簡易檢索 / 詳目顯示

回結果列表
研究生： 林雅婷
Lin, Ya-Ting
論文名稱： 內涵式音樂檢索中以瀏覽樣式為基礎之關聯性回饋技術
A Novel Navigation-Pattern-Based Relevance Feedback Technique for Content-Based Music Retrieval
指導教授： 曾新穆
Tseng, Vincent Shin-Mu
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年： 2011
畢業學年度： 99
語文別： 英文
論文頁數： 51
中文關鍵詞： 音樂內容檢索 、樣式關聯性回饋 、移動查詢點 、擴充查詢 、瀏覽樣式探勘
外文關鍵詞： content-based music retrieval, relevance feedback, query point movement, query expansion, navigation pattern mining
相關次數： 點閱：106  下載：2 
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

    • 傳統上，使用者藉由比對音樂內涵式相似度，檢索其偏好音樂，一般稱之為「內涵式音樂檢索」(Content-Based Music Retrieval，CBMR)。然而，現今內涵式音樂檢索方法中，使用者很難於一次檢索中得到較佳的音樂清單。因此，我們提出「內涵式音樂檢索中以瀏覽樣式為基礎之關聯性回饋技術」(Navigation-Pattern-based Relevance Feedback for Music retrieval，NPRFM)，來提高音樂檢索的效能和效率。針對效率而言，藉由探勘使用者記錄產生的瀏覽樣式來降低冗長的回饋次數；針對效能而言，結合了兩種關聯式回饋方法，分別為「移動查詢點」 (Query Point Movement，QPM)和「擴充查詢」 (Query EXpansion，QEX)，來收斂搜尋的空間並且往使用者感興趣的區域移動。因此，透過整合Navigation Patterns、QPM和QEX，我們的方法可以在比較少次的回饋次數中準確預測出使用者偏好的音樂。實驗結果證實我們的方法在準確率和效率上，優於既有的內涵式音樂檢索方法。

    Traditionally, people retrieve preferred music based on the similarities of music contents, namely Content-Based Music Retrieval (CBMR). A number of studies on content-based music retrieval have been presented over the past few years. However, it is not easy for the user to make a high precise search within a query session. This motivates us to develop a technique called NPRFM (Navigation-Pattern-based Relevance Feedback technique for Music retrieval), to achieve the high efficiency and effectiveness of CBMR. In terms of efficiency, the iterations of feedbacks are reduced substantially by using the navigation patterns discovered from the user query log. In terms of effectiveness, our proposed search algorithm NPRFM makes use of the discovered navigation patterns and two kinds of query refinement techniques, namely QPM (Query Point Movement) and QEX (Query EXpansion), to converge the search space towards the user’s intention effectively. The experimental results reveal that NPRFM outperforms other existing methods significantly in terms of precision and number of feedbacks.

    ABSTRACT I 摘要 III 誌謝 IV CONTENTS V List of Tables VIII List of Figures IX Chapter　1　Introduction 1 1.1　Background 1 1.2　Motivation 3 1.3　Overview of Proposed Method 4 1.4　Contributions 5 1.5　Thesis Organization 6 Chapter　2　Related Work 7 2.1　The Low Level Features of Music 7 2.2　Music Information Retrieval System 7 2.3　Relevance Feedback Technique 8 2.3.1　Query Point Movement 9 2.3.2　Query Re-weighting 10 2.3.3　Query Expansion 11 Chapter　3　Proposed Approach 12 3.1　Overview of Music Navigation-Pattern-Based Relevance Feedback 12 3.2　Offline Stage 14 3.2.1　Music DB Pre-processing Phase 15 3.2.1.1　Music Features Extraction 16 3.2.1.2　Feature Symbolization 16 3.2.2　Knowledge Discovery Phase 19 3.2.2.1　Data Transformation 19 3.2.2.2　Navigation Patterns Mining 21 3.2.2.3　Pattern Indexing 22 3.3　Online Stage 23 3.3.1　Initial Query Phase 23 3.3.2　Relevance Feedback Search Phase 25 Chapter　4　Experimental Evaluation 30 4.1　Experimental Settings 30 4.1.1　Experimental Data 30 4.1.2　Experimental Design 31 4.1.3　Experimental Measurement 32 4.2　Experimental Results 33 4.2.1　Objective Evaluations 33 4.2.1.1　Impact of Relevant Query Points (s) Setting 33 4.2.1.2　Impact of Cluster Number (cl) Setting 34 4.2.1.3　The Comparisons of Precisions between NPRFM and Other Approaches 35 4.2.1.4　The Precisions of Different Music Genres 37 4.2.2　Subjective User Study 39 4.2.2.1　The Comparisons of Precisions between NPRFM and PBRF 40 4.3　Experimental Discussions 41 Chapter　5　Conclusions and Future Work 42 5.1　Conclusions 42 5.2　Future Work 44 References 45 VITA 51

    [1] J. J. Aucouturier and F. Pachet, "Music similarity measures: What's the use?," in Proceedings of the third International Conference on Music Information Retrieval, Paris, France, pp. 157-163, 2002.
    [2] J. J. Aucouturier and F. Pachet, "Improving timbre similarity: How high is the sky?," Negative Results Speech Audio Sciences, vol. 1, 2004.
    [3] J. J. Aucouturier, F. Pachet, and M. Sandler, ""The way it Sounds": timbre models for analysis and retrieval of music signals," IEEE Transactions on Multimedia, vol. 7, pp. 1028-1035, 2005.
    [4] M. A. Bartsch and G. H. Wakefield, "Audio thumbnailing of popular music using chroma-based representations," IEEE Transactions on Multimedia, vol. 7, pp. 96-104, 2005.
    [5] D. Byrd and T. Crawford, "Problems of music information retrieval in the real world," Information Processing and Management, vol. 38, pp. 249-272, 2002.
    [6] P. Cano, E. Batlle, T. Kalker, and J. Haitsma, "A review of audio fingerprinting," Journal of VLSI Signal Processing, vol. 41, pp. 271-284, 2005.
    [7] M. Casey and M. Slaney, "The importance of sequences in musical similarity," in Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, 2006.
    [8] M. Casey and M. Slaney, "Song intersection by approximate nearest neighbor search," in Proceedings of International Conference on Music Information Retrieval, Victoria, Canada, 2006.
    [9] M. A. Casey, R. Veltkamp, M. Goto, M. Leman, C. Rhodes, and M. Slaney, "Content-based music information retrieval: current directions and future challenges," in Proceedings of the IEEE, vol. 96, pp. 668-696, 2008.
    [10] K. Chakrabarti, K. Porkaew, and S. Mehrotra, "Efficient query refinement in multimedia databases," in Proceedings of 16th International Conference on Data Engineering, pp. 196-196, 2000.
    [11] G. Chen, T. J. Wang, and P. Herrera, "A novel music retrieval system with relevance feedback," in Proceedings of the 3rd International Conference on Innovative Computing Information and Control, pp. 158, 2008.
    [12] R. Cilibrasi, P. Vitanyi, and R. D. Wolf, "Algorithmic clustering of music based on string compression," Computer Music Journal, vol. 28, pp. 49-67, 2004.
    [13] J. S. Downie, "Music information retrieval," Annual Review of Information Science and Technology, 2003.
    [14] J. Foote, M. Cooper, and U. Nam, "Audio retrieval by rhythmic similarity," in Proceedings of Institute Research Coordination Acoustics Music, 2002.
    [15] H. Fujihara and M. Goto, "A music information retrieval system based on singing voice timbre," in Proceedings of International Conference on Music Information Retrieval, Vienna, Austria, 2007.
    [16] A. Ghias, J. Logan, D. Chamberlin, and B. C. Smith, "Query by humming: musical information retrieval in an audio database," in Proceedings of the third ACM international conference on Multimedia, San Francisco, California, United States, pp. 231-236, 1995.
    [17] E. Gomez, "Tonal description of polyphonic audio for music content processing," INFORMS Journal on Computing, vol. 18, pp. 294-304, 2006.
    [18] J. Haitsma and T. Kalker, "A highly robust audio fingerprinting system," in Proceedings of the International Symposium on Music Information Retrieval, Paris, France, 2002.
    [19] K. Hoashi, K. Matsumoto, and N. Inoue, "Personalization of user profiles for content-based music retrieval based on relevance feedback," in Proceedings of the eleventh ACM international conference on Multimedia, Berkeley, CA, USA, pp. 110-119, 2003.
    [20] K. Hoashi, H. Ishizaki, K. Matsumoto, and F. Sugaya., "Content-based music retrieval using query integration for users with diverse preferences," in Proceedings of International Conference on Music Information Retrieval, pp. 463-466, 2007.
    [21] L. Hofmann-Engl, "Rhythmic similarity: A theoretical and empirical approach," in Proceedings of International Conference on Music Perception Cognition, pp. 564-567, 2002.
    [22] H. Hoos, K. Renz, and M. Gorg, "GUIDO/MIR - an experimental musical information retrieval system based on guido music notation," in Proceedings of the International Symposium on Music Information Retrieval, pp. 41-50, 2001.
    [23] N. Hu and R. B. Dannenberg, "A comparison of melodic database retrieval techniques using sung queries," in Proceedings of the 2nd ACM/IEEE-CS joint conference on Digital libraries, Portland, Oregon, USA, pp. 301-307, 2002.
    [24] Y. Ishikawa, R. Subramanya, and C. Faloutsos, "MindReader: querying databases through multiple examples," in Proceedings of the 24rd International Conference on Very Large Data Bases, pp. 218-227, 1998.
    [25] J. S. R. Jang, H. R. Lee, and J. C. Chen, "Super MBox: an efficient/effective content-based music retrieval system," in Proceedings of the ninth ACM international conference on Multimedia, Ottawa, Canada, pp. 636-637, 2001.
    [26] N. Kosugi, Y. Nishihara, S. Kon'ya, M. Yamamuro, and K. Kushima, "Music retrieval by humming-using similarity retrieval over high dimensional feature vector space," in Proceedings of PACRIM'99, pp. 404-407, 1999.
    [27] N. Kosugi, Y. Nishihara, T. Sakata, M. Yamamuro, and K. Kushima, "A practical query-by-humming system for a large music database," in Proceedings of the eighth ACM international conference on Multimedia, Marina del Rey, California, United States, pp. 333-342, 2000.
    [28] L. Kyogu and M. Slaney, "Acoustic chord transcription and key extraction from audio using key-dependent HMMs trained on synthesized audio," IEEE Transactions on Audio, Speech, and Language Processing, vol. 16, pp. 291-301, 2008.
    [29] M. Levy and M. Sandler, "Signal-based music searching and browsing," in Proceedings of International Conference on Consumer Electronics, 2007.
    [30] C. C. Liu and C. S. Huang, "A singer identification technique for content-based classification of MP3 music objects," in Proceedings of the eleventh international conference on Information and knowledge management, McLean, Virginia, USA, pp. 438-445, 2002.
    [31] B. Logan and A. Salomon, "A music similarity function based on signal analysis," in Proceedings of IEEE International Conference on Multimedia and Expo, pp. 745-748, 2001.
    [32] M. Mueller, F. Kurth, and M. Clausen, "Audio matching via chroma-based statistical features," in Proceedings of 6th International Conference on Music Information Retrieval, London, UK, pp. 288-295, 2005.
    [33] K. Porkaew and K. Chakrabarti, "Query refinement for multimedia similarity retrieval in MARS," in Proceedings of the seventh ACM international conference on Multimedia, Orlando, Florida, United States, pp. 235-238, 1999.
    [34] S. Rho, E. Hwang, and M. Kim, "Music information retrieval using a GA-based relevance feedback," in Proceedings of the 2007 International Conference on Multimedia and Ubiquitous Engineering, pp. 739-744, 2007.
    [35] Y. Rui, T. S. Huang, and S. Mehrotra, "Content-based image retrieval with relevance feedback in MARS," in Proceedings of International Conference on Image Processing, vol. 2, pp. 815-818, 1997.
    [36] J. Saunders, "Real-time discrimination of broadcast speech/music," in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 2, pp. 993-996, 1996.
    [37] M. K. Shan, M. F. Chiang, and F.-F. Kuo, "Relevance feedback for category search in music retrieval based on semantic concept learning," Multimedia Tools and Applications, vol. 39, pp. 243-262, 2008.
    [38] A. Sheh and D. P. Ellis, "Chord segmentation and recognition using EM-trained hidden Markov models," in Proceedings of International Conference on Music Information Retrieval, Baltimore, Maryland 2003.
    [39] J. H. Su, T. S. Hung, C. J. Lee, C. L. Lu, W. L. Chang and Vincent S. Tseng, " Effective content-based music retrieval with pattern-based relevance feedback," in Proceedings of the 15th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems, Kaiserslautern, Germany, 2011.
    [40] J. H. Su, W. J. Huang, Vincent S. Tseng and Philip S. Yu, "Efficient relevance feedback for content-based image retrieval by mining user navigation pattern," in Proceedings of IEEE Transactions on Knowledge and Data Engineering, Volume 23 Issue 3, March 2011.
    [41] D. Tao, H. Liu, and X. Tang, "K-BOX: A query-by-singing based music retrieval system," in Proceedings of the 12th annual ACM international conference on Multimedia, New York, USA, 2004.
    [42] G. T. Toussaint, "A comparison of rhythmic similarity measures," in Proceedings of 5th International Conference on Music Information Retrieval, Barcelona, Spain, pp. 242-245, 2004.
    [43] R. Typke, F. Wiering, and R. Veltkamp, "A survey of music information retrieval systems," in Proceedings of the International Symposium on Music Information Retrieval, pp. 153-160, 2005.
    [44] M. Varewyck, J. Pauwels, and J. P. Martens, "A novel chroma representation of polyphonic music based on multiple pitch tracking techniques," in Proceeding of the 16th ACM international conference on Multimedia, Vancouver, British Columbia, Canada, pp. 667-670, 2008.
    [45] A. Volk, J. Garbers, P. V. Kranenburg, F. Wiering, R. C. Veltkamp, and L. P. Grijp, "Applying rhythmic similarity based on inner metric analysis to folksong research," in Proceedings of International Conference on Music Information Retrieval, Vienna, Austria, 2007.
    [46] X. Wu and M. Li, "A QBSH system based on a three-level melody representation," in Proceedings of International Conference on Music Information Retrieval, Vienna, Austria, 2007.
    [47] J. Yuhua, Y. Bian, L. Mingyu, and N. Xiamu, "MDCT-based perceptual hashing for compressed audio content identification," in Proceedings of IEEE 9th Workshop on Multimedia Signal Processing, pp. 381-384, 2007.

    下載圖示 校內：2014-09-06公開
    校外：2014-09-06公開
    QR CODE