Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote 4 down vote favorite

I'd like to compare some Jazz tunes.

Jazz tunes are characterized by a succession of chords. The interval between each succeeding chord (number of tones) and the order in which they appear matter.

At first, I thought of a Mann-Whitney test that could compare two tunes with a different number of chords using the ranks of their intervals.

Another thing matters, though: the quality of the chord. A major chord can follow a minor chord, a dominant one, or a semi-diminished one. So, there is a mix of ordinal and categorical variables of which to take account.

What methodology should be used in testing the similarity of two jazz tunes?

share|improve this question
2  
Have you tried the default (and generic) way, i.e. calculate MPEG4 descriptors and cluster? – mbq♦ Aug 14 '12 at 10:40
When people do comparisons of musical pieces for the purposes of information retrieval algorithms, most use MFCCs to decompose the music, rather than doing all of what you describe. – jonsca Aug 15 '12 at 7:12
The analysis is meant to be applied to scores, not recordings. – mathieu_r Aug 23 '12 at 9:45

Know someone who can answer? Share a link to this question via email, Google+, Twitter, or Facebook.

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Browse other questions tagged or ask your own question.