Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution Gray-Scale And Rotation Invariant Texture Classification With Local Binary Patterns”. IEEE Trans. On Pattern Analysis and Machine Intelligence, vol. 24, pp. 971-987, 2002.
[18] L. Cohen. “Time-Frequency Analysis”. Prentice Hall PTR, Englewood Cliffs 1995.
[19] J. Bello, L. Daudet, S. Abdallah, C. Duxbury, M. Davies and M. Sandler. “A Tutorial On Onset Detection In Music Signals”. IEEE Transactions on Speech and Audio Processing, 2005.
[20] S. Paris. “A Gentle Introduction To Bilateral Filtering And Its Applications”. In ACM SIGGRAPH 2007 courses, Course 13.
[21] V. Aurich and J.Weule. “Non-Linear Gaussian Filters Performing Edge Preserving Diffusion”. in Proceedings of the DAGM Symposium, pp. 538–545, 1995.
[22] C. Tomasi and R. Manduchi. “Bilateral Filtering For Gray And Color Images”. in Proceedings of the IEEE International Conference on Computer Vision, pp. 839–846, 1998.
[23] F. Durand and J. Dorsey. “Fast Bilateral Filtering For The Display Of Highdynamic-Range Images”. in Proceedings of the ACM SIGGRAPH conference, 2002.
[24] Paul Masri and Andrew Bateman. “Improved Modeling Of Attack Transients In Music Analysis-Resynthesis”. in Proceeding of International Computer Music Conference, 1996.
[25] M. Goto and Y. Muraoka. “Beat Tracking Based On Multiple-Agent Architecture — A Real-Time Beat Tracking System For Audio Signals —” in ICMAS-96, pp. 103–110, 1996.
[26] H. Freeman, “Techniques For The Digital Computer Analysis Of Chain-Encoded Arbitrary Plane Curves”. in: Proc. Nat. Electronics Conf., 1961, pp. 421-432.
[27] E. Bruce Goldstein. Sensation and Perception. Wadsworth Publishing Co., Belmont, California, 1980.
[28] Y. He and A. Kundu. “2-D Shape Classification Using Hidden Markov Model”. IEEE Trans. Pat-tern Analysis and Machine Intelligence, 13(1991) 1172-1184.
[29] Xu Qing, Yang Jie and Ding Siyi. “Texture Segmentation Using LBP Embedded Region Competition”. Inst. of Image Processing & Pattern Recognition.