Musical Similarity and Commonness Estimation Based on Probabilistic Generative Models of Musical Elements

摘要

This paper proposes a novel concept we call musical commonness, which is the similarity of a song to a set of songs; in other words, its typicality. This commonness can be used to retrieve representative songs from a set of songs (e.g. songs released in the 80s or 90s). Previous research on musical similarity has compared two songs but has not evaluated the similarity of a song to a set of songs. The methods presented here for estimating the similarity and commonness of polyphonic musical audio signals are based on a unified framework of probabilistic generative modeling of four musical elements (vocal timbre, musical timbre, rhythm, and chord progression). To estimate the commonness, we use a generative model trained from a song set instead of estimating musical similarities of all possible song-pairs by using a model trained from each song. In experimental evaluation, we used two song-sets: 3278 Japanese popular music songs and 415 English songs.Twenty estimated song-pair similarities for each element and each song- set were compared with ratings by a musician. The comparison with the results of the expert ratings suggests that the proposed methods can estimate musical similarity appropriately. Estimated musical commonnesses are evaluated on basis of the Pearson product-moment correlation coefficients between the estimated commonness of each song and the number of songs having high similarity with the song. Results of commonness evaluation show that a song having higher commonness is similar to songs of a song set.