Leader ： Masahiro HAMASAKI
Members ： Keisuke ISHIDA, Masataka GOTO, Tomoyasu NAKANO
In this research, we developed Songrium that is a music browsing assistance service based on visualization of music relations and launched Songrium in August 2012. Songrium visualizes relations among both original songs and derivative works. Songrium also features a social annotation framework to verbalize and share various relations among songs, and a flexible ranking mechanism to find interesting songs. After Songrium was released to the public, over 110,000 original songs and 500,000 derivative works have been registered in Songrium. This work collaborate with Songle that is the result of our research product on 2012.
Enrich your music listening experience with music networks
Songrium is a music browsing assistance service based on visualization of relations between music content on the video sharing web searce, e.g., Niconico and YouTube. Songrium uses web mining and music understanding technologies together with advanced data visualization techniques to achieve unique functions, such as Music Star Map, Planet View, Bubble Player, and Singing Voice Analysis. These functions facilitate discovery and understanding of songs. The annotation (Arrow Tag) function allows users to reveal relations between original songs. The visualized relations and derivative works provide a better user experience of retrieving and browsing songs.