Improving music genre classification using collaborative tagging data

ABSTRACT

As a fundamental and critical component of music information retrieval (MIR) systems, music genre classification has attracted considerable research attention. Automatically classifying music by genre is, however, a challenging problem due to the fact that music is an evolving art. While most of the existing work categorizes music using features extracted from music audio signals, in this paper, we propose to exploit the semantic information embedded in tags supplied by users of social networking websites. Particularly, we consider the tag information by creating a graph of tracks so that tracks are neighbors if they are similar in terms of their associated tags. Two classification methods based on the track graph are developed. The first one employs a classification scheme which simultaneously considers the audio content and neighborhood of tracks. In contrast, the second one is a two-level classifier which initializes genre label for unknown tracks using their audio content, and then iteratively updates the genres considering the influence from their neighbors. A set of optimizing strategies are designed for the purpose of further enhancing the quality of the two-level classifier. Extensive experiments are conducted on real-world data collected from Last.fm. Promising experimental results demonstrate the benefit of using tags for accurate music genre classification.

REFERENCES

• 1: Ralitsa Angelova , Gerhard Weikum, Graph-based text classification: learn from your neighbors, Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval, August 06-11, 2006, Seattle, Washington, USA [doi>10.1145/1148170.1148254]
• 2: J.-J. Aucouturier and F. Pachet. Representing musical genre: A state of the art. Journal of New Music Research., 32(1):83--93, 2003.
• 3: Shenghua Bao , Guirong Xue , Xiaoyuan Wu , Yong Yu , Ben Fei , Zhong Su, Optimizing web search using social annotations, Proceedings of the 16th international conference on World Wide Web, May 08-12, 2007, Banff, Alberta, Canada [doi>10.1145/1242572.1242640]
• 4: B. Berendt and C. Hanser. Tags are not metadata, but just more content - to some people. In ICWSM, 2007.
• 5: Christopher H. Brooks , Nancy Montanez, Improved annotation of the blogosphere via autotagging and hierarchical clustering, Proceedings of the 15th international conference on World Wide Web, May 23-26, 2006, Edinburgh, Scotland [doi>10.1145/1135777.1135869]
• 6: J. J. Burred and A. Lerch. A hierarchical approach to automatic musical genre classification. In 6th Int. Conf. Digital Audio Effects, 2003.
• 7: Soumen Chakrabarti , Byron Dom , Piotr Indyk, Enhanced hypertext categorization using hyperlinks, Proceedings of the 1998 ACM SIGMOD international conference on Management of data, p.307-318, June 01-04, 1998, Seattle, Washington, United States
• 8: Bin Cui , H. V. Jagadish , Beng Chin Ooi , Kian-Lee Tan, Compacting music signatures for efficient music retrieval, Proceedings of the 11th international conference on Extending database technology: Advances in database technology, March 25-29, 2008, Nantes, France [doi>10.1145/1353343.1353374]
• 9: R. Dannenberg, J. Foote, G. Tzanetakis, and C. Weare. Panel: new directions in music information retrieval. In Proc. Int. Computer Music Conf., 2001.
• 10: Pavel A. Dmitriev , Nadav Eiron , Marcus Fontoura , Eugene Shekita, Using annotations in enterprise search, Proceedings of the 15th international conference on World Wide Web, May 23-26, 2006, Edinburgh, Scotland [doi>10.1145/1135777.1135900]
• 11: Micah Dubinko , Ravi Kumar , Joseph Magnani , Jasmine Novak , Prabhakar Raghavan , Andrew Tomkins, Visualizing tags over time, Proceedings of the 15th international conference on World Wide Web, May 23-26, 2006, Edinburgh, Scotland [doi>10.1145/1135777.1135810]
• 12: S. Golder and B. A. Huberman. The structure of collaborative tagging systems. In http://www.hpl.hp.com/research/idl/papers/tags/tags.pdf, 2006.
• 13: F. Gouyon, S. Dixon, E. Pampalk, and G. Widmer. Evaluating rhythmic descriptors for musical genre classification. In AES 25th Int. Conf., 2004.
• 14: Harry Halpin , Valentin Robu , Hana Shepherd, The complex dynamics of collaborative tagging, Proceedings of the 16th international conference on World Wide Web, May 08-12, 2007, Banff, Alberta, Canada [doi>10.1145/1242572.1242602]
• 15: Tao Li , Mitsunori Ogihara , Qi Li, A comparative study on content-based music genre classification, Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval, July 28-August 01, 2003, Toronto, Canada [doi>10.1145/860435.860487]
• 16: Q. Lu and L. Getoor. Link-based classification. In ICML, pages 496--503, 2003.
• 17: Sofus A. Macskassy , Foster Provost, Classification in Networked Data: A Toolkit and a Univariate Case Study, The Journal of Machine Learning Research, 8, p.935-983, 5/1/2007
• 18: M. Mandel and D. Ellis. Song-level features and support vector machines for music classification. In ISMIR, pages 594--599, 2005.
• 19: C. McKay and I. Fujinaga. Automatic genre classification using large high-level musical feature sets. In ISMIR, 2004.
• 20: C. McKay and I. Fujinaga. Musical genre classification: Is it worth pursuing and how can it be improved? In ISMIR, pages 101--106, 2006.
• 21: E. Pampalk, A. Flexer, and G. Widmer. Improvements of audio-based music similarity and genre classificaton. In ISMIR, pages 628--633, 2005.
• 22: L. Pelkowitz. A continuous relaxation labelling algorithm for markov random fields. volume 20, pages 709--715, 1990.
• 23: N. Scaringella, G. Zoia, and D. Mlynek. Automatic genre classification of music content: a survey. IEEE Singal Processing Magazine., 23(2):133--141, 2006.
• 24: P. Schmitz. Inducing ontology from flickr tags. In the workshop on Collaborative Web Tagging at WWW, 2006.
• 25: B. Taskar, P. Abbeel, and D. Koller. Discriminative probabilistic models for relational data. In UAI, pages 485--492, 2002.
• 26: G. Tzanetakis and P. Cook. Musical genre classification of audio signals. IEEE Trans. on Speech and Audio Processing, 10(5):293--302, July 2002.
• 27: K. West and S. Cox. Finding an optimal segmentation for audio genre classification. In ISMIR, pages 680--685, 2005.
• 28: B. Whitman and P. Smaragdis. Combining musical and cultural features for intelligent style detection. In ISMIR, 2002.
• 29: Xian Wu , Lei Zhang , Yong Yu, Exploring social annotations for the semantic web, Proceedings of the 15th international conference on World Wide Web, May 23-26, 2006, Edinburgh, Scotland [doi>10.1145/1135777.1135839]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL

Additional Classification:
  J. Computer Applications
  J.5 ARTS AND HUMANITIES

General Terms:
Algorithms, Experimentation, Performance

Keywords:
exploiting tag semantics, music genre classification, relaxation labeling