Useless for what _you_ guys do with pyTone. For my purposes classification is essential and the core of what Dancebox will do for the user. My classifications are much more specific than what a single field genre allows and allow a song to span mutiple classifications.
I should have said a time-waster instead of useless. (unless you have a limited set of files) Can you give a list of different characteristics that you use for classification ?
Sure but remember that my requirements are very specific to partner dance and for use in a dance studio and or a dance party. The concept may be more generally applied to other areas but not my data. The major areas: The dance that can be done to the song The class of dance the song is The fuzzy speed The style of dance - Class is a over all catagory of dances. Latin, Smooth, Swing, Rhythm, Misc - Dance is a specific dance, ChaCha, Rumba, East coast swing, Samba, Foxtrot,etc - Style is a subclass of dance. Some dances have both and International and American style. East coast swing can be single, double or triple time. The beat and speed of the music drives all of these. - Speed is fuzzy in that a song that is fast for one dance may be slow for another but both dances still work for the same song. So you can't just go off of BPM.
I bet most (if not all) the objective characteristics can be deduced automatically. I've been looking at some literature on this. Search for 'automatic classification of music', 'music fingerprinting' or 'accoustic fingerprinting'.
Having something that did this would be cool. For my purposes it dosen't have to be that accurate. I'm expecting the use to do a lot of manual classification up front anyway. One thing I do want to come up with eventually though is some sort of guid for a song such that users can share databases of songs that have previously been classified. -- Richard A. Smith