A Method of Music Retrieval Using Impression Keywords

Recently, making electronic data of the multimedia such as music, images, books, and so on has been spread. However, it is necessary to look for specific contents in the database with a large amount of music data because electronic data increases rapidly. Therefore, an efficient search engine is requested. This paper presents a music retrieval method focusing on the impression keywords. In the presented method, impression keywords as queries is constructed by using Twitter beforehand. The impression vector to music is generated by using this impression keyword set. And, the retrieval is processed by measuring the similarity to impression vectors with a query. From experimental results, it turns out that the recommended music displayed as a retrieval result appropriately expresses the impression of the user requests.

[1]  Peter Knees,et al.  Towards Semantic Music Information Extraction from the Web Using Rule Patterns and Supervised Learning , 2011 .

[2]  Panagiotis Symeonidis,et al.  Ternary Semantic Analysis of Social Tags for Personalized Music Recommendation , 2008, ISMIR.

[3]  Youngmoo E. Kim,et al.  Exploring automatic music annotation with "acoustically-objective" tags , 2010, MIR '10.

[4]  Masao Fuketa,et al.  Word classification and hierarchy using co-occurrence word information , 2004, Inf. Process. Manag..

[5]  George Tzanetakis,et al.  A comparative evaluation of search techniques for query-by-humming using the MUSART testbed , 2007 .

[6]  Tadahiko Kumamoto.  Design and Evaluation of a Music Retrieval Scheme That Adapts to the User's Impressions , 2005, User Modeling.

[7]  Masao Fuketa,et al.  An incremental construction method of a large-scale thesaurus using co-occurrence information , 2013, Int. J. Comput. Appl. Technol..

[8]  Jun-ichi Aoe,et al.  Automatic acquisition for sensibility knowledge using co-occurrence relation , 2008, Int. J. Comput. Appl. Technol..

[9]  Tadahiko Kumamoto.  A Natural Language Dialogue System for Impression-based Music Retrieval , 2010, Polytech. Open Libr. Int. Bull. Inf. Technol. Sci..

[10]  Gert R. G. Lanckriet,et al.  Semantic Annotation and Retrieval of Music and Sound Effects , 2008, IEEE Transactions on Audio, Speech, and Language Processing.

[11]  Masao Fuketa,et al.  A link trie structure of storing multiple attribute relationships for natural language dictionaries , 1999, Int. J. Comput. Math..