(3.238.173.209) 您好!臺灣時間:2021/05/16 19:29
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:何奇峰
研究生(外文):Chyi-Feng Ho
論文名稱:樂器音色分類之特徵值分析評估
論文名稱(外文):Musical Instrument Identification with Salient Feature Extraction
指導教授:顧孟愷
學位類別:碩士
校院名稱:國立臺灣大學
系所名稱:資訊工程學研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2004
畢業學年度:92
語文別:英文
論文頁數:44
中文關鍵詞:DFTK-Nearest Neighbors特徵值樂器音色分類
外文關鍵詞:DFTfeature extractionK-Nearest Neighborsinstrument classification
相關次數:
  • 被引用被引用:4
  • 點閱點閱:265
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
音樂訊號處理在實務上有著許多的應用,這些應用包括了資料庫查詢系統、自動音樂訊號辨識以及可以作為音樂家的寫作工具。而特徵值在分析樂器訊號處理上又是一個很重要的部分,這些訊號包含了許多的資訊,而特徵值的計算在訊號處理上是獲得特定重要資訊的一個步驟。
在本篇論文裡我們實作了一個樂器音色分類的模型。我們介紹了許多音樂訊號上特徵值的特性以及計算的方法,當然也包含了在頻譜分析下的特徵值。我們使用K-Nearest Neighbors 演算法作為我們樂器分類的基礎,作為測試的音樂檔案包含了絃樂器以及管樂器,我們使用決策樹的方法找出利用最少的特徵值來分辨出各種的樂器種類,並且達到一個完美的準確率。


Music content analysis usually has many practical applications. For example, such applications include database retrieval systems, automatic music signal annotation, and musicians’ tools. In this thesis, we present a system for musical instrument classification. A wide set of features covering both spectral and temporal properties are investigated and their extraction algorithms are designed. We apply the K-Nearest Neighbors algorithm as the classification method. The instrument samples included string (bowed and struck), woodwind (single, double, and air reed). Using the complete feature for training, we achieve a perfect accuracy. We apply decision trees to select the best feature subset to improve the identification performance.

Abstract i
中文摘要 ii
Contents iii
List of Figures v
List of Tables vii
Chapter 1 Introduction 1
1.1 Background……………..………………………………………1
1.2 Motivation……………………………...……………………….2
1.3 Thesis Organization…………………....……………………….2
Chapter 2 Signals in Time and Frequency 4
2.1 Digital Signals and the Sampling Theorem…...………………...4
2.1.1 Pitch……………..…………...……………………………………….6
2.1.2 Loudness……………………...…………………………………….7
2.1.3 Timbre……...……………...………………………………………….8
2.2 Discrete Fourier Transform……………………………………..9
Chapter 3 Feature Extraction 14
3.1 Acoustic features for instrument identification.……………….14
3.2 Time Domain Analysis……...…………………………………17
3.2.1 Short-Time Energy Function…...………………………………….17
3.2.2 Average Zero-Crossing Rate (ZCR)……………………………….18
3.2.3 Amplitude Envelope……………………………………………….20
3.2.4 Attack Time………………………………………………………….21
3.3 Frequency Domain Analysis……...…………………………22
3.3.1 Spectral Centroid………………...………………………………….22
3.3.2 Spectral Smoothness………………..……………………………….23
Chapter 4 Implementation and Result 25
4.1 K-Nearest Neighbors Algorithm….……………………………26
4.2 Implementation…..……….……………………………………29
4.3 Experiment Results………….…………………………………30
4.3.1 Spectral Centroid………………...………………………………….31
4.3.2 Frame by Frame RMS……………..……………………………….33
4.3.3 Zero-Crossing Rate………….…...………………………………….35
4.3.4 Feature Selection…..……………..……………….……………….38
Chapter 5 Conclusion and Future Work 41
References 43


[1]Kaminskyj, I. & Materka, A. “Automatic source identification of monophonic musical instrument sounds”. Proceedings of the 1995 IEEE International Conference of Neural Networks, pp. 189-194, 1995.
[2]C. Roads, The Computer Music Tutorial, MIT Press, Cambridge, MA, 1996.
[3]F. Richard Moore, Elements of Computer Music, Prentice-Hall, Inc. 1990.
[4]S. Handel, Listening: An Introduction to the Perception of Auditory Events, MIT Press, Cambridge, MA, 1989.
[5]Charles Dodge and Thomas A. Jerse, Computer Music: Synthesis, Composition, and Performance, A Division of Macmillan, Inc. 1985.
[6]J. B. Allen, “Short Term Spectral Analysis, Synthesis, and Modification by Discrete Fourier Transform,” IEEE Trans. on Acoustic, Speech, and Signal Processing, Vol. 25(3), pp. 235-238.
[7]Martin, K. D. “Musical Instrument Identification: A Pattern Recognition Approach”. Presented at the 136th meeting of the Acoustical Society of America, 1998.
[8]Martin, K. D. “Sound-Source Recognition: A Theory and Computational Model”. Ph.D. thesis, Massachusetts Institute of Technology, Cambridge, MA, 1999.
[9]L. R. Rabiner and R. W. Schafer, Digital Processing of Speech Signals, Prentice-Hall, Englewood Cliffs, NJ, 1978.
[10]Alan V. Oppenheim and Ronald W. Schafer, Discrete-Time Signal Processing, Prentice-Hall, Inc. 1989.
[11]Beauchamp, J. W. (1981) Data reduction and resynthesis of connected solo passages using frequency, amplitude, and ‘brightness’ detection and the nonlinear synthesis technique, Proc. ICMC (pp. 316- 323).
[12]Beauchamp, J. W. (1982) Synthesis by spectral amplitude and “brightness” matching of analyzed musical instrument tones. J. Audio Eng. Soc., 30(6), 396-406.
[13]Brown, J. C. (1996) Frequency ratios of spectral components of musical sounds. J. Acoust. Soc. Am., 99(2), 1210-1218.
[14]Eronen, A.; Klapuri, A. Musical instrument recognition using cepstral coefficients and temporal features. IEEE International Conference on Acoustics, Speech, and Signal Processing, Vol. 2, pp. 63-71, 2000.
[15]Perfecto Herrera, Xavier Amatrian, Eloi Batlle, Xavier Serra
Towards instrument segmentation for music content description: a critical review of instrument classification techniques


QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top