Loading...
|
Please use this identifier to cite or link to this item:
https://nccur.lib.nccu.edu.tw/handle/140.119/32650
|
| Title: | 根據概念學習發展以內容為主的音樂查詢之相關回饋機制
Relevance feedback for content-based music retrieval based on semantic concept learning |
| Authors: | 江孟芬
Chiang, Meng-Fen |
| Contributors: | 沈錳坤
Shan, Man-Kwan
江孟芬
Chiang, Meng-Fen |
| Keywords: | 資料探勘
音樂檢索
相關回饋
Data Mining
Music retrieval
Relevance Feedback |
| Date: | 2006 |
| Issue Date: | 2009-09-17 13:56:24 (UTC+8) |
| Abstract: | 傳統的音樂檢索系統主要在提供使用者特定音樂的查詢(target search)。除此之外，使用者也有類型音樂查詢(category search)的需求。在類型音樂查詢中，該類型的所有音都共同具備使用者所定義的概念(semantic concept)。這個由使用者定義的概念在音樂檢索系統上是主觀的且動態產生的。換句話說，同一使用者在不同情境之下對於同一首音樂可能產生不同的解讀概念。為了動態擷取使用者的概念，讓使用者參與在查詢過程的互動機制是必要的。因此， 我們提出將相關回饋(relevance feedback)的機制運用在以內容為主的音樂查詢系統上，讓系統從使用者的相關回饋中學習使用者的概念，並利用這學習出的概念來幫助音樂查詢。
由於使用者可能從整首音樂或音樂片段兩種角度來判斷該音樂是否具備使用者定義的概念。因此，本論文提出用以片段為主的音樂模型(segment-based modeling approach)將音樂表示成音樂片段的集合。進一步再從整首音樂和片段中擷取特徵。
其次，我們針對該問題提出相關演算法來探勘使用者的概念。該演算法先從相關和不相關的音樂資料庫中個別探勘常見樣式，再利用這些樣式建立分類器以區分音樂的相關性。
最後，我們分析各種系統回饋機制對搜尋效果的影響。Most-positive回傳機制會選擇根據目前系統判斷為最相關的物件。Most-informative機制則是回傳系統無法判斷其相關性的音樂物件。Most-informative 機制的目的在增加每回合系統從使用者身上得到的資訊量。Hybrid 則是中和前兩種機制的優點。本文中，我們模擬並比較各種回傳機制的效能。實驗結果顯示相關回饋機制確實能提升查詢的效果。
Traditional content-based music retrieval system retrieves a specific music object which is similar to the user’s query. There is also a need, category search, for retrieving a specific category of music objects. In category search, music objects of the same category share a common semantic concept which is defined by the user. The concept for category search in music retrieval is subjective and dynamic. Different users at different time may have different interpretations for the same music object. In the music retrieval system along with relevance feedback mechanism, users are expected to be involved in the concept learning process. Relevance feedback enables the system to learn user’s concept dynamically.
In this paper, the relevance feedback mechanism for category search of music retrieval based on the semantic concept learning is investigated. We proposed a segment-based music representation to assist the system in discovering user’s concept in terms of low-level music features. Each music object is modeled as a set of significant motivic patterns (SMP) achieved by discovering motivic repeating pattern. Both global and local music features are considered in concept learning.
Moreover, to discover user’s semantic concept, a two-phase frequent pattern mining algorithm is proposed to discover common properties from relevant and irrelevant objects respectively and based on which a classifier is derived for distinguishing music objects.
Except user’s feedback, three strategies of the system’s feedback to select objects for user’s relevance judgment are investigated. Most-positive strategy returns the most relevant music object to the user while most-informative strategy returns the most uncertain music objects for improving the discrimination power of the next round. Hybrid feedback strategy returns both of them. Comparative experiments are conducted to evaluate effectiveness of the proposed relevance feedback mechanism. Experimental results show that a better precision can be achieved via proposed relevance feedback mechanism. |
| Reference: | [1] Agrawal, R. and Srikant, R. Fast algorithms for mining association rules. In Proc. of Intl. Conference on Very Large databases (VLDB ‘94), (Chile, September 12-15, 1994).
[2] Amir, A. Berg, M. and Permuter. H. Mutual relevance feedback for multimodal query formulation in video retrieval. In Proc. of ACM SIGMM Intl. Workshop on Multimedia Information Retrieval (MIR ‘05) (Singapore, November 10-11, 2005).
[3] Chen, H. and Chen Arbee L.P. A music recommendation system based on music data grouping and user interests. In Proc. of the ACM CIKM Intl. Conference on Information and Knowledge Management (CIKM ‘01) (Atlanta, Georgia, USA, November 5-10, 2001). ACM press 2001, 231-238.
[4] Cox, I.J. Miller, M. Minka, T.P. Papathomas, T. and Yianilos P. The baysian image retrieval system, PicHunter: theory, implementation, and psychophysical experiments. IEEE Trans. Image Processing, 9, 1, (Jan. 2000), 20-37.
[5] Grimaldi, M. and Cunningham. P. Experimenting with music taste prediction by user profiling. In Proc. of ACM SIGMM Intl. Workshop on Multimedia Information Retrieval (MIR ‘04) (New York, NY, USA, October 15-16, 2004). ACM press 2004, 173-180.
[6] Haas, M. Lamel, L. Thomee, B. and Lew, M.S. Relevance feedback: perceptual learning and retrieval in bio-computing, photos, and video. In Proc. of the ACM SIGMM Intl. Workshop on Multimedia Information Retrieval (MIR ‘04) (New York, NY, USA, October 15-16, 2004). ACM press 2004, 151-156.
[7] Han, E.H. and Karpis, G. Feature-based Recommendation System. In Proc. of the ACM CIKM Intl. Conference on Information and Knowledge Management (CIKM ‘05) (Bremen, Germany, October 31-November 5, 2005). ACM press 2005, 446-452.
[8] He, X.F. King, W.Y. Ma, W.Y. Li, M.J. and Jiang, H.J. Learning a semantic space from user’s relevance feedback for image retrieval. IEEE Trans. Circuits and Systems and Video Technology, 13, 1 (Jan 2003), 39-48.
[9] Ho, M.C. Theme-Based Music Structural Analysis. Master Thesis, University of Chen Chi, Taipei, Taiwan, 2004.
[10] Hoi, C.H. and Lyu, M.R. A novel log-based relevance feedback technique in content-based image retrieval. In Proc. of the ACM Intl. Conference on Multimedia (MM ‘04) (New York, NY, USA, October 10-16, 2004). ACM press 2004, 24-31.
[11] Hoashi, K. Matsumoto, K. and Inoue, N. Personalization of user profiles for content-based music retrieval based on relevance feedback. In Proc. of the ACM Intl. Conference on Multimedia (MM ‘03) (Berkeley, CA, USA, November 2-8, 2003). ACM press 2003, 110-119.
[12] Hsu, J.L. Liu, C.C. and Chen, Arbee L.P. Discovering non-trivial repeating patterns in music data. In Proc. of Intl. Conference on Data Engineering (ICDE ‘99) (Sydney, Australia, March 23-36, 1999). IEEE Computer Society Press, 1999, 14-21.
[13] Jing, F. Li, M. Zhang, L. Zhang, H.J. and Zhang, B. Relevance feedback in region-based image retrieval. IEEE Trans. Circuits and Systems and Video Technology, 14, 5 (May 2004), 672-681.
[14] Jing, F. Li, M. Zhang, H.J. Zhang, B. An effective region-based image retrieval framework. In Proc. of the ACM Intl. Conference on Multimedia (MM ‘02) (Juan les Pins, France, December 1-6, 2002). ACM press 2002, 456-465.
[15] Kuo, F.F. and Shan, M.K. A personalized music filtering system based on melody style classification. In Proc. of the IEEE Intl. Conference on Data Mining (ICDM ‘02) (Maebashi, Japan, December 9-12, 2002). IEEE Computer Society Press 2002, 649-652.
[16] Liu, B. Hsu, W. and Ma, Y. Integrating Classification and Association Rule Mining. In Proc. of the Intl. Conference on Knowledge Discovery and Data Mining (KDD’98) (New York, USA, August 27-31, 1998). AAAI Press, 1998, 80-86.
[17] Liu, C.C. Hsu, J.L. and Chen, A.L.P. An approximating string matching algorithm for content-based music data retrieval. In Proc. of IEEE Intl. Conference on Multimedia Computing and Systems (ICMCS ‘99) (Florence, Italy, June 7-11, 1999). IEEE Computer Society, Press 1999, 451-456.
[18] Ortega-Binderberger, and M. Mehrotra, S. Relevance feedback techniques in the MARS image retrieval system. Multimedia System, 9, 6 (June. 2004)535-547.
[19] Ragno, R. Burges, C.J.C. and Herley, C. Inferring similarity between music objects with application to playlist generation. In Proc. of ACM SIGMM Intl. Workshop on Multimedia Information Retrieval (MIR ‘05) (Singapore, November 10-11, 2005).
[20] Rocchio, J.J. and G. Salton. Relevance feedback in information retrieval. Prentice Hall. Inc., Englewood Cliffs, New Jersey, 1971.
[21] Rui, Y. Huang, Thomas S. Ortega, M. and Mehrotra, S. Relevance feedback: a power tool for interactive content-based image retrieval. IEEE Trans. Circuits and Systems for Video Technology, 8, 5 (Sep. 1998), 644-655.
[22] Schohn, G. and Cohn, D. Less is more: active learning with support vector machines In Proc. of the Intl. Conference on Machine Learning (ICML ‘00) (Stanford, CA, USA, June 29-July 2, 2000). Morgan Kaufmann 2000, 839-846.
[23] Selfridge-Field. E. Conceptual and representational issues in melodic comparison. In Hewlett, W.B. & Selfridge-Field E. Melodic similarity: Concepts, procedures, and applications (Computing in Musicology: 11), The MIT Press.
[24] Shardanand, U. and Maes, P. Social information filtering: algorithms for automating “Word of Mouth” In Proc. of the Conference on Human Factors in Computing Systems (CHI ‘95) (Denver, Colorado, USA, May 7-11, 1995). ACM/Addison-Wesley Press 1995, 210-217.
[25] Shen, X. and Zhai, C. Active feedback in Ad Hoc information retrieval. In Proc. of ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR ‘05) (Salvador, Bahia, Brazil, August 15-19, 2005). ACM press 2005, 59-66.
[26] Stein, L. Structure & Style. Summy-Birchard, 1979.
[27] Tong, S. and Koller, D. Support vector machine active learning with applications to text classification. Journal of Machine Learning Research, 2 (Nov. 2001), 45-66.
[28] Tong, S. and Chang, E. Support vector machine active learning for image retrieval. In Proc. of ACM Intl. conference on Multimedia (MM ‘01) (Ottawa, Ontario, Canada, September 30- October 5, 2001). ACM press 2001, 107-118.
[29] Uitdenbgerd, A. and Zobel, J. Melodic matching techniques for large music databases. In Proc. of ACM Intl. conference on Multimedia (MM ‘99) (Orlando, Florida, USA, October 30-Novermber 5, 1999). ACM press 1999, 57-66.
[30] Wu, Y. and Zhang, A. Interactive pattern analysis for relevance feedback in multimedia information retrieval. Multimedia System, 10, 1 (June. 2004)41-55.
[31] Wu, Y. Tian, Q. and Huang, T.S. Discriminant-EM algorithm with application to image retrieval. In Proc. of IEEE Intl. Conference on Computer Vision and Pattern Recognition (CVPR ‘00) (Hilton Head, SC, USA, June 13-15, 2000). IEEE computer society 2000, 1222-1227.
[32] Yan, R. Hauptmann. A. and Jin, R. Negative pseudo-relevance feedback in content-based video retrieval. In Proc. of the ACM Intl. Conference on Multimedia (MM ‘03) (Berkeley, CA, USA, November 2-8, 2003). ACM press 2003, 343-346.
[33] Zhou, X.S. and Huang, Thomas S. Relevance feedback in image retrieval: a comprehensive review. Multimedia System, 8, 6 (Apr. 2003)536-544. |
| Description: | 碩士
國立政治大學
資訊科學學系
93753009
95 |
| Source URI: | http://thesis.lib.nccu.edu.tw/record/#G0093753009 |
| Data Type: | thesis |
| Appears in Collections: | [資訊科學系] 學位論文
|
All items in 政大典藏 are protected by copyright, with all rights reserved.
|
