Responsive image
博碩士論文 etd-0909112-110138 詳細資訊
Title page for etd-0909112-110138
論文名稱
Title
基於前進選擇之特徵選取之流行音樂曲風辨識與分析
Forward-Selection-Based Feature Selection for Genre Analysis and Recognition of Popular Music
系所名稱
Department
畢業學年期
Year, semester
語文別
Language
學位類別
Degree
頁數
Number of pages
62
研究生
Author
指導教授
Advisor
召集委員
Convenor
口試委員
Advisory Committee
口試日期
Date of Exam
2012-07-24
繳交日期
Date of Submission
2012-09-09
關鍵字
Keywords
RBF、支援向量機、前進選擇、特徵選擇、曲風辨識
RBF (radial basis function), SVM (support vector machine), forward selection, Genre recognition, feature selection
統計
Statistics
本論文已被瀏覽 5632 次,被下載 266
The thesis/dissertation has been browsed 5632 times, has been downloaded 266 times.
中文摘要
近年來由於流行音樂的數量以非常驚人的速度成長,為了方便人們尋找自己喜愛的音樂,各種不同的音樂查詢方式因應而生,如透過歌名、歌手、情緒、曲風等等來查詢便是很常見的方式。為了更方便且有效地整理這些大量的資料,各種自動分類的技術也日漸成熟,但在許多不同的辨識演算法中,不管是針對音樂情緒或是音樂曲風,使用到的特徵皆不同,也沒有任何人可以證明所使用的特徵一定是最佳且最有效的。在此篇論文中,針對日本流行歌曲提出了一個使用SVM並結合前進特徵選擇機制的曲風辨識系統。首先,先由輸入歌曲的數位訊號中擷取眾多常見之聽覺特徵,如子頻帶、能量、節奏、拍子、共振峰等等,再將這些特徵經由支援向量機訓練並結合前進選擇,藉由實驗與統計的方式來找出最適合的曲風辨識特徵以及分類器參數。實驗結果顯示,利用前進選擇挑選出來的特徵及分類器參數可使辨識準確率達到78.81%,且辨識歌曲數量增大的情況下辨識率仍可維持穩定。
Abstract
In this thesis, a popular music genre recognition approach for Japanese popular music using SVM (support vector machine) with forward feature selection is proposed. First, various common acoustic features are extracted from the digital signal of popular music songs, including sub-bands, energy, rhythm, tempo, formants. A set of the most appropriate features for the genre identification is then selected by the proposed forward feature selection technique. Experiments conducted on the database consisting of 296 Japanese popular music songs demonstrate that the accuracy of recognition the proposed algorithm can achieve approximately 78.81% and the accuracy is stable when the number of testing music songs is increased.
目次 Table of Contents
Contents
中文摘要 i
Abstract ii
Contents iii
List of Figures iv
List of Tables v
Chapter 1 Introduction 1
1.1 Overview of Popular Music 1
1.2 Motivation 3
1.3 Contribution 4
1.4 Organization 4
Chapter 2 Background Review 5
2.1 Music Genre Classification 6
2.2 Support Vector Machine 7
Chapter 3 Proposed Forward-Selection-Based Feature Selection 10
3.1 Feature Extraction 11
3.2 Forward-Selection-Based Feature Selection 24
Chapter 4 Experimental Results 30
4.1 Results of Forward-Selection 31
4.2 Testing and Verifying 46
4.3 Discussion 47
Chapter 5 Conclusions and Future Works 48
5.1 Conclusion 48
5.2 Future Work 49
Reference 50
參考文獻 References
[1] C. Xu, N.C. Maddage, S. Xi, C. Fang, and T. Qi, “Musical genre classification using support vector machines,” in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 5, pp. 429-432, 2003
[2] E. Scheirer and M. Slaney, “Construction and evaluation of a robust multifeature speech/music discriminator,” in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 2, pp. 1331-1334, April 1997.
[3] R. Vergin, D. O'Shaughnessy, and V. Gupta, “Compensated mel frequency cepstrum coefficients,” in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. 323-326, May 1996.
[4] C-H. Lee, J-L. Shih, K-M. Yu, and J-M Su, “Automatic music genre classification using modulation spectral contrast feature,” in Proceedings of IEEE International Conference on Multimedia and Expo, pp. 204-207, 2007
[5] K. West and S. J. Cox, “Features and classifiers for the automatic classification of musical audio signals,” in Proceedings of International Conference on Music Information Retrieval, pp. 10-15, October 2004.
[6] D. N. Jiang, L. Lu, H. J. Zhang, J. H. Tao, and L. H. Cai, “Music type classification by spectral contrast feature,” in Proceedings of IEEE International Conference on Multimedia and Expo, vol. 1, pp. 113-116, 2002.
[7] Y.M.G Costa, L.S. Oliveira, A.L. Koericb, and F. Gouyon, “Music genre recognition using spectrograms,” in Proceedings of International Conference on Systems, Signals and Image Processing, pp. 1-4, 2011
[8] S.T. Dumais, E. Osman, J. Platt and B. Scholkopf, “Support vector machines,” IEEE Transactions on Intelligent Systems and their Applications, vol. 13, pp. 18-28 ,1998
[9] S-H. Chen, S-H. Chen, and R.C. Guido, “Music genre classification algorithm based on dynamic frame analysis and support vector machine,” in Proceedings of IEEE International Symposium on Multimedia, pp. 357-361, 2010
[10] O. Lartillot, T. Eerola, P. Toiviainen, and J. Fornari, “Multi-feature modeling of pulse clarity: Design, validation, and optimization”, in Proceedings of International Conference on Music Information Retrieval, Philadelphia, 2008.
[11] 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, September 2002.
[12] G. Peeters, “A large set of audio features for sound description (similarity and classification) in the CUIDADO project,” CUIDADO I.S.T. Project Report, 2004
[13] P. J. Blamey, R. C. Dowell, G. M. Clark, and P. M. Seligman, “Acoustic parameters measured by a formant-estimating speech processor for a multiple-channel cochlear implant,” Journal of the Acoustical Society of America, vol. 82(1), pp. 38-47, July 1987.
電子全文 Fulltext
本電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
論文使用權限 Thesis access permission:自定論文開放時間 user define
開放時間 Available:
校內 Campus: 已公開 available
校外 Off-campus: 已公開 available


紙本論文 Printed copies
紙本論文的公開資訊在102學年度以後相對較為完整。如果需要查詢101學年度以前的紙本論文公開資訊,請聯繫圖資處紙本論文服務櫃台。如有不便之處敬請見諒。
開放時間 available 已公開 available

QR Code