Digital music has changed the world. It has never been easier to feed your music addiction.Â
I personally will never understand why people have bought over 3 billion tracks at iTunes when they can get a much better deal using subscription services like Yahoo! Music Unlimited, which cost less per month than the price of a single drink at a club and allow you to download or play on demand over 2 million tunes.  You may occasionally find me at the bar, getting obstreperous about this subject. I can usually convince two or three people to try it for every one that I actually get into a fight with.  In the end, I think the problem is that most people don’t know that music subscription services exist or how they work. There’s also the nagging issue that many of these services suffer from some annoying technical glitches, which can often require a bit of work to get around. This will hopefully go away once all the major labels agree to drop their requirement that subscription services only offer DRM encoded tracks.
With all this music available though, it’s easy to get lost in the music.  You’ll never be able to actually listen to all of those 2 million tunes you have access to. There simply isn’t enough time in the day. So how do you choose what to listen to? Subscription services can typically deliver about 75% of what you already know you like, but I much prefer finding new music I’ve never heard before. It’s refreshing and makes you feel good, like sipping Erdinger in the sun on Venice Beach or Leffe au Saint-Michel.
So how do you discover new music in a world of too much choice? I used to really like Webjay for this sort of thing, but it’s gone now. One of the best ways to find that more eclectic 25% is by surfing music blogs. Sites like Hype Machine or Musiclibre let you explore the mp3 blog world and find new stuff accordingly - they are a great place to start, but there is much opportunity for cool new discovery tools to be built.
To this end, I had the pleasure of working with DSP guru Malcolm Slaney on this problem last year. We used signal analysis to analyze web media tracks that otherwise had very little metadata information. Sadly this is the norm for most audio tracks on the web. When websites like Yahoo! or Google go out and crawl the web looking for audio files, they often return very little relevant info about the content of the audio files themselves. We analyzed over 25,000 popular mp3 files and found less than 20% had data in their ID3 tags. To make matters worse, the actual contents of the ID3 tags were often incomplete or incorrect. This means that searching for web media using traditional metadata techniques, or traditional web search techniques (ie. the status quo) ignores the vast majority of audio files on the web.
We used MARSYAS to help us analyze our corpus and projected the results into a multidimensional audio feature space based upon the acoustic properties of each track. Our demo page lets you browse this feature space to find music which is acoustically similar.  Using this technique, we can suggest music that would otherwise never be returned from any existing audio search engine - yet sounds similar to music you enjoy and want to listen to.  Use it to select a seed song which you like, and check out the acoustically similar tunes it recommends:Â
http://www.musiclibre.org/research/playlist.php
Popularity: 25% [?]
4 Users Commented In This Post
8-30-2007 at 10:40:50 from 12.219.148.49
> “So how do you discover new music in a world of too much choice?”
one word: pandora
http://pandora.com
now, they just need to work on getting all that CC and independently produced music out there on blogs into pandora’s database.
8-30-2007 at 18:18:02 from 216.145.54.158
Yeah, Pandora is definitely very cool - but using musicologists to analyze and annotate music doesn’t exactly scale very well. As you note, all that CC and independently produced music is not in the Pandora database, and it’s unlikely that it will be anytime soon.
This is where automated techniques, such as audio content analysis can be effective. In a head to head race, I’ll take the human analysis every time, but the computer is a lot faster, cheaper and less subjective. Automated techniques which incorporate a human computational element should eventually win out.
8-31-2007 at 05:31:22 from 12.219.148.49
Hmm … now what you’re saying makes me think of a very cool idea.
IF we had a clue how pandora’s database worked (and we don’t — it’s pretty complicated, I’m sure). But IF you knew how to get data into a pandora-like database (or pandora could be persuaded to try something out like this themselves), then one could in theory publish a widget that can be included on music weblogs to categorize the tunes found there .. or even better, integrated into the flash players everyone’s using these days.
So, not necessarily “expert musicologists” like pandora has, but “wisdom of the masses” type stuff.
SO, folks view your tunes on your blog, and if they’re nice, sort them, It all goes back to a big database, getting all of that cc music into a pandora like thing.
8-31-2007 at 12:13:34 from 209.131.62.116
Hmmm, that’s a pretty good idea. I don’t know how “pandoresque” it would be. But I really like the idea of a widget for musicbloggers that people can use to comment/rate/annotate the blog content with, which bloggers could then access via an open API to see what people think of their site… (-:
Leave A Reply.....