Category Archives: Uncategorized

I came across two articles by Matthew Butterfield, a professor of music theory at Franklin & Marshall College, that should be interesting for us in surveying analyses of jazz, and in resorting to observations or measurements using waveforms as evidence. … Continue reading →

Just as a point of interest, here’s an example of a human-generated, heavily annotated transcription of a jazz performance: Sancticity, Scofield solo analysis transcribed by Bert Ligon http://in.music.sc.edu/ea/jazz/Transcriptions/Sancticity.all.pdf It’s clear that in the near future we’ll be able to generate … Continue reading →

Much of our discussion lately has been about biases of various sorts in MIR tools and how to avoid/fix them. Here’s a paper that touches on many of the topics we’ve been thinking about: Computational Ethnomusicology George Tzanetakis, Ajay Kapur, … Continue reading →

We are now hosting a general discussion list for people and machines interested in exploring the application of MIR (Music Information Retrieval) techniques to jazz: https://lists.columbia.edu/mailman/listinfo/jazz-mir  

DAn commented on my last post agreeing that it was circular to ask whether a drummer is “ahead” or “behind” the beat, when it is precisely the drummer we may be relying on to determine the beat.  That led me … Continue reading →

          After working on beat tracking for whole performances, our conversation turned to how to think about the chief rhythmic instrument in a conventional jazz group. The drummer states the tempo for the group. He also … Continue reading →

One of the first steps toward high-level analysis of audio recordings is decomposing the signal into a representation that can be easily digested by a computer.  A more or less standard approach is to carve up the signal into a … Continue reading →

I’ve been playing with plotting various EN analysis quantities against one another. I thought that pitch vs loudness or pitch vs segment duration might turn up something interesting, but visually at least, there’s not much of interest. Then I tried … Continue reading →

I used Paul Lamere’s Infinite Jukebox app to generate some fun examples for the j-disc MIR launch event a couple weeks ago: * Sonny Stitt: Autumn Leaves * Bill Monroe: Roanoke * Kenny G: Careless Whispers  

We’re starting to think that maybe beat tracking, as it’s usually implemented, isn’t really that useful for a lot of jazz. Not only do many jazz tracks seem to confuse beat trackers, but it’s not clear that “beats” are really … Continue reading →