期刊文献+

最大熵模型在音乐自动语义标注中的应用研究 被引量:2

Research on maximum entropy model for music auto-tagging
下载PDF
导出
摘要 随着Web 2.0的发展,音乐自动语义标注成为音乐检索系统的关键技术。但是,目前主流的语义模型都是对音频的内容特征进行处理,并且对每个标签独立建模,忽略了标签间的关联产生的音乐上下文特征。将最大熵模型应用于音乐自动语义标注中,对音乐上下文特征进行建模处理,可以通过约束条件的多少调节模型对已知数据的拟合程度和对未知数据的适应度,并自然地解决统计模型中参数平滑的问题。实验表明,最大熵模型具有较高的预测准确率,同时,在建模过程中引入音乐相似度对特征信息函数进行选择,可以提高系统性能。 With the development of Web 2. 0, music auto-tagging has become a key technology of music retrieval system. However, in typical music auto-tagging and retrieval systems, all tag level models are trained based on music content of audio features independently, ignoring the music context features between tags. This article applies the maximum entropy model to music auto-tagging system, in order to process the music context features, adjust the fitness of both known data and unknown data, and naturally smooth the parameters in the statistical model by changing the number of constraint conditions. Experimental results show that the maximum entropy model has relatively high prediction accuracy. In addition, the applying of tag similarity in feature information function selection can improve the prediction performance.
出处 《电子测量技术》 2014年第12期32-35,40,共5页 Electronic Measurement Technology
关键词 音乐自动语义标注 最大熵模型 特征信息函数选择 music auto-tagging maximum entropy model feature information function selection
  • 相关文献

参考文献10

  • 1SCHEDI M, GOMEZ E, GOTO M. Multimedia information retrieval: music and audio [ C ]. Proceedings of the 21st ACM international conference on Multimedia. ACM, 2013: 1117-1118.
  • 2金聪,金枢炜.面向图像语义分类的视觉单词集成学习方法[J].电子测量技术,2012,35(8):53-56. 被引量:5
  • 3LEVY M, SANDLER M. Music information retrieval using social tags and audio [J]. Multimedia, IEEE Transactions on, 2009, 11(3): 383 395.
  • 4高天虹,马恩云.效率与成本是数据采集迎接挑战的关键[J].国外电子测量技术,2014,33(3):6-8. 被引量:4
  • 5NESS S R, THEOCHARIS A, TZANETAKIS G, et al. Improving automatic music tag annotation using stacked generalization of probabilistic svm outputs [C]. Proceedings of the 17th ACM international conference on Multimedia. ACM, 2009: 705-708.
  • 6MIOTTO R, LANCKRIET G. A generative context model for semantic music annotation and retrieval[J]. IEEE Transactions on Audio, Speech, and Language Processing, 2012, 20(4): 1096-1108.
  • 7HOFFMAN M D, BLEI D M, COOK P R. Easy As CBA: A Simple Probabilistic Model for TaggingMusic [C]. ISMIR. 2009, 9: 369-374.
  • 8曾金芳,滕召胜.信息熵在曲线拟合辨识中的应用[J].电子测量与仪器学报,2012,26(2):171-176. 被引量:10
  • 9文莹,肖明清,王邑,赵亮亮.基于信息熵属性约简的航空发动机故障诊断[J].仪器仪表学报,2012,33(8):1773-1778. 被引量:15
  • 10SERGIO D, YASM N, GONZALO G. A maximum : entropy model for opinions in social groups[J]. The European Physical Journal B, 2014.4.

二级参考文献45

共引文献30

同被引文献20

  • 1AHSAN H, KUMAR V, JAWAHAR C V. Multi- label annotation of music [ C ]. 2015 Eighth International Conference on Advances in Pattern Recognition (ICAPR), IEEE, 2015: 1-5.
  • 2NAM J, HERRERA J, SLANEY M, et al. Learning sparse feature representations for music annotation and retrieval[C]. ISMIR, 2012 : 565-570.
  • 3MIOTTO R, LANCKRIET G. A generative context model for semantic music annotation and retrieval[J]. IEEE Transactions on Audio, Speech and Language Processing, 2012, 20(4): 1096-1108.
  • 4. DHANALAKSHMI P, PALANIVEL S, RAMALINGAM V. Pattern classification models for classifying and indexing audio signals[J]. Engineering Applications of Artificial Intelligence, 2011, 24 (2) : 350-357.
  • 5HOFFMAN M, BLEI D, COOK P. Easy as CBA: a simple probabilistic model for tagging music [J]. International Symposium/Conference on Music Information Retrieval, 2009.
  • 6WANG Y. The constrained Fisher scoring method for maximum likelihood computation of a nonparametrie mixing distribution [ J ]. Computational Statistics, 2009, 24(1): 67-81.
  • 7ZHANG M L, ZHANG K. Multi-label learning by exploiting label dependency[C]. Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, 2010 : 999-1008.
  • 8LI C X. Exploiting label correlations for multi-label classification[J]. 2011.
  • 9DEI.AYE A, LIU C L. Contextual tezct/non-text stroke classification in online handwritten notes with conditional random fields[J].Pattern Recognition, 2014, 47(3): 959-968.
  • 10YIN J, YAN Q, LV Y, et al. Music auto-tagging with variable feature sets and probabilistic annotation[C]. 2014 9th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP), IEEE, 2014: 156-160.

引证文献2

二级引证文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部