Songle and Songrium with YouTube content
AIST have gone a step further with Songle.jp, including YouTube content. Previously only less mainstream music from SoundCloud and independent MP3 sources and the Vocaloid community could be found on the site. Songle is a miraculous shop window for Music Informatics Research, with many of the core MIR tasks performed on the song, and with the crucial ability for users to improve on the automatic detection. Chord detection, beat and bar detection, chorus detection, vocal activity detection, melody estimation, and song similarity, are all part of the chic web interface. Take this Muse track, for example. Now I’m, of course, partial, having been involved in the early stages of the project (see our 2011 paper), but the guys around Masataka Goto have really worked on it lots. Apart from the new content, what is interesting is the integration with Songrium.jp, which is focused on browsing derived and related tracks, in a beautiful interface. The Muse track, for example, has a link to Songrium that takes you to this page, which shows other YouTube videos orbiting the original. Fascinating stuff! Check it out!