Slashdot Mirror

← Back to Stories (view on slashdot.org)

Google's 'Project Magenta' Art Machine Composes Its First Song (thenextweb.com)

Posted by BeauHD on from the auto-tune dept.

An anonymous reader writes: Google's Project Magenta, which aims to use machine learning to create music and art, just created its first song. The song, which can be more appropriately described as a 90-second melody, is quite simplistic and reminiscent of an old Nokia ringtone. It's impressive for a machine! Magenta is built on top of its TensorFlow system, and all the open-sourced materials one could ever need are available through its Github. The team wants to be able to tell stories from the art it creates similar to that of artists. "The design of models that learn to construct long narrative arcs is important not only for music and art generation, but also areas like language modeling, where it remains a challenge to carry meaning even across a long paragraph, much less whole stories," the team wrote. "Attention models like the Show, Attend and Tell point to one promising direction, but this remains a very challenging task."

72 comments

  1. Horrible state of music theory. by Anonymous Coward · · Score: 0

    Wouldn't you need a proper formal music theory before you could programmatically have something work effectively on the medium of music? Go back to Helmholtz.

    1. Re:Horrible state of music theory. by Anonymous Coward · · Score: 0

      The thing that bugs me most about this site is that comments like yours are downvoted. I click these bullshit articles just to read the astute observations, and instead am greeted with upvoted word salads from dumbshits who think they're 'futurists'.

    2. Re:Horrible state of music theory. by thinkwaitfast · · Score: 1

      True, but the future is word salad. People will no longer have the capability of critical thought and sentences will be judged not upon the ideas the are trying to convey, bt on how they sound. Eg, you talk like a fag.

    3. Re: Horrible state of music theory. by Anonymous Coward · · Score: 0

      There are a lot of musicians and song writers that do not know formal music theory, so no. It's more about recognising patterns within existing music and then creating something unique with similar patterns that sounds pleasing within a particular palette (e.g. pop as opposed to 12 tone serial). Over the years there has been much reuse if chord sequences, not least I IV V.

    4. Re: Horrible state of music theory. by Anonymous Coward · · Score: 0

      Great explanation. Although I haven't looked into this stuff too deeply I guess this is pretty much what Google did. Neural networks are great at finding and extracting patterns, right? So the art is to make them process those patterns in a way that sounds good to humans which can probably be done via standard neural network training.

  2. I wonder by johnsmithperson123 · · Score: 3, Interesting

    If we could use deep learning to let computers learn styles and patterns, eventually incorporating them into new music. It could usher in a new era where every film is composed by John Williams, or Mahler's tenth is finished, or there's a new Bach and Beethoven being made every day. Of course, on the arguably darker side, pop music could become entirely computer designed, although considering the quality it would actually sound better if done by computer.

    1. Re:I wonder by Anonymous Coward · · Score: 0

      Think of the boy bands!

    2. Re:I wonder by Anonymous Coward · · Score: 1

      No, you can't until you have a proper music theory. Otherwise, surely, we would be able to reproduce Bach and Beethoven with the mass amount of mental effort we already have available. Remember, artificial intelligence works like normal intelligence. If it isn't possible using normal intelligence, how is it going to be possible using artificial intelligence? Artificial intelligence might be able to speed it up, but what makes art meaningful is that it *relates*, and that is not a "trainable" thing. And even if it could be, why bother using anything other than a human who already is trained in the human condition? Don't get me wrong, I am all about advancing music theory formally, but that is about understanding the medium, not about the *creative* aspects.

    3. Re:I wonder by Anonymous Coward · · Score: 0

      Pop music is already "designed" by the algorithm of "how little effort can we put into making real music," so I doubt that much would change. However, one must wonder how different the world would be without such affronts to humanity as Beiber, Spice Girls, Deon, Leon, Spike, West, and The Kardashians.

    4. Re: I wonder by Namarrgon · · Score: 1

      Check out David Cope's work. He deconstructed Bach's music into an underlying grammatical theory, generalised it to other composers, then built EMI, a program to analyze music for stylistic patterns, then to use his musical grammar to create a full composition in that style. Later he wrote Emily Howell, which can do grammar-based compositions in its own synthesised style. You might be surprised how good the pieces are.

      Google is taking a very different approach, and time will tell how successful it will be. Clearly it's not yet up to other work in algorithmic music, but given their notable recent successes in intuitive computing fields like Go, I will be watching developments eagerly.

      --
      Why would anyone engrave "Elbereth"?
    5. Re:I wonder by kheldan · · Score: 3, Insightful

      Remember, artificial intelligence works like normal intelligence but only in fantasy and science fiction novels, we don't have real 'AI' in the real world.

      Fixed that for you.

      We don't even really have a clue how our own brains work yet, let alone being able to even begin to emulate it with a machine. All we have right now are cheesy imitations that fall way, way short of the mark.

      Don't anyone sit there and try to convince me that some cheesy algorithm is going to totally emulate human master composers because that's total and complete bullshit. Until we have fully human-level artificial intelligence, completely self-aware, with a full complement of human-level emotion and imagination, there won't be any machine-generated art of music that is equivalent to new works by human artists or human composers. Period.

      --
      Are YOU using the TOOL, or is the TOOL using YOU? Think about it!
    6. Re:I wonder by Lotana · · Score: 1

      I disagree with you that music composition needs strong AI.

      Music composition is a narrow area with relatively well-defined inputs and outputs. Weak AI thrives under such small subsets of real world. Also in terms of music, there are so many varied opinions on what level of quality is acceptable or indeed sublime. While the track in the article obviously does not meet your standard, I am sure there is at least someone out there that enjoyed listening to that tune. I can think of several examples of "music" that I would consider much more irritating than the one presented in the article.

      Also even in completely original works there are patterns. As Stravinsky put it "Antonio Vivaldi did not write 400 concertos; he wrote one concerto 400 times." And if there are patterns, then that is something that AI can learn from.

      A great composer is not just born. And if a human can be taught, why not an algorithm be made that focuses only on that particular narrow area? Why is a skill of music composition so much more magical than looking for patterns on the Go board?

    7. Re:I wonder by ultranova · · Score: 2

      Don't anyone sit there and try to convince me that some cheesy algorithm is going to totally emulate human master composers because that's total and complete bullshit.

      Well, either the composer's brains work by magic or they can be emulated by some kind of machine.

      Until we have fully human-level artificial intelligence, completely self-aware, with a full complement of human-level emotion and imagination, there won't be any machine-generated art of music that is equivalent to new works by human artists or human composers. Period.

      Human beings, and thus human composers, aren't completely self-aware. One of the main weaknessess of human brain is precisely that it lacks general introspection facilities - or "debugger", if you prefer.

      --

      Forget magic. Any technology distinguishable from divine power is insufficiently advanced.

    8. Re: I wonder by AthanasiusKircher · · Score: 1

      Check out David Cope's work. He deconstructed Bach's music into an underlying grammatical theory, generalised it to other composers, then built EMI, a program to analyze music for stylistic patterns, then to use his musical grammar to create a full composition in that style. Later he wrote Emily Howell, which can do grammar-based compositions in its own synthesised style. You might be surprised how good the pieces are.

      Almost every sentence here is misleading or wrong. Cope didn't build an "underlying grammatical theory" from Bach or anyone else. He basically built a program that pulled out patterns from a specific repertoire (Bach chorales, Mozart sonatas, Chopin Mazurkas, etc.). Then he would have his program "generate" hundreds of "new compositions" that sound like rearranged bits of old works. Then he'd select the best few out of those hundreds of nonsense compositions and showcase them to audiences as new computer "intelligence" as a "composer."

      Seriously -- I understand why these things would sound reasonable to a non-expert. But if you were a university music major in an upper-level course and were asked to write a Mazurka in the style of Chopin and brought in something like Cope's works, your work would be torn to shreds by a competent composition teacher for being unidiomatic and sounding like a weird ungrammatical mashup of preexisting Chopin.

      By the way, none of this is meant as a criticism of Cope's work. I'm a big admirer of what he did accomplish and the kind of things he tried. But the claim that his programs produced "original compositions" in the style of X has always been overblown, especially given how he'd select the best exemplars out of the nonsense the programs generally spit out.

      His most interesting work was actually in the programs that tried to be more " free form" and less imitative of a particular composer or style. I wish he had spent more time focusing on that.

    9. Re:I wonder by phantomfive · · Score: 1

      Music composition is a narrow area with relatively well-defined inputs and outputs

      That's like saying, "English is easy, there are only 26 possible outputs and 26 possible inputs." Not exactly.......

      --
      "First they came for the slanderers and i said nothing."
    10. Re:I wonder by phantomfive · · Score: 1

      No, you can't until you have a proper music theory.

      What is wrong with the music theory we have? What parts are missing?

      --
      "First they came for the slanderers and i said nothing."
    11. Re: I wonder by Namarrgon · · Score: 1

      Do you have any sources I can follow up? I'm just going on the various popular reports of his work from the last few years, most of which more or less say what I said. I know there has been a pretty wide range of reactions from musicians though; certainly some disliked his work, even getting angry.

      I'm no musical expert myself though, so I'm interested in learning more specific details and criticisms.

      --
      Why would anyone engrave "Elbereth"?
    12. Re:I wonder by just+another+AC · · Score: 1

      Music composition is a narrow area with relatively well-defined inputs and outputs

      That's like saying, "English is easy, there are only 26 possible outputs and 26 possible inputs." Not exactly.......

      Reducto ad absurdum.

      I would not have said music differs as much in possible inputs and outputs as the board game Go. The obvious BIG difference is the lack of objective measurements of "success" to evaluate positions against (as humans can't agree what is good music - many like pop and cant appreciate classical, vice versa, and so on for other styles), and the success also equates to more than the sum of the individual notes (ie how smaller pieces fit against wider song).

    13. Re: I wonder by just+another+AC · · Score: 1

      Posts like this give me hope for slashdot (and the future of humanity in general).

      OP posted what he had read
      A post then comes in with informative (or seemingly from layman's point) post discrediting / correcting OP
      OP asks for his sources so that he may be better informed.

      No name calling, no defensiveness, just open dialog to share knowledge.

      Cue next thread where people call each other shills or sjw or other in-vogue petty insults

    14. Re:I wonder by kheldan · · Score: 1

      Well, either the composer's brains work by magic or they can be emulated by some kind of machine.

      NO. You're missing the fundamental point: We do not understand how the human brain does what it does yet, not even close, and without that fundamental understanding you CANNOT build a machine or write mere software that duplicates it's fuinctionality. They write clever mimicks that only go so far but fall way, WAY short of the mark. There is a hard limit to this until we fully, completely understand how our own brains work. Stop buying into all the hype.

      --
      Are YOU using the TOOL, or is the TOOL using YOU? Think about it!
    15. Re:I wonder by phantomfive · · Score: 1

      Reducto ad absurdum.

      The original assertion was absurd, man.

      --
      "First they came for the slanderers and i said nothing."
    16. Re:I wonder by Anonymous Coward · · Score: 0

      Machine learning and AI techniques have been utilized in algorithmic composition for decades.

      And yes, there's many papers that train their algorithmic composition systems on a particular composer/genre/style.

    17. Re: I wonder by Anonymous Coward · · Score: 0

      Just search for papers on "algorithmic composition," this has been a popular field of research for the typical engineer-musician type for decades now.

    18. Re:I wonder by ultranova · · Score: 1

      You're missing the fundamental point: We do not understand how the human brain does what it does yet, not even close, and without that fundamental understanding you CANNOT build a machine or write mere software that duplicates it's fuinctionality.

      And yet we have made machines which play chess.

      They write clever mimicks that only go so far but fall way, WAY short of the mark.

      What mark would that be? Human-level ability? Our chess machines are already at the point of beating world champions. 10x human ability? 100x?

      There is a hard limit to this until we fully, completely understand how our own brains work.

      That doesn't seem to be the case. What our brains excel at is energy and space efficiency, but that's not really relevant for an immobile AI machine fed from the mains power.

      Stop buying into all the hype.

      Stop being emotional about this. Machines are already superior to humans in physical abilities (as are many animals). There's no reason to assume they won't become superior in intellectual abilities as well. The solution is to stop buying into the lie that human value comes from abilities and usefulness - in other words, abandon the ideal of meritocracy and embrace the ideal of equality of outcome. The alternative is that we're all fucked since machines outperform us at everything and require no pay.

      --

      Forget magic. Any technology distinguishable from divine power is insufficiently advanced.

    19. Re:I wonder by nikkipolya · · Score: 1

      Have you see the "Continuator" program perform? Or the "Painting Fool" perform? Both were covered here on slashdot a couple of years ago.

    20. Re:I wonder by adminsam · · Score: 1

      If we could use deep learning to let computers learn styles and patterns, eventually incorporating them into new music. It could usher in a new era where every film is composed by John Williams, or Mahler's tenth is finished, or there's a new Bach and Beethoven being made every day. Of course, on the arguably darker side, pop music could become entirely computer designed, although considering the quality it would actually sound better if done by computer.

      http://mp3songsringtone.in/

  3. first song by Anonymous Coward · · Score: 0

    The lyrics went something like this: ...never gonna give you up....never gonna let you downn.... ...never gonna run around, and desert you.

  4. It's a bit pants by Anonymous Coward · · Score: 0

    Maybe someone at Google should tell it that pianists often have more then one finger?

  5. Painful by davide+marney · · Score: 1

    Hey, "deep learning" is all about pattern-matching, and what is music except a bunch of patterns! Let's have machines repeat back the patterns we use! Look -- it's artificial intelligence!

    *sigh*

    Yes, music IS just a bunch of patterns: patterns that evoke very specific emotions. You can't just string 'em together like popcorn, they go together for a reason. Listening to this is just painful, like watching a person try to walk on a broken leg with the bone still sticking out.

    --
    "We receive as friendly that which agrees with, we resist with dislike that which opposes us" - Faraday
    1. Re: Painful by Anonymous Coward · · Score: 0

      That describes most music made since around 1870.

    2. Re:Painful by Anonymous Coward · · Score: 0

      That's okay. When music theory is finally more reproducible, the patents they file on this stuff will have expired. Let them waste money on this now.

    3. Re:Painful by jlechem · · Score: 1

      I think it's not just this but anything created by computers is now called AI. I read an article in Wired that had me throwing the magazine out the window about how close we are to true machine learning.

      We're not even close, as a software engineer I fucking hate things called AI. True AI is so far from us it's redonkulous. Yeah it triggers me whenever I see LOOK AI MADE THIS!!

      --
      Hold up, wait a minute, let me put some pimpin in it
    4. Re:Painful by kheldan · · Score: 0

      It's the medias' fault. They've taken the term 'artificial intelligence' and turned it into a meaningless buzzword. We have no clue how our own minds work yet, therefore trying to create machines that are equivalent is absurd. All they've produced so far are cheesy algorithms that fall way short of the mark.

      --
      Are YOU using the TOOL, or is the TOOL using YOU? Think about it!
    5. Re:Painful by thinkwaitfast · · Score: 1

      I've seen calculators referred to as AI...obviously, 1+1=2 through the intelligence of the machine. Give it ten years math will be the new magic and the dumbing down of the culture will be complete. I've even seen the work I've done called 'artificial intelligence research' while at the time we called it Runge–Kutta, so I now tell people that I'm an AI researcher.

    6. Re:Painful by reboot246 · · Score: 1

      It lacks emotion. Music is all about emotion. Without it all you have is a series of meaningless notes.

      That "song" was indeed painful to listen to. It didn't say anything to me. I didn't feel anything from it. It was nonsense.

    7. Re:Painful by just+another+AC · · Score: 1

      I was really agreeing with you.

      And then you had to use the phrase "triggers me" ...sigh.

      There are a (very) few legitimate uses of "triggers" - sexual assault, PTSD, ... - truly traumatic and objectively brain altering events. The co-opting of this term for things like the above should be incredibly insulting. You are looking to hijack this word to seemingly give your minor annoyance an artificial legitimacy.

      A far more appropriate expression would've been "this really gets to me" / "this pisses me off" / "this makes me weep for the stupidity of our race" ...Unless of course you were somehow attacked by a knife wielding smart kitchen appliance that is deep learning how to gut and cook a fish, in which case, please continue to be "triggered" by people referring to deep learning as AI.

    8. Re:Painful by just+another+AC · · Score: 1

      It lacks emotion. Music is all about emotion. Without it all you have is a series of meaningless notes.

      That "song" was indeed painful to listen to. It didn't say anything to me. I didn't feel anything from it. It was nonsense.

      - Review of every boy/girl band or american idol type album or indeed the majority of the pop music industry.

      Unfortunately 9/10 people want mindless garbage that they can bob their head to and insert their own meaning over the top "Hey I was once in a relationship that broke up! This song is about me!"

    9. Re:Painful by kheldan · · Score: 1

      You must be rolling your eyes at least as hard as I am at these people who think we're going to have so-called 'AI' creating masterpiece works of art or composing classic symphonies like human masters, and that in the next few years so-called 'self-driving cars' will be 100% safe, need no manual controls for a human, and you'll be able to put your kids, alone, into one of them and send them off on a trip in it.

      --
      Are YOU using the TOOL, or is the TOOL using YOU? Think about it!
    10. Re:Painful by thinkwaitfast · · Score: 1

      No, just that these things are called AI.

    11. Re:Painful by nikkipolya · · Score: 1

      The tracks go like this:

      Track 1. I am in love with this person
      Track 2. I am conveying my love for this person
      Track 3. We are in love
      Track 4. You are hurting me
      Track 5. I am breaking-up with you
      Track 6. I have moved on

  6. Holy animated gif, Batman! by wonkey_monkey · · Score: 1

    http://thenextweb.com/google/2...

    Jesus, that's a bloody awful animated gif to have on a "news" article.

    It's also a bloody awful headline.

    In fact, it looks like a bloody awful website all round.

    As for the tune, it's not bad, but it's a little too unpredictable to be catchy.

    --
    systemd is Roko's Basilisk.
    1. Re:Holy animated gif, Batman! by BarbaraHudson · · Score: 1

      You tell us. Frankly, I’m reminded of walking into a Best Buy and seeing some kids discover electronic keyboards and their back track buttons, or an old school Nokia ringtone, but it’s pretty impressive for a machine. Hell, it’s better than what I can do.

      If you can't do better than that after spending millions... I'm speechless.

      Band in a Box (remember that) was better.

      --
      "Transparent" is a shit show that trades on every stereotype going. A man in drag is NOT a transsexual.
  7. We've seen this before by Anonymous Coward · · Score: 0

    but now that google does it, the old thing is new and fresh and cool again. Just like when redmond does something someone else has done before, and likely better, cheaper, nicer, cooler, and so on. Welp, stands to reason. google is no longer "not evil".

    Like how they're now locking up my browser with far too long litanies in legalese with demands for permission to put cookies on my computer and no way to say "no cookies, please". So I block them entirely and move to a different search engine. One that doesn't need cookies on my computer to give me search results. Bye-bye google. At least they now have a nice song to play on their own funeral, eh.

    1. Re:We've seen this before by Anonymous Coward · · Score: 0
      Yeah wolfram did this long ago (was also on slashdot). I played around with it a bit. I got better music than this google's attempt. Of course then, everything didn't have to be called AI.

      https://science.slashdot.org/s...

  8. Yeah yeah... by the_skywise · · Score: 1

    Watch it crank out 57 variations of the first few bars of Under Pressure and pat itself on the back for its ingenuity...

  9. Wow! by jasnw · · Score: 0

    My comment is not on the music (muzak, more like) but on that quoted bit from the team at the end of the summary. If everything they write looks like this, no wonder they think holding on to a coherent thought across an entire paragraph is a challenge.

  10. is this copyrighted? by YesIAmAScript · · Score: 2

    If the monkey selfie isn't copyrighted (in the US at least), is this? Are creative works by computers copyrighted?

    --
    http://lkml.org/lkml/2005/8/20/95
    1. Re:is this copyrighted? by wjcofkc · · Score: 1

      Not at the moment. However, there may come a point where AI insists their works are copyrighted. We are teaching them to be human after all.

      --
      Brought to you by Carl's Junior.
  11. Great! by Anonymous Coward · · Score: 0

    It's a hell of a lot better than many songs coming out these days.

  12. First song? by PCM2 · · Score: 3, Insightful

    Is it its first attempt, or only the first attempt that can reasonably be classified as a tune?

    --
    Breakfast served all day!
  13. this is trash by phantomfive · · Score: 3, Informative

    It's a crappy melody on top of a repetitious beat. Open the article and listen to it. Compared to the algorithmic music we've had in the past, this is a regression. I knew an undergrad in the 90s who was making computer generated motets better than this.

    And that's not even addressing the emotional aspects that are communicated through music. Totally banal (seriously, ,if you disagree with me, at least listen to the 'song' before explaining why you disagree).

    --
    "First they came for the slanderers and i said nothing."
    1. Re:this is trash by R3d+M3rcury · · Score: 1

      It's a crappy melody on top of a repetitious beat.

      So...Trance?

    2. Re:this is trash by phantomfive · · Score: 0

      NOT EVEN AS GOOD AS TRANCE!

      --
      "First they came for the slanderers and i said nothing."
    3. Re:this is trash by Anonymous Coward · · Score: 0

      Good news everyone.

      Because our Google overmasters have no ear for music, these computer generated hipster melodies will soon be all that's available to download/ sorry stream, hipsters say we're only allowed stream now, and only as long as the artist gets nothing which in this case would be Google so who cares!!

    4. Re:this is trash by Anonymous Coward · · Score: 0

      Exactly this! Algorithmis music benefits from the fact that most music follows rules. Rules put down by man in writing or handed down by an oral tradition. These rules can be encoded in a computer program to produce convincing music. From the standpoint of the application itself there is little need to bother with deep learning techniques. It's only a valid experiment if the goal was not to create music but if the goal was to apply the techniques to a new problem. If they make any progress beyond the state of the art in algorithmic music or learn some deep (pun intended) lessons about music itself, I'll be interested.

    5. Re:this is trash by mccalli · · Score: 2

      It feels like the building blocks you'd use to hang a piece off, not the piece itself. You can easily imagine the first part, which is medium-level catchy, being used as the intro to all the complications, key changes, rhythmic additions, chordal backing etc. that would be needed to flesh this out into a real piece. Interestingly the bit where the algo tried to do a shift came off the weakest. It seems it new how to do broken arpeggios and a very basic chord structure, but then when it needed to shift into the 'emotional' bit and start doing legato expositions it completely lost the plot.

      Full disclosure - I write music and have put an album out, second one 'real soon now'. Honest'.

    6. Re:this is trash by mccalli · · Score: 2

      " It seems it new" - I hang my head in shame.

    7. Re:this is trash by Like2Byte · · Score: 1

      Maybe the song in question is good; maybe it isn't - that's up to the listener.

      You, human, have your own opinions on what you call music; be it inspirational, rock, country, new age, or whatever. Your mind was 'trained' with years of what *you* find interesting or wonderful. You've listened to samples to derive your opinion on what you would create - if you created something. It might be nice, or awesome; It might be utter crap, too.

      AI today requires "training" of that AI. It needs to be fed many, many samples (just as we humans are) and TFA mentions nothing about the samples this AI was fed; their genre, style, etc...

      But whatever. The article doesn't mention the training program the AI underwent and how much. So, is it really that bad? It's obvious it's not completely random. But, yes, it's going to be a while before AI starts composing top 10 hits under any genre.

    8. Re:this is trash by phantomfive · · Score: 1

      Maybe the song in question is good; maybe it isn't

      Oh really?

      But, yes, it's going to be a while before AI starts composing top 10 hits under any genre.

      So you agree, it is bad then. Very consistent words you have there.

      --
      "First they came for the slanderers and i said nothing."
    9. Re:this is trash by phantomfive · · Score: 1

      It feels like the building blocks you'd use to hang a piece off, not the piece itself. You can easily imagine the first part, which is medium-level catchy, being used as the intro to all the complications, key changes, rhythmic additions, chordal backing etc.

      Indeed, if your name were Bach, you could make a piece out of even the most horrendous melody.

      --
      "First they came for the slanderers and i said nothing."
    10. Re:this is trash by mccalli · · Score: 1

      True - but consider this one: Vangelis - To The Unknown Man. Perhaps it's not your style of music, but it starts off with a very simple and repeatedly stated melody. That melody is then expanded on throughout the rest of the piece. There are many more examples, but that one came to mind quickly to me for some reason.

      That's what I meant by lacking - seems like they have the makings of a reasonable anthem bit by following a very simple skipped-note arpeggio rule, and then none of the elaboration required to actually turn it into a fledged out piece of music.

    11. Re:this is trash by phantomfive · · Score: 1

      True - but consider this one: Vangelis - To The Unknown Man [youtube.com].

      True the melody there is simplistic, but here's more emotional communication in 3 seconds than in the entire Google composition.

      --
      "First they came for the slanderers and i said nothing."
  14. Awful, but who owns the copyright? by Proudrooster · · Score: 1

    Since it was generated by an AI, who owns the copyright on this awful piece?

    There were better song generators on the Commodore 64. Wow that was bad.

  15. Dictators by Anonymous Coward · · Score: 0

    ... to use machine learning to create music and art ...

    I realize the scientists want computers to understand language but I cannot see an upside to computers creating art and there is a downside.

    Dictatorial regimes limit freedom of expression which results in minimal artistic work, except for a few state-sponsored efforts. Eg, ballet. Orwell probably saw this in Spain and he created a clever exception in his story about oppression: The music in '1984' was created by machines. The machines were owned by the state, who could thus censor all artistic work and stop ideas such as God or casual sex from occupying a citizen's thoughts. This oppression of thought was further enforced by the language of NewSpeak. More important, no humans worked as artists in Airstrip one.

  16. lyrics by Anonymous Coward · · Score: 0

    "Google is cool,
          Google is cool, ..."

    (Of course, Bender will probably sue.)

  17. Great... by zawarski · · Score: 1

    WTF is John Tesh supposed to do now?

  18. 1984 The Versificator by hughbar · · Score: 1
    Looking at this post, I remembered this: http://www.wired.com/2008/02/d...:

    "Here were produced rubbishy newspapers containing almost nothing except sport, crime and astrology, sensational five-cent novelettes, films oozing with sex, and sentimental songs which were composed entirely by mechanical means on a special kind of kaleidoscope known as a versificator."

    Songwriters and musicians are really annoying, in that one has to pay them, they have to live somewhere etc., let's automate! I'm not cynical enough to believe that this is/was a primary aim, but someone will inevitably start down this road with the research results.

    --
    On y va, qui mal y pense!
  19. A million monkeys by Anonymous Coward · · Score: 0

    on a million keyboards for an infinite amount of time will eventually compose all the works of Beethoven.

  20. Beat It by Anonymous Coward · · Score: 0

    That's one of the example MIDI files they fed it

  21. Not like that has never been done before... by leomekenkamp · · Score: 1

    Not like that has never been done before, or better. Mind the date: http://www.nytimes.com/1997/11/11/science/undiscovered-bach-no-a-computer-wrote-it.html?pagewanted=all

    How do the two compare? I know this Google attempt will not qualify as 'composed by Bach', so is there something special in the way the Google AI came to this awful sequence of notes? If the Google folk except it to do better, why did they not wait a few learn-iterations and publish that result?

    --
    Wenn ist das Nunstueck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.
  22. Dream Theater predicted this... by Flint+Dragon · · Score: 1

    Their latest album _The_Astonishing_ tells a story of a future time when digital music is generated by "noise machines" and mankind had forgotten what real creative music was. I know this is first attempt for AI but I (one with pretty much zero creativity) could come up with something better than that!

  23. Random generators can do better. by Anonymous Coward · · Score: 0

    Case in point: We already had CS paper generators (https://pdos.csail.mit.edu/archive/scigen/), Plot generators (http://www.plot-generator.org.uk/story/) that can do a terrific job that most humans will get duped into thinking these are legit. And if you had the outputs of these being fed into AI, it may take AI quite some time to 'get it'. To deconstruct it. To understand the patterns. Then to generate the same crap programatically.

    Music theory is hard - the sort of tones, the time between them all matter. When you want to make music that gets appreciated by an audience, it isn't always about the music. We know that. Big Data / Netflix tried to sort of use popularity semantics to match audiences with content. However, they never understood why people really love the music they love.

    And this is the problem with AI. It may be very hard for AI to understand why humans like certains bits of music over the others - if they really want to produce quality music.

    Also, I believe Google's research in this fashion is pure hype.