Accessing Music Digital Libraries by Combining Semantic Tags and Audio Content

An interesting problem in accessing music digital libraries is how to combine the information of different sources in order to improve the retrieval effectiveness. This paper introduces an approach to represent a collection of tagged songs through an hidden Markov model with the purpose to develop a system that merges in the same framework both acoustic similarity and semantic descriptions. The former provides content-based information on song similarity, the latter provides context-aware information about individual songs. Experimental results show how the proposed model leads to better performances than approaches that rank songs using both a single information source and a their linear combination.