Preparing for ISMIR

I am getting excited about ISMIR in a couple weeks. As many people suggested to me last year, I am going to ISMIR with (almost) nothing to do but take it all in. I do have a late breaking session poster, but that is on the very last session on Thursday. I do not anticipate many people attending the session since most will be trying to make flights back home. To be honest, I think they should scrap the last day or make it a full day with the dinner to end everything.

I have even started reading some of the proceedings as Elias pointed out that they are up for everyone to see. So far I have read about five papers. I have to admit, I was a little fearful about the focus of interdisciplinary research being incorporated into every individual paper. This is largely subjective and I feared that people would apply too broad of a focus and the papers would not get into technical detail in any one area. While I am sure some of this is true, I was happy to find a couple papers that were really good. I liked the paper by Moh and Buhmann about adaptive kernels and would like to see it applied to something other than artist classification, which does not necessarily translate into general similarity as Elias pointed out in his thesis. Matthew Riley, et. al., was good too. It is great to see that people are tokenizing songs to incorporate dynamics better. I think they could get more modeling power if they added HMMs and did something closer to the acoustic segment modeling approach that my adviser and I did at ISMIR a couple years ago. I really like Kurt Jacobson's paper on identifying artist communities in social communities, especially the attempt to incorporate audio analysis into the design. I am definitely going to discuss this with him at the conference.

If I have not mentioned your paper, then I probably have not read it yet, so do not take offense. I will get to it and I am sure I will like it, even if I do not post about this in the future.

Radio killed the radio star

One of my favorite Internet radio stations, Pandora, may finally be shutting down thanks to the recent hike in royalty fees. I think the only way that people may start to notice is if an Internet radio giant takes the fall. No one ever notices a problem until a staple goes down. One wonders just how record companies plan on making a profit in the future. CDs are not selling and everyone is praying for its demise. Digital distributers of music are closing shop, causing people to fear downloading anything having to do with DRM.

I guess this quote signifies how little record companies understand capitalism: "SoundExchange officials argue that because different media have different profit margins, it is appropriate to set different royalty rates." Really? Do record companies pay more for the raw materials to make CDs? If Jack White and I walk into a guitar store and purchase the same guitar, does he pay more? Surely, he will make a lot more money with that guitar than I will ever make. If I'm not mistaken, isn't charging two different people for the same product illegal when it results in decreasing competition?

Closed-set vs Open-set Tags

Ugh. The cluster is still down. I was hoping to get something together for MIREX's tag annotation contest, but there is no way I can get to it with everything else I have going on. Oh well, maybe next year. Anyway, on to the subject.

I have been examining playlist prediction using Last.fm and Pandora tags. Not surprisingly, I got this result:


This was a real simple nearest-neighbor search. While this gives evidence to (part of) my hypothesis that Last.fm's "anything goes" open tag set will perform better than Pandora's expert-assigned closed tag set, I need to eliminate some other variables before any final conclusions are made. Most noteably, Pandora's tag set has a size of around 500 tags, while Last.fm's tag set is (at least) on the order 10,000. In fact, on just a subset of the USPop set, I found over 20,000 tags. I need to reduce the dimensions so they are comparable, but still maintain the flavor of Last.fm's set.

Occum's Razor and the "Rap Problem"

Yesterday, I briefly described the "Rap problem," which is where artists names appear several times in a database because they feature other artists. It's probably unfair to "pick" on rap after looking at the greatest violators, but there is a clear trend that rap is a fairly big violator. Note: I'm not saying rap sucks or anything like that. I'm just saying that this presents a problem for researchers dealing in search technology. In fact, as I'll show, people who feature lots of guest artists make a pretty impressive list of musicians and performers.

At first, I thought I would have to do an extensive literary search for an efficient solution to this problem, but my girlfriend proposed a quick solution. She suggest that I just look to see if the artists' names are the first ones listed. At the surface this seemed reasonable, except that some artists have names that are sub-sequences of other artists (e.g., "Joe", "Pink"). But this lead to an efficient solution to the problem: look for names that are equal or that have a special formatting. For example, most of the feature problems can be dealt with by looking for the regular expression /^artistsName_feat_/ or /^artistName_&_/ (underscores and ampersand are not wildcards).

This actually worked fairly well since I am only looking for a group of users that listened to songs from my dataset. This is not a solution to the misspelling problem, but it's a fair assumption that most people will listen to correct spellings when using a well-established site like Last.fm. This greatly saved some time and proved once again that one should always try something quick and dirty first.

Looking at the top 20, there is a definite pattern:

mariah_carey:	135
busta_rhymes:	105
usher:	54
nelly:	52
madonna:	48
ludacris:	42
wyclef_jean:	40
santana:	39
michael_jackson:	37
bob_marley:	37
david_bowie:	35
ja_rule:	32
dmx:	31
nelly_furtado:	31
ricky_martin:	29
frank_sinatra:	29
sting:	28
cypress_hill:	27
elton_john:	27
outkast:	25

One should note that artists like Mariah Carey and Busta Rhymes have not necessarily played with over a hundred different artists because those artists can have different spellings, which I did not correct for (e.g., "mariah_carey_feat_boys_2_men" vs "mariah_carey_feat_boys_ii_men). However, the likelihood of mispelling of the featured artists is probably not an inherint trait of the first artists, so we can treat it as noise. I don't think Mariah Carey has a particular fondness of easily mispelled or varied names.

One can also divide this group into about 3 groups (some overlap depending on personal genre definitions): hip-hop, rap, and old and established rock/pop artists. So, the "rap" problem may not be such a problem in terms of taste given the list above. Also, voice and style are very central to the "musicalness" of rap and hip-hop, so using a different artist is probably the same as a rock musician using an orchestra or a different instrument than normal.

The Continued Popularity of USPop2002

In order to gather some useful training data for my thesis, I need to get some preference rankings for music recommendation. It is also necessary for there to exist tag information as well, such as Last.fm and Pandora. Further, I must be able to obtain audio (or some acoustic features) rather cheaply. The best data I have found is LabROSA's USPop2002. It's much larger than RWC Database and because the songs are based on popularity in 2002, it is much more likely to have tags than Magnatunes. The downside is that I'm limited to Mel-frequency cepstral coefficients.

While, LabROSA also has playlists from OpenNap, there are no preferences given; a song is either on a person's playlist or not on a person's playlist. I've been using Last.fm's API to try to remedy this situation. First, I gathered the top listeners for each of the 400 artists in the USPop2002 set. Over the past couple weeks I have been extracting the total combined weekly chart lists to get the number of plays of a particular song for each listener. While number of plays may not be a direct measure of preference (or rating), it is reasonable to assume that people will listen to song they like more than the ones they do not like. At the moment, I have only downloaded about 4000 listeners (I have to download several pages per listener and Last.fm requests a 1 second wait between requests). Also, artist names appear in several different varieties. Rap and hip-hop seem to be exceptionaly bad since they are unable to do any song without a guest star.

There's tons of data to play with, but for now, let's look into what artists are popular. Note: there are still thousands of users to download and some artists' top 50 listeners have not been reached yet. These results should be taken with precaution so that we don't leap to Montauk monster conclusions (it's a racoon, let it go people).

This kind of continued success is what I would expect to see: superstars make up the vast majority of hits and the short-lived fame of others dies out. However, one should note the artists appearing at the bottom may have more plays due to the "rap problem" described above. I also wanted to see if the data was consistent with Zipf's Law, but it is not (the bend is not deep enough).


One neat thing occurred in the top 5 artists: Beatles, Radiohead, Pink Floyd, David Bowie, Queen. Only the Beatles and possibly David Bowie have had enough users from their lists to explain such high results. Indeed, it appears that the other artists would be just as popular if I had taken a random group of users (note: I'm sure the Beatles will also have this once I extract more pages).

I'll have more later.

X-cluster down

The X-cluster was taken down today for summer maintenance. Looks like it may be two weeks, but hopefully the file server gets back on-line soon. I'll probably post some preliminary results on a couple of experiments during this time.

How labels could profit from Radiohead and NIN 'experiment'

I just got done reading an interesting economic article by Will Page and Eric Garland on whether Radiohead's "pay what you want" experiment was successful in attracting usual torrent users to the band's website. I'm a little cautious of the conclusions by Page and Garland of "yes, but with a twist" because ultimately, this is a very small sample size and because the novelty might have changed user behavior.

But the author's have a fantastic analysis in the form of a table comparing InRainbows.com, theslip.nin.com, and torrent sites. The author make note of the various invisible costs to the users such as "attention costs", "privacy costs", and "quality of product". What if record labels viewed torrent sites, not as competition, but rather as base designs that could be improved upon?

As the authors' note, a large number of people still went to torrent sites for illegal downloads even though InRainbows.com offered the same thing, but free and legal. They conclude this is because people will ultimately keep their buying habits steady unless they have a benefit to gain from switching (clearly, legality alone is not enough). Why can't labels cash in on this?

Why could labels not offer similar sites and offer additional content? Imagine a completely different type of business model: instead of collecting money from consumers, collect them from the artists. One of the problems with a future like the one InRainbows.com advocates is that I would have to go to a bunch of different sites (one for each artist) to obtain music. Labels could offer an "online free supermarket" of music. In addition, targeted advertisement could be done in a similar way as iLike and Amazon (e.g., "we've noticed that you like Band X, did you know that Band X has a show scheduled near you? Here are some T-shirts you can buy"). Artists would pay to have their music on these sites, sell shirts, etc. Recommendations would be made in addition. One day, oh one day, we'll have iToogle.fm.