ABSTRACT
Efficient and intelligent music information retrieval is a very important topic of the 21st century. With the ultimate goal of building personal music information retrieval systems, this paper studies the problem of identifying "similar" artists using both lyrics and acoustic data. The approach for using a small set of labeled samples for the seed labeling to build classifiers that improve themselves using unlabeled data is presented. This approach is tested on a data set consisting of 43 artists and 56 albums using artist similarity provided by All Music Guide. Experimental results show that using such an approach the accuracy of artist similarity classifiers can be significantly improved and that artist similarity can be efficiently identified.
- Shlomo Argamon, Marin Saric, and Sterling S. Stein. Style mining of electronic messages for multiple authorship discrimination: first results. In SIGKDD, pages 475--480, 2003. Google ScholarDigital Library
- Eric Bill. Some advances in transformation-based parts of speech tagging. In AAAI, pages 722--727, 1994. Google ScholarDigital Library
- David M. Blei, Andrew Y. Ng, and Michael I. Jordan. Latent dirichlet allocation. J. Mach. Learn. Res., 3:993--1022, 2003. Google ScholarCross Ref
- Eric Brochu and Nando de Freitas. Name that song!: A probabilistic approach to querying on music and text. In NIPS, 2002.Google Scholar
- D.P.W.Ellis, B. Whitman, A. Berenzweig, and S. Lawrence. The quest for ground truth in musical artist similarity. In ISMIR, pages 170--177, 2002.Google Scholar
- D. Huron. Perceptual and cognitive applications in music information retrieval. In ISMIR, 2000.Google Scholar
- Tao Li and Mitsunori Ogihara. Semi-supervised learning from different information sources. Knowledge and Information Systems Journal, 2004. In Press. Google ScholarDigital Library
- Tao Li, Mitsunori Ogihara, and Qi Li. A comparative study on content-based music genre classification. In SIGIR, pages 282--289, 2003. Google ScholarDigital Library
- R. Mitton. Spelling checkers, spelling correctors and the misspellings of poor spellers. Information Processing and Management, 23(5):103--209, 1987. Google ScholarDigital Library
- Efstathios Stamatatos, Nikos Fakotakis, and George Kokkinakis. Automatic text categorization in terms of genre and author. Computational Linguistics, 26(4):471--496, 2000. Google ScholarDigital Library
- George Tzanetakis and Perry Cook. Musical genre classification of audio signals. IEEE Transactions on Speech and Audio Processing, 10(5), July 2002.Google ScholarCross Ref
- G. Weiss and F. Provost. The effect of class distribution on classifier learning: An empirical study. Technical Report ML-TR 44, Rutgers University, 2001.Google Scholar
- B. Whitman, D. Roy, and B. Vercoe. Learning word meanings and descriptive parameter spaces from music. In HLT-NAACL03 workshop, 2003. Google ScholarDigital Library
- B. Whitman and P. Smaragdis. Combining musical and cultural features for intelligent style detection. In ISMIR, pages 47--52, 2002.Google Scholar
- Bianca Zadrozny and Charles Elkan. Learning and making decisions when costs and probabilities are both unknown. In SIGKDD, pages 204--213, 2001. Google ScholarDigital Library
Index Terms
- Music artist style identification by semi-supervised learning from both lyrics and content
Recommendations
Semi-supervised learning for music artists style identification
CIKM '04: Proceedings of the thirteenth ACM international conference on Information and knowledge managementMusic/lyrics composition system considering user's image and music genre
SMC'09: Proceedings of the 2009 IEEE international conference on Systems, Man and CyberneticsThis paper proposes a music/lyrics composition system consisting of two sections, a lyric composing section and a music composing section, which considers user's image of a song and music genre. First of all, a user has an image of music/lyrics to ...
Inductive Semi-supervised Multi-Label Learning with Co-Training
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningIn multi-label learning, each training example is associated with multiple class labels and the task is to learn a mapping from the feature space to the power set of label space. It is generally demanding and time-consuming to obtain labels for training ...
Comments