研究生: |
陳泰丞 Tai-cheng chen |
---|---|
論文名稱: |
基於旋律片段分群之曲風分類方法 Music Genre Classification Base On Clustered Melody Patterns |
指導教授: |
林伯慎
Bor-shen Lin |
口試委員: |
古鴻炎
Hong-yen Gu 楊傳凱 Chuan-kai Yang |
學位類別: |
碩士 Master |
系所名稱: |
管理學院 - 資訊管理系 Department of Information Management |
論文出版年: | 2012 |
畢業學年度: | 100 |
語文別: | 中文 |
論文頁數: | 46 |
中文關鍵詞: | 音樂曲風分類 、N-gram 、條件式平滑化 、階層式分群 |
外文關鍵詞: | conditional smoothing, N-gram, Musical genre classification, hierarchical cluster |
相關次數: | 點閱:244 下載:3 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
本論文提出使用音樂旋律特徵進行自動風格分類的方法。我們比較了三種統計分類方法:以關聯度為基礎的方法、類神經網路、k個最近相似度方法。在基礎實驗中以類神經網路67.5%的正確率最高,而本論文的關聯度分類方法正確率則達到66.2%。
接著我們將旋律片段分群對關聯度為基礎的方法進行改進。在資料稀疏時,藉由群聚內的旋律片段達到機率共享的好處,可以將正確率提升到 70.0%。因此,進一步我們提出條件式平滑化方法,希望能依照訓練資料的充足與否做為判斷是否相信群聚關聯度統計值的準則。實驗結果發現,當在旋律片段出現次數排名前20%者(統計資料充足),可以把正確率在提升到70.67%。也就是說,條件式平滑化是有助於正確率提升。
This paper proposes a scheme of using melodic patterns to classify the musical genres. Three types of statistical classification approaches are compared, correlation-based classifier, artificial neural network(ANN), K-nearest neighbor classifier. In the baseline experiment, ANN can achieve the highest accuracy of 67.5%, while the correlation-based classifier proposed in this paper the accuracy of 66.2%.
The correlation-based classifier were there improved by smoothing the statistical of correlations based on clustered melodic patterns. The accuracy of 70.0% can be achieved for correlation-based classifier after applying the smoothing approach. Finally, a scheme of conditional smoothing by considering the amount of training data can be further used to improve the accuracy up to 70.67%.
[1] PadamaIyer: Music Information Retrieval, Vishvabharti Publications, New Delhi, (2004).
[2] Michael A. Casey, RemcoValtkamp, MasatakaGoto, Marc Leman, Christophe Rhodes, and Malcolm Slaney:“Content-Based Music Information Retrieval: Current Directions and Future Challenges”,Proceedings of the IEEE, Vol. 96, No. 4, pp. 668–696, (2008).
[3] 梁敬偉,「基於不同音樂特徵的音樂檢索方法的效果及效率比較」,碩士論文,國立政治大學,台北(2006)。
[4] Hewijin Christine Jiau and Chuan-Wang Chang:“A Dual Ternary Indexing Approach for Music Retrieval System”, Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.12, No.3, pp. 227-233, (2008).
[5] JueHou, et al:“Effectiveness of N-Gram fast Match for Query-by-Humming System”, IEEE International Conference on Multimedia and Expo(ICME 2009), pp. 1310-1313.
[6] Aurora Marsye and MirnaAdriani, “Searching Polyphonic Indonesian Folksongs Based on N-gram Indexing Technique”, The Fifth Asia Information Retrieval Symposium (AIRS 2009), LNCS Series, pp. 387-396, (2009).
[7] Alexandra Uitdenbogerd and Justin Zobel. “Melodic Matching Techniques for Large Music Databases”,In:Proceedings of the ACM Multimedia Conference, (1999).
[8] S. Doraisamy, “Polyphonic Music Retrieval: The N-GramApproach”, PhD Thesis, Imperial College London, (2004).
[9] Alexandra Uitdenbogerd and Justin Zobel.“Manipulation of Music for Melody Matching”,In: ProceedingACM International Multimedia Conferences, pp. 235-240. ACM Press, Bristol, (1998).
[10] A. Ghias, J. Logan, D. Chamberlin and B. C. Smith,“Query by humming: Musicalinformation retrieval in an audio database” In Proc ACM Int'l Conf. on Multimedia, ACM,pp. 231-236, (1995).
[11] J.L. Hsu, C.C. Liu, and A.L.P. Chen: “Discovering Non-trivial Repeating Patterns in Music Data”, IEEE Transactions on Multimedia, (2001).
[12] Tom Collins, Jeremy Thurlow, Robin Laney, Alistair Willis, and Paul H. Garthwaite: “A Comparative Evaluation of Algorithms for Discovering Translational Patterns In Baroque Keyboard Works”, Proceedings of International Society for Music Information Retrieval Conference, pp. 3-8, (2010).
[13] J.L. Hsu, A.L.P. Chen, and H.C. Chen: “Finding Approximate Repeating Patterns from Sequence Data”, In Proceedings of International Symposium on Music Information Retrieval, (2004).
[14] Suyoto, I.S., Uitdenbogerd, A.L.: “Effectiveness of Note Duration Information for MusicRetrieval”, Proceeding Tenth International Conference on Database Systems for AdvancedApplication, pp. 265-275. Springer, Beijing, (2005).
[15] Uitdenbogerd, A.L.; Zobel, Justin:“Musicranking techniques evaluated.”, Twenty-Fifth Australasian Computer Science Conference, (2002).
[16] D. Meredith, K. Lemstrom, and G.A. Wiggins, "Algorithms for discovering repeated patterns in multidimensional representations of polyphonic music",Journal of New Music Research, vol. 31, no. 4, pp. 321-345, (2002).
[17] Yu-lung Lo, Ho-cheng Yu, and Mei-chin Fan, "FastPET: A FastNon-trivial Repeating Pattern Extracting Technique for Music Data," 2001National Computer Symposium, Taipei, pp. 43-52, (2001).
[18]羅有隆、游合成,「以線性記憶體空間發現音樂資料中非不重要重覆片段之技術」,2002 年第六屆資訊管理學術暨警政資訊實務研討會,中央警察大學,桃園,pp. 341-350(2002)。
[19] ShyamalaDoraisamy and Stefan Rüger, "Robust Polyphonic Music Retrieval with N-grams," Journal of Intelligent Information Systems, vol. 21, no. 1, pp. 53-70, (2003).
[20] C. C.Liu, A. J.L. Hsu, and A. L. P. Chen, “1-D List: An Approximate StringMatching Algorithm for Content-Based Music Data Retrieval,” IEEE Int. Conf. on Multimedia Computing and Systems, vol.1,pp.451-456, (1999).
[21] T. C.Chou, A. L. P. Chen, and C. C. Liu, “Music Databases: IndexingTechniques and Implementation,” International Workshop on Multimedia DataBase Management Systems, (1996).
[22] Ian Knopke and FraukeJurgensen: “A System for Identifying Common Melodic Phrases in the Masses of Palestrina”, Journal of New Music Research, Vol. 38,
No. 2, pp. 171-181, (2009).
[23] H. Sakoe and S. Chiba, "Dynamic programming algorithm optimization for spoken word recognition",IEEE Transactions on Acoustics, Speech, and Signal Processing,vol. ASSP-26,no. 1,pp.43-49, (1978).
[24] Gerard Salton, Christopher Buckley, “Term-weighting approaches in automatic text retrieval”,Information Processing and Management: an International Journal, vol.24 no.5, pp.513-523, (1988).
[25]Yi Hong, Sam Kwong, Hanli Wang, QingshengRen“Resampling-based selective clustering ensembles”, Pattern Recognition Letters 30 (2009) 298–305.
[26] Grimalidi,M.,A. Kokaram, and P. Cunningham.2003.Classifying music by genre using a discrete wavelet transform and a round-robin ensemble. Work report. Trinity College, University of Dublin, Ireland.
[27] Koshina, K. 2002. Music genre recognition.Diplomathesis.Technical College of Hagenberg, Austria.
[28] Tzanetakis, G., and P. Cook. 2002. Musical genre classification of audio signals. IEEE Transactions on Speech and Audio Processing 10 (5).293-302.
[29] Whitman, B., and P. Smaragdis. 2002. Combining Musical and Cultural Features for Intelligent Style Detection. Proceedings of the International Symposium on Music Information Retrieval.47-52.
[30] Jang, J.-S. Roger and Gao, Ming-Yang, “A Query-by-Singing System based onDynamicProgramming”, International Workshop on Intelligent Systems Resolutions (the 8th BellmanContinuum), Hsinchu, Taiwan, pp. 85-89, (2000).
[31] Chuang, S.-L. and L.-F. Chien (2002). Towards automatic generation of query taxonomy: a hierarchical query clustering approach
[32] FarbrizioS,”Machine Learning in AutomatedText Categorization,”ACM Computing Surveys,Vol.34, NO.1, March 2002,pp.1-47.
[33]蘇木春、張孝德,機械學習:類神經網路、模糊系統以及基因演算法則,全華科技圖書股份有限公司,1999。