Quantifying the Salience of Musical Characteristics From Unstructured Text

Abstract. Music is a discerning window to the rich diversity of the world. We hypothesize that identifying the differences betweenmusic from different cultures will lead to richer information models representative of them. Using five music styles, this paper presents a novel approach to bring out the saliences of a given music by rank-ordering its characteristics by relevance using a natural language text corpus. The results agree with the cultural reality reflecting the diverse nature of the music styles. Further, to gather insights into the usefulness of this knowl-edge, an extrinsic comparative evaluation is performed. Similarities between enti-ties in each music style are computed based on a salience-aware semantic distance proposed using the knowledge acquired. These are compared with the similarities computed using an existing linked-data based distance measure. A sizable over-lap accompanied by an analysis of users ' preferences over the non-overlapping portions indicate that the knowledge acquired using our approach is indeed musi-cally meaningful and is further complementary in nature to the existing structured information.