摘要： 随着协同标注功能的普及,用户可以通过标注自己感兴趣的音乐实现个性化的分类管理,因此音乐共享系统中的社会化标签已成为互联网的重要资源。为了提高音乐检索系统的效率,综合考虑了社会化标签的特性及其对音乐检索模型的影响,利用了TLDA方法来进行标签聚类以获取更多的语义相关的标签,综合考虑了用户检索行为、歌词、音乐标签和音乐流行度来提高音乐信息检索系统的性能。实验表明,基于TLDA和SVSM的音乐检索模型相比于基于属性数据的音乐检索模型以及k-means标签聚类的模型,尤其是在音乐标签稀疏和非正规的情况下,能够在一定程度上提高音乐检索的性能。
| [1] Levy M,Sandler M．Music Information Retrieval Using Social Tags and Audio[J]．IEEE Transactions on Multimedia,2009,11(3):383-395 [2] Beckett D．Semantics Through the Tag[C]∥Proceeding ofXTech 2006:Building Web 2.0．2006 [3] Kim H,Breslin J G,Yang S,et al．Social Semantic Cloud of Tag:Semantic Model for Social Tagging[C]∥Proceedings of the 2nd KES International Conference on Agent and Multi-agent systems:technologies and applications (ACM)．LNCS,vol．4953:83-92 [4] Knees P,Pohle T,Schedl M,et al．A Document-centered Approach to a Natural Language Music Search Engine[C]∥Proceedings of the IR research,30th European Conference on Information Retrieval (ECIR)．Glasgow,UK,2008:627-631 [5] Blei D,Ng A,Jordan M．Latent Dirichlet Allocation[J]．Journal of Machine Learning Research,2003(3):993-1022 [6] Fei W,Xin W,Shao B,et al．Tag Integrated Multi-Label Music Style Classification with Hypergraph[C]∥International Society for Music Information Retrieval．Kobe,Japan,October 2009:363-368 [7] Begelman G,Keller P,Smadja F．Automated Tag Clustering,Improving Search and Exploration in the Tag Space[C]∥The 15th International World Wide Web Conference．Edinburgh,UK,2006 [8] Karydis I,Nanopoulos A,Gabriel H,et al．Tag-aware SpectralClustering of Music Items[C]∥International Society for Music Information Retrieval．Kobe,Japan,October 2009:159-164 [9] Levy M,Sandler M．A Semantic Space for Music Derived from Social Tags[C]∥International Society for Music Information Retrieval．Philadelphia,Pennsylvania,USA,September 2007:14-18 [10] Downie S,Nelson M．Evaluation of a Simple and Effective Music Information Retrieval Method[C]∥Special Interest Group on Information Retrieval (ACM)．Athens,Greece,2000:73-80 [11] Byrd D,Crawford T．Problems of Music Information Retrieval in the Real World[J]．Information Processing & Management,2002,38(2):249-272 [12] Rosen-Zvi M,Chemudugunta C,Griffiths T．Learning author-topic models from text corpora[J]．ACM Transactions on Information Systems (TOIS),2010,28(4):1-4 [13] Krestel R,Fankhouser P,Nejdl W．Latent dirichlet allocation for tag recommendation[C]∥ACM Conference on Recommender Systems．New York,USA,October 2009:61-68 [14] Newman D,Chemudugunta C,Smyth P．Statistical entity-topic models[C]∥ACM Special Interest Group on Knowledge Discovery and Data Mining (ACM SIGKDD)．Philadelphia,PA,USA:680-68 [15] Mimno D,McCallum A．Topic Models Conditioned on Arbitrary Features with Dirichlet-multinomial Regression[C]∥UAI,2008．2008:411-418 [16] Feng Y,Zhang Y,Pan Y．Popular Music Retrieval by Detecting Music[C]∥ACM SIGIR’03．Toronto,Canada,July 2003 [17] Korhonen M D,Clausi D A,Jernigan M E．Modeling Emotional Content of Music Using System Identification[J]．IEEE Transactions on System,Man,and Cybernetics,Part B,2006,36(3):588-599 [18] 夏云庆,杨莹,张鹏洲,等．基于情感向量空间模型的歌词情感分析[J]．中文信息学报,2010,1(24):99-103 [19] Han B-J,Rho S,Jun S,et al.Music Emotion Classification and Context-based Music Recommendation[J]．Multimedia Tools and Applications,2010,47(3):433-460 [20] Li J,Lin H,Zhou L．Emotion Tag Based Music Retrieval Algorithm[C]∥Proceedings of the AIRS’10．Taibei,Taiwan,2010:599-609 [21] Chen Y,Santamaría R,Butz A,et al．TagClusters:Semantic Aggregation of Collaborative Tags beyond TagClouds[C]∥Proceedings of the 10th International Symposium on Smart Gra-phics．Salamanca,Spain,2009:56-67 [22] 马希荣,梁景莲．基于情感音乐模板的音乐检索系统研究[J]．计算机科学,2009,6(1):239-278 |
| No related articles found! |
|
||
首页