臺灣博碩士論文加值系統

音樂節拍的自動分析工具目前已有相當普遍的應用，特別是對電腦音樂、伴唱系統、音樂理論與自動編曲的相關輔助。本論文旨在發展輔助工具來讓電腦能夠即時分析音樂的節奏。例如：我們可應用在電腦動畫與音樂同步的領域裡，來讓虛擬舞者的每個動作皆能符合節拍。但對於此應用範例，鼓點偵測一直是相當重要的環節，所以在節拍分析中本論文是針對鼓點偵測做相關的研究及實作。
本論文先將說明人感覺節奏的背景知識，以及相關的語音訊號處理技術來偵測節拍。而為了減少運算的時間，此演算法只需整數運算就能運作。我們並且會展示由電子舞曲和流行樂曲所偵測出的鼓點。最後，我們也將提出未來的研究方向。

Automatic rhythm analysis is a development tool that have more and more popular
in many applications, especially in computer music, accompaniment systems,
musicology and automatic music transcription. The main goal of this thesis is to implement a real-time analysis tool that can perceive the rhythm. For example, we can apply real-time computer graphics synchronized with music and displays virtual dancers whose motions and positions change in time to beats. Beat detection plays an important role on this application. This research focuses on the related studies and implementation of beat detection on rhythm analysis.
This thesis will introduce the background knowledge for human rhythm perception
and some related speech signal processing techniques that will be applied
to emulate rhythm perception. To decrease the operating time, our algorithm
has be implemented to need only the integer operation. We also demonstrate the
experimental results obtained in detecting the musical beats from audio signals
sampled form compact discs of technos and pop musics. Finally, we will address
our future works and give some directions on future researches.

Contents
1 Introduction 1
1.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Thesis Organization . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
2 Background 4
2.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2.2 Human Rhythm Perception . . . . . . . . . . . . . . . . . . . . . . 5
2.3 Understand Rhythm Perception From The Viewpoint of Psycho-
analysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2.4 Musical Rhythm Structure . . . . . . . . . . . . . . . . . . . . . . . 8
2.5 The Computer Models Of Rhythm Analysis . . . . . . . . . . . . . 9
2.6 Related Speech Signal Processing Techniques . . . . . . . . . . . . . 11
2.7 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
3 Implementation of Beat Detection 15
3.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
3.2 Decimation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
3.3 Beat Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
3.4 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
4 Experiments 24
4.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
4.2 Test Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
4.3 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
5 Conclusions and Future Works 29
5.1 Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
5.2 Future Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30

[1] S. Dixon, "Beat induction and rhythm recognition", Proceedings of the Australian
Joint Conference on Arti‾cial Intelligence, Perth, Australia, pp. 311-320, 1997.
[2] L. M. Smith, "A Multiresolution Time-Frequency Analysis and Interpretation of
Musical Rhythm", PhD thesis, Department of Computer Science, University of
Western Australia, 1999.
[3] I. Orife, "Riddim: A Rhythm Analysis and Decomposition Tool Based on Indepen-
dent Subspace Analysis", M.A. thesis, Dartmouth College, 2001.
[4] G. P. Nava and H. Tanaka, "Finding Music Beats and Tempo by Using an Image
Processing Technique", Proceedings of the 2nd International Conference on Infor-
mation Technology for Applications (ICITA 2004), 2004.
[5] H. Takeda, T. Nishimoto, and S. Sagayama, "Automatic Rhythm Transcription from
Multiphonic MIDI Signals", Graduate School of Information Science and Technol-
ogy, University of Tokyo Hongo, 2003.
[6] M. Escobar, "Beat Detection in Music Using Average Mutual Information", Music
Engineering Technology, University of Miami, 2001.
[7] M. M. Sondhi, "New Methods of Pitch Extraction", IEEE Trans. Audio Electroa-
coust. Special Issue on Speech Communication and Processing-Part II, AU-16:263-
266, 1968.
[8] M. J. Ross, H. L. Sha®er, A. Cohen, R. Freudberg and H. J. Manley, "Average
Magnitude Di®erence Function Pitch Extractor", IEEE Trans. on Acoustics, Speech
and Signal Processing, vol. 22, no. 5, pp. 353-362, 1974.
[9] M. Goto and Y. Muraoka, "An Audio-Based Real-Time Beat Tracking System and
Its Applications", Proceedings of the International Computer Music Conference,
Computer Music Association, 1998.
[10] Masataka Goto, "An Audio-based Real-time Beat Tracking System for Music With
or Without Drum-sounds", Journal of New Music Research, Vol.30, No.2, pp.159-
171, 2001.
[11] J. Foote and S. Uchihashi, "The Beat Spectrum: a New Approach To Rhythm
Analysis", Proceedings of IEEE ICME2001, pp. 1088-1091 2001.
[12] F. Gouyon, L. Fabig and, J. Bonada, "Rhythmic expressiveness transformations of
audio recordings: swing modi‾cations", Proceedings of 6th International Conference
on Digital Audio E®ects, 2003.
[13] http://www.gamedev.net/reference/programming/features/beatdetection/
[14] http://hyperphysics.phy-astr.gsu.edu/hbase/hframe.html