Slashdot Mirror
Pandora Radio from Music Genome Project
kramthegram writes "The Music Genome Project, an attempt to define music by it's traits in a way similar to DNA defines traits in humans has led to the development of Pandora. Pandora uses the song choices you make to see what traits appeal to you and present you with custom radio station. While limiting you to thumbs up or thumbs down, the "gene" heuristics allows for a very quick adaptation to your musical tastes." Not sure how deep it goes, and I'm not sure I like that it led me from The Who to Styx and Def Leppard. But this is a neat little tool for discovering new music.
http://slashdot.org/article.pl?sid=05/10/07/173021 5&tid=141&tid=187
At least this one took over a month.
...Rob
The American Dream isn't an SUV and a house in the suburbs; it's Don't Tread On Me.
How useful will it really be? Sure, I like Punk, Alternative, and Metal. But the different bands have diffrents styles within the genra and I may love one band, but hate another similar one.
Someone save me from this sanity.
Is it anything like Last.FM, or does it run independant of other users? If it runs independant of other users, I'd say Last.FM would win in that category, because it's showing you what other people that listen to the same music that you do like.
I think Last.FM and this have the same aim, recommending music you might like, but I think Last.FM pulled it off better.
...Six Degrees of Kevin Bacon.
Actually, it seems like an interesting idea. We all have libraries of CDs based on our likes and I suspect if the libraries were analyzed we'd find slighlty deeper relations between the disparate music we collect. I've got a very eclectic collection of music and I'd be hard pressed to see the link between Reba McIntyre, Pink Floyd, and David Sanborn, but maybe there is one.
Of course some conspiracy theorist is going to use this to determine that the music industry is actually selling the same 5 songs over and over again, just in different keys and rhythms. Because we all know it's true.
GetOuttaMySpace - The Anti-Social Network
I like the user interface, but it would be cool if they would allow us to enter more than one "seed" artist. For example, I like Benny Bennassi, Patsy Cline and Rachmaninov. It would be cool to enter those three "seeds" and get some bizarre combination or mix of techno, country and classical. Fun!
Helping with organizational effectiveness is our job.
The best resutls come from submitting a song that you like. Using the Artist will most likely get you going down the wrong path. This is due to not all songs sounding similar from one artist. I have had the best results by putting in 2 or 3 songs that are similar to my ear that like. If you can't think of any songs by an Artist, Google it first. Also, there is a "rating" system. If you like the song, then give it a Thumbs Up, if you don't, give it a Thumbs Down. This will help your station learn what kind of music you are actually looking for. Rate the songs for better results.
I've been loving Pandora for about a week now. Just this morning I thought, "Hmmm... maybe I should try to get this posted to Slashdot. I'll bet a lot of the Slashdot crowd would dig this," but then I thought again to myself. I said, "Self, why would you want to slashdot their server and rob yourself of this little jewel?"
If you dirty buggers bring down this server... so help me steve...
I do like the site, unfortunately though after around 3 hours of using it, it stopped giving me new songs that I liked; it just played song's I already said I'd liked, or songs I didn't like. One interesting thing is that is uses basic mp3 files for the music, so it's actually not too hard to download the mp3's directly from the server if you log the right packets.
Pity they'll be putting ads on it (soon).
At least this one took over a month.
That's because it was on Fark.com (yesterday? the day before?), so the people that like to copy links from one site to the other thought it was new.
I want to drag this out as long as possible. Bring me my protractor.
... I've given up. The Pandora player insists on using Flash local storage, which I had disabled. Now, no matter what I do with the local storage settings, Pandora just keeps telling me I need to enable Flash local storage. Following their instructions doesn't help.
Too bad.
Sean
A very similar concept that actually works is www.music-map.com. This engine takes the input of all users into account and really let's you discover new artists from the genres you like.
Comment removed based on user account deletion
I once bought a highly recommended cd from Amazon, and it was the worst piece of noise I have ever heard (I won't mention the artist in question). But almost all the reviews were five starts and glowing. Finding new interesting artists which match your taste in music is a hard task. Could a classification system help to make suggestions?
I find Last.FM a better method to find new music. Granted, the new Player REALLY SUCKS, I used it before they started the new player thing. There is a Proxy being developed which restores the old functionallity more or less.
Oh, that and the Pandora music project is not free:
Q: How much does it cost?
Pandora is available in two forms. Both versions have exactly the same features.
The first form is an advertising-supported version which is entirely free. Over time we'll be incorporating ads into this version of Pandora.
For those who want to steer clear of advertising, subscriptions are available in two different flavors:
ANNUAL: 12 months of unlimited use for $36
QUARTERLY: 3 months of unlimited use for $12
while the last.fm is free unless you want a "personal" radio.
Ubuntu is an African word meaning 'I can't configure Debian'
The site is not responding (big surprise). But from the description it sounds like it is similar to Music-Map.
It appears that giving it a song is a much better fit than giving it a group. Because a group is so diverse in the songs it plays (and the AI is based around the songs), it is really hit or miss... but if you pick a song you like from the group, you'll find a much better match.
Go ahead and try it.
Good quote, too many chars. Seriously, the slashdot 120 char limit sucks!
The Slashdot Genome Project
On November 29, 2005 a group of programmers and tech-loving technologists came together with the idea of creating the most comprehensive analysis of Slashdot stories ever.
Together we set out to capture the essence of stories at the most fundamental level. We ended up assembling literally hundreds of story attributes or "genes" into a very large Slashdot Genome. Taken together these genes capture the unique and magical tech identity of a story - everything from author, source and url, to opinion, bias, trollishness, voice, and of course the rich world of editing and slashvertising. It's not about what a story looks like, or what site they supposedly belong to, or about who reads their stories - it's about what each individual story reads like.
Over the past 5 minutes, we've carefully read the stories of over 10,000 different submitters - ranging from popular to obscure - and analyzed the technical qualities of each story one attribute at a time. This work continues each and every day as we endeavor to include all the great new stuff coming out of basements, offices and garages around the world.
It has been quite an adventure, you could say a little crazy - but now that we've created this extraordinary collection of stoiry analysis, we think we can help be your guide as you explore ways to remove duplicates from Slashdot.
We hope you enjoy the journey.
A.N. Cow-Ard
Founder
The Slashdot Genome Project
and now that I know C a little, maybe I'll try out making a plugin or something..
/right now/.
/would/ go well. (various probability weighting schemes, decreased weight as we move on, requiring much use before it really knows you, blah blah blah...)
I have lots of MP3s. I like most of them. However, I'm not always in the mood for all of them. There is very little music I've dismissed completely as bad, so "Thumbs up" || "Thumbs down" is pretty lame (,stupid, closed-minded, moronic, a horrible basis for anything, encouraging of the already prevailent general-dumbness of people whose music I tend not to be in the mood for, etc)
What I've wanted is a system by which music can be automatically catagorized based not on whether or not I like it, but rather based on whether or not I'm likely to enjoy it
How this would work: Start with the standard "Shuffle", picking at random any song. Then, if I hit "next" right after a song starts, decide "This song doesnt go well with this other song right now", and instead try selecting one which my lack of hitting "next" in the past has indicated
The closest I've seen has been plugins which weight the shuffle based on a rating you choose, which doesnt ever fluxuate.
Point: Playlists should be quaint by now. Why should I need to choose in advance what I'm in the mood to listen to an hour from now?
-- 'The' Lord and Master Bitman On High, Master Of All
Click on the downturned triangle on your station after you add the first artist, and it'll let you add as many other artists as you want. Not Rachmaninov though, they haven't done Classical yet.
Sue them!!
-- RIAA
(the funny/scary part is that it's not far fetched to me that they actually will, for being too accurate in handing out music a user wants to listen to)
Beware: In C++, your friends can see your privates!
I have been a happy (and donating) user of Last FM formerly Audioscrobbler. They do a really good job of matching up music tastes and their radio program is good. They also have a plugin that allows you to submit what you play from most major audio players so you can track what you listen to and compare with others. They have full tagging capabilities and extensive forums as well as music 'groups' of like minded appreciators. I have been very impressed and I admit I haven't played with Pandora much but it doesn't seem too much better/different.
Frist post!
I think that you'll have to ask Senator Frist a little more nicely than that...
http://www.liveplasma.com/ (Flash application)
I believe this is the company that does the related stories matrix on news.com.com.
Also, in my case Pandora chose a song off the Opeth album "Damnation", which happens to be a much more laid-back album that contains mostly folksy ballads and absolutely no heavy metal whatsoever. So when Pandora attempted to find similar bands based on that one song, obviously the selections weren't at all what I had in mind. I couldn't figure out how to get the thing to choose a different song - it seemed locked in on that first one.
At any rate, I remember the first article speaking derisively of the "user recommendations" at Amazon. Yeah, they often suck, but I've discovered some great music there too. I never would have known about a great band called Porcupine Tree if Amazon hadn't recommended them to me as a fan of Opeth, for no other reason than the fact that Porcupine Tree's singer/songwriter/guitarist/etc. produced a few Opeth albums.
...a combination of the iTunes store (trying without buying) and www.pitchforkmedia.com to hunt for new music. Pitchfork has a few recommended albums every month, I'll look them up on iTunes, and often iTunes itself has suggestions for other artists I'll like. It's been spot on so far and has let me to some great discoveries.
I've been using Pandora for a while now. Although sometimes it misses badly, it generally gives you bands or songs similar on their 400 qualities. It does not go by genre, it goes by stuff like 'tone progression', 'emphasis on studio production', 'melody', etc. It does NOT go by genre or label. I've discovered some good artists with this thing.
TIP: When you hit the max songs per hour limit, just start a new 'station' with another band/song you like or that was already listed.
As someone who has read enough books on music to know what they are talking about when they say 'We chose this song because it features x and y', I can honestly say this doesn't mean much. I think genre and statistical comparisons between users has a far greater impact on what songs it chooses than what they suggest in their FAQ/info pages.
The whole idea of analyzing a song for different qualities is great, but it really doesn't get you very far with something like this. I can think of a million songs with 'Mild rhythmatic syncopation' and 'Major key tonality' (just an example of the reasons it told me it was playing a song), and I would probably only like a small portion of them. I suspect that the genre of my song (eg 'Hard rock roots' or 'punk roots' etc) is the biggest deciding factor in what it plays -- not the actual style of the song.
CmdrTaco, we all know the MGP doesnt lie. You should just admit there is a little Styx and Def Leppard in each and every one of us. The object is to suppress this tendency and desire lest loved ones get hurt by it.
I think you underestimate just how much I just dont care.
oh my god, they linked to an online radio. isn't anything sacred anymore? ...thankfully its flash based so most of the comments will be how none can hear it because they don't have open source plugins and they will not loose that many bandwith
I put in Kimya Dawson, Hank Williams, Public Enemy, Blue Oyster Cult, and then my machine crashed.
Makes sense.
I always dug Audioscrobbler for social recommendations, I guess it's operating as Last.fm now.
I am skeptical of any algorithm that purports to gauge or classify taste. People listen to music for complicated reasons and they often listen to very different genres.
A better solution is to point people to "taste-makers".
I found by illegally downloading music using limewire, that I could find very interesting new music by simply broswing the collections of the people that were downloading from me. That really opened up my horizons as far as taste is concerned. I don't think an algorithm could come close to that.
Does anyone know where you can find the technical details of any of these systems? I'd like to know how they're representing their knowledge and how they're doing their reasoning (a.k.a. song selection).
I've done some work in knowledge representation using the OLW specifications from the W3C and the Racer reasoning engine, but I had never thought of applying it to music. As a music buff and computer geek, the application of knowledge modeling to music seems a natural fit to me, and I'd love some pointers to any ongoing research in this area or thoughts on future directions for this technology.
Oh yea, and if anyone wants to front a couple million for me to form a startup that would be cool too. I know several bright people who could really dig into something like this.
anyone have problems getting pandora to output sound on your linux computer? I've got Fedora core 3 and I don't hear anything (although xmms works fine /w arts).
It's nice because it exposes you to new music. The problem is that most music isn't that good, even it's similar to music you like. I still use it even though it didn't live up to my expectations.
It's also interesting the way it describes the music you like. I like music with minor tonalities, varying time signatures, dirty guitar riffs and an emphasis on production (metal).
try out http://www.musicplasma.com./
It has an interesting [flash based] visulisation engine that shows associations between artists and their peers. The interface is reasonably nice and quick to use. It seems if you create an account then you can create your own maps and recommendations.
The bikini - security through obscurity since 1943
If you couple the plain annoyance from seeing a story duped and the slashdoting that is going to inevitably occur, this dupe really pisses me off. I'm a subscriber to Pandora and as soon as one slashdotting is over, then it gets digged. Then digged again, then slashdoted once more.
Enough with the dupes already! I'm looking at YOU slashdot and digg. I want to listen to my music in peace!
All Music does a pretty good job of classifying artists
You have the tastes of an ogre.
[Throws computer into swamp]
Well, there's spam egg sausage and spam, that's not got much spam in it.
You know, most of the media world is pretty excited about these concepts of "personalized media"... where the media that is presented to you is based on the types of things that you already like (it's just starting to take off in music, but watch for it in the future in television, movies, and internet sites). But I see this as somewhat of a problem, where people are never exposed to new things. If everything in our world is personalized and created specifically for our tastes, how do we define our tastes? When do we ever get a chance to listen to something we don't like, and say that we don't like it? Or listen to new things we've never heard of, and that may not be in any way related to our database of media we like, and say we like it?
The situation presents us with two possibilities: either we get pidgeonholed into a "genre" artificially created by the content distributors (as broad or narrow as that genre might be), or our tastes enter a feedback loop, where the only things we listen to are the things our personalized media players play for us, whose choices are based on things we listen to in our personalized media players.
So where do we get outside input? My suggestion at this point would be to do away with artificial genres and create relationships between media based purely on a database of what people like and don't like. (Last.FM does this now.) Then I would like to see the media player throw in a randomly chosen selection once in a while, just to test its own theory, so to speak. However, for that to work, the selection would have to be truly random; no fair throwing in something that you are marketing heavily (I'm talking to you, [RI|MP]AA...) just to get people to hear it. So instead of choosing music based only on your tastes, your media player will choose music based *mostly* on your tastes, and then throw you a curve ball once in a while to see how you react. Who knows? Maybe that diehard punk fan would enjoy a Beethoven piece or a 70's pop song. But the media player would never know that unless it tried.
For security, the MD5 hash of this message and sig is 09f911029d74e35bd84156c5635688c0.
how is this different from gnod, other than having some bizzare split basic-free/premium-pay_for_service model instead of being free?
Launchcast (now Yahoo Music) has been doing this for several years already. So what?
I prefer audioscrobbler.com (not for those afraid of having stuff logged).
:P
It has a small opensource client which runs in lots of mp3 players, it sends the info of the songs to their database giving you a massive list of which songs you listen to etc etc and reccomends more etc.
Awesome stuff
www.audioscrobbler.com/user/djsmiley2k
- http://www.milkme.co.uk
Thought I'd weigh in with a "this sucks" rating. I put in the first popular artist that came to mind - the Barenaked Ladies - and it seems that they are the only band in this thing's database that I like in that genre. I assumed the programming would move through genres with my selections, but all it did was annoy me with more crappy artists - often three or more times with the same artists. It should be adaptive enough to see that if I negatively rate an artist twice, that perhaps I dislike that artist. This isn't adaptive at all. It is simply "choose a genre" and cycle through random songs. And in agreement with some posts here, I feel that attempting to boil down music into certain elements such as the tempo, volume, attitude and instruments used is unfair to artists. There are so many different factors, I greatly doubt the effectiveness of attempting to classify music in such descript and specific terms. Well wasn't this a dandy for my first post >.>
Any idea what progress has been made on this music genome project? How well 'sequenced' is this (ever growing) genome? The blurb kind of indicates that they've reached an end of analysing.
The first (and my favourite) artist I typed in couldn't be found. It might just be that I have an obscure taste, of course.
This isnt the kind of music genome project i want to see. Basically the traits which are analysed are highly subjective and if you listen to a lot of one particular genre of music (particularly smaller genres) you are almost certainly going to be more qualified to judge the supposed traits than the experts. To me it seems they essentially lumped all of heavy metal together leading me to getting results like megadeth with a seed of tool despite the two artists not sounding similar at all.
I'd prefer to see a project which tries to create an analytic genome for each song, I've been thinking about if it would be possible to do something like compare FFTs of segments of the song, sam 2 second frames throughout the track. If these could be encoded in some kind of relative way you're likely to get music that has similar characteristics. Further its entirely objective.
However from what i remember they're experts are all from Nashville so if your into country music your probably gonna get some pretty decent results.
I have discovered a truly remarkable sig which this post is too small to contain.
I want to give it a variety of what I listen to, and have it offer suggestions from all those categories, mixed up together. For instance, my main favorites are 90s alt rock groups, Smashing Pumpkins, Nirvana, Weezer, Rancid, Metallica, Reel Big Fish (heck even in that group there's a bunch of variety) come to mind. But I also listen to hiphop/rap (lately it seems I'm on an old-school kick, but some of the eclectic newer stuff is good, too). I'll also listen to country and the occasional techno. I want new or unheard of music in all of those genres without having to track down each one separately. I want to seed it with say, 50 (100?) songs, and have it base it on that. I don't really want to listen to all of my music that is based on a single song. Just my $.02.
Do not open the site
I have diversified tastes. The Who and Nickel Creek don't have much in common.
Add enough different bands, and you get "we chose this for mixed instrumentation in a major key."
Which leads to Backstreet Boys.
What they need is several categories with a randomized selection from your multiple tastes.
Design for Use, not Construction!
Slashdot mentioned Pandora in October and linked to a good article in the WSJ that explains Pandora.
I came across this yesterday (I forget how), and it's actually pretty cool. I didn't spend a lot of time using it, but I picked two bands that I liked, and out of the eight or nine songs that it played, there was only one I didn't like.
I agree that the rating system needs more refinement, but this seems to be a stage 1 product. The sound quality was really good, the interface is nice (if not a little Flash-bloated), and the music collection seems pretty extensive. I'd like to see how it progresses in the coming months (the page said it's going to start placing ads soon... whether they're audio ads or banner ads, we'll have to wait and see). However it may be a new contender for dethroning Launchcast as my favorite internet radio station.
Slashdot: News for nerds. Stuff tha-- MICRO$OFT IS THE DEVIL!!1
I've blogged about it here:
http://www.peterbe.com/plog/pandora
home http://www.peterbe.com/
Yahoo Launchcast premium does something similar. For your personalized radio station, based on your ratings of songs, artist and album it plays music you've already selected or is selected by other users whose selections overlap yours. Works fairly well once you done something like 200+ ratings, except that it uses DirectX and so requires me to run windows and IE. The pandora player mentioned doesn't seem to work with firefox, it just shows a blank portion of the screen.
Basically what you are saying is that they are lying about how they choose songs. But why would they do that? If they were using social networking or grouping by genre, and it worked, why wouldn't they say so?
Furthermore I haven't seen anything that would lead me to think that they are grouping things like you claim. Try typing in a band like Ween. You won't get anything that is remotely related by genre or popular tastes at all.
One of the biggest things that I like about this site is that it does play different artists than I find with other systems that determine thier suggestions by genre or social linking (people who liked A liked B), and I have liked many of them.
I can think of a million songs with 'Mild rhythmatic syncopation' and 'Major key tonality' (just an example of the reasons it told me it was playing a song), and I would probably only like a small portion of them.
They are rating on hundreds of different factors. The fact that two songs are related by just one of those factors would not cause it to be played. It is the fact that it is related on a large number of those factors. And it isn't surprising that music within a genre share many traits with each other.
I suspect that the genre of my song (eg 'Hard rock roots' or 'punk roots' etc) is the biggest deciding factor in what it plays -- not the actual style of the song.
Again I don't see any reason to think this. I have found it rare for it to only play music within a specific genre, and to the extent that it did, the songs were all musically simular.
What I haven't yet seen is anyone who actually seem to have tried it out and seen what they think. Fortunately this is probably because all the asshats have posted first, and the actual people that are trying it will post 20-30 mins later as they've listened to a few songs. But jesus, its like watching a train wreck here so far.
Hey, I'm a Bushie and just the other day I told a gay friend I envied him. It's getting so I can't stand women anymore. Plus, I have several friends who are Canadian. Generalizations are almost as bad as using the Reply to All button in a workplace with a thousand people.
Someone save me from this sanity.
Yeah, that does it. You are gay. Must've posed for the goatse picture, you must have.
Surely you must have been joking?
He who knows best knows how little he knows. - Thomas Jefferson
psst - just a little hint - I'm one of those "commie liberal-socialist pinko canucks" I was poking fun at :-)
And if you really want to encourage innovation and sock it to the RIAA, start listening to the local bands. In a decent-sized city, it's not hard to find some group performing in local venues who fits your musical preferences. Most sell their own CDs too. I've found some really gems in these bands and I know that my money is going towards someone local.
Another place to look for CDs of local bands are in your music shops. Not the places that sell CDs, but the ones that sell the instruments. Frequently, the counter will have CDs from several local bands available for purchase.
This sig has absolutely no significance and serves only to take up screen space and waste the time of the reader.
I haven't tried out Last.FM, yet. I'll have to do that when I get home - I always love finding new places to discover music.
:)
However, I have been running out of luck with social networking type music recomendations lately, because they tend to just recomend music that I already know about from word of mouth (online and off). So I like Pandora, simply because it is different. The fact that it uses a different approach to link music means that I get exposed to different bands then I do using other avenues.
Of course, if I didn't like any of this different music then it wouldn't be very usefull. But in the last several weeks since I started using it Pandora has been decent at finding music that I might like. It isn't perfect, but I don't think any algorithm could possibly predict what a person will and wont like. It is better than chance. It is better than digging through music at the local record store, or online, and much less work
In time, Pandora will probably start running thin on new recommendations, as I use it more. Any of these algorithms probably has it limitations. Having several sucessfull ones is great, and very welcomed.
I find that its kinda like 6 degrees. Listen to any song and in an hour its playing house music.
Yeah, while I don't appreciate all choices (technically, two quite disparate songs might share a lot of characteristics) I do appreciate most of them, and there are lots of bands I've never heard of ("The Vaselines"?) who apparently make music that appeals to me. As long as they keep this honest it's a great way to learn more about smaller bands.
The "Buy this song from iTunes" link is also a great idea, which I hope generates a lot of revenue for them.
The Pandora app was written using OpenLaszlo ( http://www.openlaszlo.org/ ), a free software rich internet application development platform. Why do you suppose they did that instead of using Macromedia's tools and runtime?
You hit the nail on the head. While Pandora's approach has some nice properties, their major drawback in comparison to Last.FM is that they need to invest a lot of manual work, and that they have no equivalent to Last.FM's "fluidity" of content (i.e., Last.FM's measurement of similarity changes with the behavior of its users).
p andora/ for a review and comparison.
See http://dekstop.de/weblog/2005/08/pandora/ for a more detailed description of this aspect, and http://dekstop.de/weblog/2005/08/a_first_look_at_
I've been using it for the last few months and I like it. The only minor compliant I have is the library is a bit small at the moment. So far pandora seems pretty responsive to feedback. I sent several suggestions and got a response from pandora. I hope their library continues to grow.
I have been a Pandora user from the early days of the service and I love it. The price is fantastic and I actually like that they are adding a free, ad-supported service for those who can't afford it; but, it is cheap. Keeping the stations in tune with a style is a breeze and I love being able to say "Hey, this song is cool. What else is there like it?" I picked up an old record of "The Ventures" at a garage sale, and now I have a station playing late-50's and 60's beach music type stuff and songs along the lines of the old batman themesong. Of course, having the founder of Pandora comment on my blog when I posted about Pandora was cool, as was the e-mail from the CTO I got, thanking me for my early adoption of Pandora and upgrading me, free of charge, from a quarterly account to a yearly. Nine months for free, now. This really is a sweetspot.
Question
http://www.ironfroggy.com/
...where's the pony?
It's better than LAST.FM in that it plays under Windows 98, ME. It ticks me off that on lower end PCs I can's access the Last.FM radio. Also I think this works different to Last.FM in that it seeks similar music, and not similar tastes in music. (I think Last.FM suggests tracks like Amazon suggests products). I hope they add more \m/374l songs.
Also, the personalization algorithms don't even really represent your own tastes all that accurately, at least, not until they've built up a considerable database about you.
For example, at one point in time or another, I bought some Star Wars-related product from Amazon.com. This was years ago. But to this day, every time I go to Amazon.com, they are recommending me the latest Star Wars novel or toy or DVD bonus package or what-have-you. Just what is it about my buying habits that makes them think I like Star Wars that much?
Not to mention the fact that my Amazon.com purchasing habits don't necessarily represent my purchasing habits as a whole. It's funny; I probably buy a ton more books than I do Star Wars DVDs. The thing is, I don't really like to order my books through the Web. I prefer to wander down to my local independent bookstore on my lunch break, thumb through the pages a bit, smell the paper, and then proceed to buy the books at the checkout counter using my 10 percent discount card.
As a result, Amazon, which by all rights should know exactly what my purchasing habits are, doesn't actually have the slightest idea.
Likewise, my iTunes (or Windows Media Player or whatever) probably doesn't have the absolute best idea of what music I listen to. Yes, the music I play on iTunes is probably music that I legitimately like. But it's also music that I downloaded. I do legitimately rip my own CDs to MP3 format, but I do that for my portable player, not to listen to at home when I have the original disc sitting right there. So if you were using iTunes to judge my preferences, you'd only really know about the music that I think is kinda catchy, but either I don't feel like paying for or else is too obscure for me to be able to track down and buy. You wouldn't know about any of the stuff that I liked enough to drop $18 on.
Breakfast served all day!
Why, unlike Last.fm, is it only available to residents of the USA? The internet is global, so should such a good idea not be usable wherever you happen to live?
Just Minimize or Bring Back The Music Player I wonder if anyone has mined Gebraltar (gepr.net) or Gnosis (gnosis2000.net) and produced webs like music-map does? Feed that back into Pandora, that would be interesting!
"Can there be a Klein bottle that is an efficient and effective beer pitcher?"
I tried it after the last slashdot post, using only songs, not bands. Bands don't work, songs do. I found that:
1. It introduced me to a number of new bands, and obscure songs by familiar bands, that I really liked.
2. It played some stuff that was bad, and I just skipped it, or told it I hated it.
3. It did not have an extensive enough library -- there were songs I couldn't base a station on, and there were limited songs in the set played, so that when I came back the next day I got the same songs.
4. Sometimes the similarity in sound is uncanny -- piano or guitar riffs, syncopation rhythms, etc.
5. I will use this for as long as I can get it.
6. SUBJECTIVE OPINION: I am a musically-jaded late-60s early 70's blues-rock-by-classically-trained-musicians fan; I have grown tired of the old stuff and have rarely heard new stuff of anywhere near the caliber of Tull, Led Zep, Yes, the Who, Jeff Beck, Allman Brothers, pre-Nicks Fleetwood Mac, etc. (TMBG and NRBQ excepted); As a result, I have not been very interested in listening to music for the last 20 years; Pandora has rekindled my love of music.
"Debugging" by Dave Agans - the perfect gift for your favorite imperfect engineer.
I have the Pandora service and have had mixed results when looking for electronic music. It tends to gravitate towards techno.
If you're looking for electronic music, I recommend the "digitally imported" radio service, related to Ishkur's guide to Electronic music
http://www.di.fm/edmguide/edmguide.html
So THAT'S why it's running so darn slowly this morning! Amazing.
I know someone who worked on this, actually. They're using the brute force approach; they built a massive database of musical analysis for each track by musically-trained folks. My friend was a music (and political science) major.
Something closer to Amazon's buyer suggestion database (which is what Last.FM sounds like) might work better.. but this seems like a truer association of musical content
I did. I don't want to play in that arena.
The tell you up front that they will install software ('plug-ins') on your computer. That they will share what they know about you with 'trusted partners'. That they e-pend what they can find from others about you.
No thanks.
you should try IMMS, I think it does exactly what you want.
it has no interface other than the player's next/prev and playlist, and is fairly easy to port in case your player isn't supported
(there's only a small plugin that needs porting, currently supports XMMS and BMP)
I don't think I'll take the test for a couple of reasons. First, what if it tells me that I like Xtina? That's like taking a DNA test and being told that I will definitely develop inoperable brain cancer. I don't want to know that. Second, how am I supposed to break my mold and hear other new things if it will help feed me similar stuff?
Contact Gillware for all your Data Recovery Needs! Data Recovery
ISTM that it's how the different attributes of a song interact together that gives it a 'flavor' that appeals to me. My tastes are very eclectic, ranging from swing to jazz to 60's/hard/acid/psychedelic/soft/(etc.) rock to disco to grunge to pop to.... as long as a song is exceptional.
What kind of algorithm can they come up with to give me that?
'Intellectual Properties' are uncontrollable in the wild. To base an economy on them is just stupid.
For what it's worth, I listen to a lot of modal music, most of which is considerably closer to minor than major, but Pandora seems to want to say in many cases (even Aeolian -- equivalent to natural minor) that such songs have "Major key tonality." Is this being determined by some tin-eared reviewer or is their software confused?
Peace and love, y'all
I havent tried it yet, but from reading the site it seems to actually be exactly what is wanted. Or at least, close enough that it can be latched on to as a good place to start wild schemes.
Just adds more evidence to the theory that "Anything I could come up with really is such an obvious idea that there's no reason to expect somebody else hasnt already accomplished it", hence the phrasing of my original post.
Now where's that Instantaneous Floppy Drive and Vertically-Oriented Arbitrarily Groupable Timeline Creator?
(note: Link seemed to be broken when I clicked it, here is google result: http://www.luminal.org/wiki/index.php/IMMS/IMMS )
-- 'The' Lord and Master Bitman On High, Master Of All
I went to a talk a while ago about automatic music clustering. Basically, the researchers got a bunch of MIDIs — some classical, some pop, some jazz — cleaned them up a bit, and then used bzip2 to test them for similarity:
From memory, to test two pieces A and B, you concatenate the files to produce AA, AB, BA, and BB. Then use bzip2 to compress each concatenation. We expect AA and BB to compress well (because there are obviously big areas of similarity). If AB and BA also compress fairly well, then A and B are "close". Otherwise, they aren't. I forget what exact computation was used, but it was pretty simple.
Here's an arciel I found on the topic: http://www.ercim.org/publication/Ercim_News/enw54/ vitanyi.html.
I thought about doing that with mp3 — take two uncompressed audio files, join them together, compress with lame — but it didn't work; I think this is because mp3 is too local and unable to take advantage of bigger structures in the audio (which is obviously a design goal because you need to be able to decode on the fly).
Interesting stuff, though..
Repton.
They say that only an experienced wizard can do the tengu shuffle.
"So you like the Stones?"
"I'm not really into classic rock."
"Oh, I see, a Zeppelin man.. That's cool."
"..."
"You'd probably like Floyd then!"
https://www.eff.org/https-everywhere
You quoted the website but missed the most important part of your argument
-The first form is an advertising-supported version which is entirely free. Over time we'll be incorporating ads into this version of Pandora.-
They have the paid version without ads, and the free version with ads. Both have the same features.
What I find that Pandora is not good at is filtering out what elements make songs different. I started a station based off the group Dead Can Dance (lots of world music influence, glossolalic vocals, interesting instrumentation) and it suggested a track by the Dave Matthews Band. Based on their analyses of the songs I can see how they might be related, but the reasons most people listen to DCD would be unlikely to make them want to listen to DMB. They Genome project says that they're trying to transcend the barriers of genre, but they're ignoring style and aesthetic, which make up a lot of music's appeal.
For those using unix, the files are cached to /tmp/plugtmp/access*
If you wanted to copy them to say... ~/pandora you could then make that your working directory and:
#!/bin/sh
for i in `ls`; do mv $i $i".mp3"; done
which will set your extensions... quick and dirty, but hey we're not keeping these songs, r-i-g-h-t-?
Be who you are and say what you feel, because those who mind don't matter and those who matter don't mind. - Dr. Seuss
This is an other point for those who want to run this in a *nix environment... Since the applet runs at the same priority as Firefox, it get's a little skippy when Firefox does, well, just about anything... If you want to listen without the skipping, you could do this:
sudo -H nice --adjustment=-19 firefox
and use that instance of firefox only for Pandora... this should prevent most or, hopefilly, all skipping.
Be who you are and say what you feel, because those who mind don't matter and those who matter don't mind. - Dr. Seuss
After experiemnting with Pandora for a while I noticed something. IMHO it appears to be 'leading' the user toward more mainstream music, which sounds like the stuff their sponsors are trying to sell. As I explored the offerings, the more I accepted, I found myself further from the Songs/Groups that sounded like what I was interested in. A couple of quick Thumbs Down would bring me right back on track, for a song or two. YMMV
"Can there be a Klein bottle that is an efficient and effective beer pitcher?"