Slashdot Mirror
Synthesized Singers
ctwxman writes "Over the past few decades, advances in computer hardware and software have eliminated many jobs... some technical, some menial, but none artistic. As an on-camera performer in television, I've always was believed that I was 'bulletproof' as far as replacement through technology was concerned. Not so fast. Recently, The Sinclair television stations began using 'central casting' to bring news and weather anchors from a central location (near Baltimore) to the local outlets. Still, real people are needed, just not as many. But now, even real performers may be replaced. The New York Times (inhalation of airplane glue required) reports on a new technology which allows synthesized singers to sing. Imagine having a singer with a world-class voice at your disposal, any hour of any day. She's just standing at the ready, game to perform whatever silly song you might make up for her: a ballad about her love for you, a tribute to your best friend's golf game, a stirring rendition of the evening's dinner menu. Scary."
Google partner link...and yes. I did use my subscription to get it. :P
Bugs are just features that have been fixed.
this with the story "Decoding the Algorithm for Pop Music" and a synthetic DJ and who needs the radio anymore? Throw in a few digital actors and you can have your very own 24 hour copyright free mtv! A whole new meaning to "homebrew music" And what better way to bring down the RIAA than to replace them with software its not like its going to be any more original.
"It's so convenient to have a system where everyone is a criminal" - A. Hitler
I knew Britney Spears' voice couldn't be real!
Same goes for her boobs.
Well the rest of him is synthesized already ;-)
From >a href="http://www.zero-g.co.uk/index.cfm?articleid= 802">http://www.zero-g.co.uk/index.cfm?articleid=8 02
LOLA Demo 1 -Little Bird (MP3)
Demo 1: "Little Bird".
(NOTE - the lead vocal line on this demo is NOT by Vocaloid - it is a real singer. Please listen to the backing vocals!). This demo illustrates well how LOLA has been used to create a simple backing vocal arrangement for a personally-produced song. The song was written and performed by one of the Zero-G singing synthesis development team, Andy Power. Andy is singing the lead vocal himself, with his real voice, but he was able to add the backing vocals to his song purely by creating them all using LOLA. Although this is only a very simple example, it immediately illustrates LOLA's usefulness in an everyday situation.
"BSD: Free as in speech. Linux: Free as in beer. Windows 10: Free as in herpes." --Man On Pink Corner in #52607549.
She's just standing at the ready, game to perform whatever silly song you might make up for her: a ballad about her love for you, a tribute to your best friend's golf game, a stirring rendition of the evening's dinner menu. Scary.
/. crowd come off as downright luddites.
Imagine a composer getting up in the middle of the night, going to his newfangled magical "keyboard" and whipping up an entire symphony without the need for a full orchestra..... ooooh... scary.
Man, for a bunch of geeks sometimes the
From the article, it seems that it was not synthesizing the singing from scratch, but was rather using a complicated sample set to recreate the voice. What I thought they were going to do was bring to fruition physically-based synthesis of the human voice. By the way, using a sample set IMO is going to reduce the amount of expression you can get with a song, especially if one were to use a very limited set of samples. And I really hope I don't start hearing the SAME VOICE in every freaking song because of this.
You Failed It
have won.
"a new technology which allows synthesized singers to sing"
I suspect Milli Vanilli, BROS, Christina, Brittney and N*sync may be suing for prior art.
Do you or your partner snore? - Visit www.snoring.com.au
The new voice with Panther (Mac OSX 10.3) is scary. Vicki can send shivers up my spine anytime. I KNOW it's only a manufactured voice, a speech synthezizer, but dammit it's a sultry one.
I'm almost considering getting a mac just to listen to her.
I can see the live concerts now... packed with people in the crowd, latest pryrotechnics ready to go, all the latest visual and audio gear deployed.
And in the middle of the stage, a beige computer tower with a monitor, keyboard and mouse and a technician on hand to wiggle the mouse every 10 minutes so the flying windows screensaver doesnt come on.
Be you Admins? nay, we are but lusers!
What is really cool is when machines can do what people cannot do. The first sign of this was several decades ago when drum machines and analog synthesizers came about. The drum machines could play beats so fast and hit more instruments simulateously than a single person has limbs for and the synthesizers could create entirely new sounds. In the present, there are pitch machines which put singers' voices at a desirable pitch when singing. Hopefully next we'll have robots/machines with AI that can create their own insightful, fun, or intelligent lyrics to songs and sing them to an original beat. Popular music analyzers(just posted on /.) are already capable of predicting what tunes have potential. Music is a product of man, whether it is created through human hands or machines. You can't mentally hold yourself back to the idea real music is only a direct product of man.
(\_/)
(O.o) This is Bunny. (> <)
and you can have your very own 24 hour copyright free mtv!
A good music industry lawyer will probably be able to argue that any song you write, even using algorithmic composition, infringes the copyright in at least one existing top-100 hit. Details
Will I retire or break 10K?
It's ironic that the very tools the music industry uses today to guarantee pitch-perfection are tomorrow going to undermine their own success, much as people giving away software are doing in many ways for the software industry. Perhaps the only thing guaranteed is acting, as Final Fantasy: The Spirits Within demonstrated, although eventually computers may catch up with live actors as well.
But progress is inevitable. And as things that were once worth money become free, we become open to do more things. So I'm not too dismayed by the concept that computers will tomorrow handle (Handel?) music composition as easily as they handle music piracy today.
Try not. Do or do not, there is no try.
-- Dr. Spock, stardate 2822-3.
Imagine having a singer with a world-class voice at your disposal, any hour of any day. She's just standing at the ready,
Is her name Sharon Apple?
Trees can't go dancing
So do them a big favor
Pretend dancing stinks!
Serious legal issues arise when creating "voice fonts" made from singing material previously released by artists. I doubt the RIAA or the artists themselves will like this new techonlogy at all. If this technology is a success then I forsee a push by the RIAA/artists themselves to get their voices copyrighted.
As an example, Harley Davidson (the motorcycle company), tried to get it's unique motorcycle engine sound copyrighted and failed. Will this change the copyright office's stance?
But now, even real performers may be replaced.
They already have been. Who would call Spears, Aguilera, or Milli Vanilli "real"?
a stirring rendition of the evening's dinner menu.
Sorry, but "Pasta Roni" sung is going to be underwhelming, no matter how good the voice is.
The coolest voice ever.
The New York Times isn't going to get slashdotted.
Nice formatting, by the way. Sure is easy to read something when it's one long stream of text.
You suck.
What I thought they were going to do was bring to fruition physically-based synthesis of the human voice.
You're looking for "formant synthesis." SoftVoice text-to-speech software already does this, but its singing sounds a bit robotic. You may know SoftVoice as the voice behind "Invasion of the Gabber Robots (All Your Base Are Belong to Us)" by The Laziest Men on Mars.
Will I retire or break 10K?
Sample Songs Available in MP3 at: http://www.soundonsound.com/soundbank/YamahaVocalo id.php
The problem with computer-synthesized voice is that it will not correctly convey emotions, and (if plaintext) will not even stress the right words. And it would be a bitch to write the appropriate tags.
eg
I didn't say he did it.
I didn't say he did it.
I didn't say he did it.
Don't waste your vote! Vote for whoever you want, unless you live in a swing state it won't matter anyways
It sounds like they've gone to much greater lengths on this project than any I'm aware of in the past, but the basic thing here has been out for a long time. Most any keyboard you can buy has human voices. A single sample can be spread out over your keyboard and sing any pitch you want, even glides and stuff, pretty easily. But it's generally fairly rudimentary - 'ahh' and 'ohh' or similar, you can actually do some nice sounding background vocals but not sing verses.
From the description in the article, this 'new' thing is really just an inevitable extension of that - they spend about 5 days with a singer, recording her singing many different phonemes and different effects, so that you can then piece together the words to your own song and put it to your own melody in her voice. And, for the moment, they're still aiming at producing background vocals, just more complex ones with the ability to do actual lyrics instead of a oohs and aaahs. Could be kind of cool, but it definately doesn't sound like a 'quantum leap' - just an extension of long-existing technology. I've been expecting to see someone do this for well over 10 years now, ever since I first got to play around with a digital synthesizer.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-
Friends don't let friends enable ecmascript.
the have some samples here
sounds synthetic to me
They said that they needed someone to sing 5 hours a day for a week...so that they could make him/her obsolete? In what life would you make yourself obsolete in your chosen profession for a weeks pay?!
I write music and produce for TV series. I have never had to use a musician. Ever. My boss uses live performers occasionally for shows that might win Emmys. I use Machfive and Digital Performer 4.1. Samplers, especially the 300 dollar Machfive platform/plugin have eliminated the need for live artists in my business. Hell, I will be recording a rap (bleh) artist soon, and the only live recording will be his vocals. The rest will be sampled.
Your time is coming to an end, but I will say that synths and samplers don't match live studio musicians...yet. Vocalists are still safe, at least until Apple fixes their Speech voices.
Sig (appended to the end of comments you post, 120 chars)
Anyone who's had a mac has been able to hear synthesized singing since Mac OS 8. Gogo Cellos and Bad News
The light you see at the end of the tunnel...
is the headlamp of a fast approaching train!
- Sherman
I find it interesting that the first voices they've decided to use are "SOULful" voices.
"But I trust in the people's capacity for reflection, rage and rebellion." -Oscar Olivera
As an on-camera performer in television YOU'RE GEORGE MICHEAL! I KNEW IT!!!
Sacred cows make the best burgers.
There's an English press release here on the Japaneese Yamaha site with some clips available. They're in some weird format that requires a special player. The player is Windows only and is in Japanese. Still easily installable...just click where you think 'Next' should be. Here's a direct link to the player:
Player
The samples are very good and worth the trouble if you're interested in this. While not perfect it is better that I was expecting and I could see how it could be passable for a real person in certain situations.. Here are some direct links to the samples:
Kimi no uwasa / Male lead vocal (Japanese song)
Sarasara yukigeshiki / Chorus (Japanese)
Amazing Grace / English example
Little would you know that while your local senator or rep are being televised bellowing out meaningless torrents of weasel-words on CSPAN, they may well actually be off porking an intern or on a lobbyist-paid junket.
When potentially used on one end of a "live" webcast or other broadcast, the possibility of creating "digital alabais" rears its head.
This is one mode of media where it may be necessary and desirable to use DRM techniques to mark a synthetic broadcast as synthetic.
Heck, maybe use the HDTV Broadcast flag for this purpose instad?
I believe I speak for all the Republicans visiting this site when I say, "Get a job, hippie!"
[o]_O
Combine these synthetic vocals with some randomized instrumentals and pipe it into your 'hitablity` algorith (covered here and here) and generate endless pop music!
Very soon this is going to replace all the chipmunk vocals.
Hear a sample of 'Amazing Grace' sung through the Vodaloid.
--J.
I want a soundtrack for my life. Like when something goes good, there would be a choir of "hallelujah". So far I only have this site for when I mess up.
I realize I'm not really adding to the discussion here but I've recently gotten into making techno (Cool Edit Pro 2 and Reason are excellent) and being a huge fan of Tracy Thorne-esque voices on techno tracks, I was just wondering the other day why I'd never heard of such a tool.
...this is excellent. $200 and soon.
So
My
Limekiller
I welcome our new Robotic Vocal Overlords.
- - - If the sun is a star, why can't I see it at night?
...Is the ability to magically summon that sound effect from reading rainbow right after the kids say what they think of the book.
Look it's a joke about my sig IN MY SIG! LOL!
Having been in a research enviroment where exposure/inhalation of airplane glue fumes (we were gluing up parts that were installed and flown on a real airplane (OK, it was tilt-rotor, and those are not real airplanes, but-still) so it counts as airplane glue), I can attest that attempting to sign into the NyTimes website can be greatly hampered by inhalation of airplane glue. Further, when some of those glue-tubes say 'use in a well ventilated area' they mean outdoors in a hurricane.
Now excuse me while I go try find where my brain cells went.
who hangs out with musicians?
A: A drummer.
ba dum dum chsst
- - - If the sun is a star, why can't I see it at night?
Hear a sample of 'Amazing Grace' sung through the Vodaloid.
And here is a sample of 'Daisy Daisy' being sung through the Vodaloid...
"Daisy....Daisy.....Give me your answer due.....I'm half-crazy....all for the love of you...."
I cant wait until cab drivers are replaced. Im tired of getting cut off in rush hour traffic...
Manipulate the moderator system! Mod someone as "overrated" today.
i just caught my dog eating the toilet paper so I KICKED THE FUCKING SHIT OUT OF IT
at least we'll be hearing talent again.
I recommend everyone pick up a copy of "Little Heros" By Norman Spinrad...it is to the music industry today what "The Shockwave Rider" by John Brunner is to Hacking. Highly, Highly recommended, esp in light of this story about the potential of artificial performers...
ttyl
Farrell
CAN-CON 2019 - Ottawa's only book oriented Science Fiction Convention! October 18-20, Sheraton Hotel, Ottawa, Canada h
http://www.global.yamaha.com/news/20030304b.html
at the bottom of this page. You need some kind of back-assward player to hear them, though.
We can replace Britney Spears musical endeavors with a small shell script. Then she'll be able to fully devote herself to just looking hot.
Fun toy.
Huh?
Marilyn Monroe singing "Happy Birthday, Mr President"?
look it up, I forgot it's been 6-7 years at least.
Gibson's Idoru book too. sheet
Why scary? My job is being moved overseas, to Hydrobad, India, because in some freak of coincidence, those geeks over there will work for 1/3 my $salary$. So, pardon me if I'm not the least bit surprised that executives in entertainment multi-national corporations find it useful that a computer program can simulate, realistically, the subtle timbre of the human voice. I can't wait for Dan Rather's replacement...
I was actually thinking about this subject the other day. The music we see on TV and hear on the radio is essentially synthesized already. The Neptunes and a few others write a huge amount of hits for all types of artists.
I keep hoping for the next N.W.A. or Nirvana and I start thinking we might never get fresh, exciting music again.
Links to penisfish porn
Please for the love of God, somebody patent this before "endless pop music" becomes a reality. We have enough noise pollution as it is.
And that is where things like JSML come in.
Karma: It's all a bunch of tree-huggin' hippy crap!
I don't know about you guys, but personally, I don't think there's that big a risk of performers really being replaced. At least, not en toto.
Now, "popular music" notwithstanding, it takes more than just hitting the right notes and holding them to make music. This applies muchly to instruments, and doubly so for voices.
First of all, just any combination of notes are not what makes music... artists have to play with hundreds of variations of tones to find "that perfect sequence," the collection of tones in a specific order, length, and style that produce a pleasing arrangement. Once that has been found, further arrengments of music are patterned and fitted to that sequence. You can have a synthesizer, but someone's still programming it... and not with numbers, either.
Voices are many times more complex than musical instruments, because not only is there tone, volume, and length, but there is, for lack of a better term (in my own knowledge), shape of the sound. The artist Karl Jenkins (of "Adiemus" fame) used singers and a nonsensical language specifically to capitalize on that very set of qualities... using the human voice and speech as another "Instrument," rather than as lyrics.
Now, you could synth using the phonemes and vocal qualities of a singer, but ultimately, without the feeling behind the voice, no amount of coding will put any life to it.
The Penguin Producer
it's interesting how the technologies of voice replication and voice recognition are so similar. The recording studio where I work recently participated in a project for the developers of a voice controlled navigation system (think OnStar). Our task was to record people born and raised in Chicago dictating a long list of words which would presumably use at least most of the phonemes at our disposal. I think they did this in most major metropolises. The goal was to build a system that could recognize english speech patterns with a wide colloquial variance. Perhaps it won't be long before we have a program that can emulate anyone's voice.
You do realize that if some moron tries this as a result of your front page article that you're going to get your ass sued off, right?
Why would I want sythesised regular ol' people when I can have the singing monk? Huh?
Hey I'm surrounded by this stuff since it's in my field.
The music technology group developed open source software called CLAM (http://www.iua.upf.es/mtg/clam)
Here is the mtg site:
http://www.iua.upf.es/mtg/eng/
Here's my university's program:
http://www.music.mcgill.ca/musictech
If you have questions send them along.
i always wanted to put my ear up to a nice anus and listen to the sweet sounds the eminate from within
Personally, I think the best examples to download are "The Easy Way" (song 15) and "K'ai - Eyes swim" (song 16).
While no where near perfect, Flinger and the samples really show where things are heading - I have said it before, but this type stuff (perfected, of course), plus tech like machinima (once again, as it becomes better) are truely going to alter what we think of movies, acting, etc - virtual actors, virtual singers, virtual movies...
Reason is the Path to God - Anon
This article is Good News...
Never mind that the Mac had singing text to speech for a long time...
A little genetic algorithm, a dash of Vocaloid, that hit-o-meter thing they were talking about earlier, and some random seeding. Then, when I get The Perfect Pop Album, I compare the results to Mozart's (alleged) Musical Dice. I'm pretty sure that after 3 years of listening to my own tandomly crappy music, I'd be crazy enough for a tenured position.
-theGreater Ponderer.
The first thing that I thought of when I read this was the classic fairy tale "nighingale" ("http://www.pacificnet.net/~johnr/cgi/aesop1.cgi? hca&a61").
The story tells of a Chineese emperor who heard a beautiful, magical bird sing. He loved the bird's singing so much he took her captive. Then someone gave him a jewell-encrusted mechanical bird. He liked the mechanical bird better because it was predictable (you knew what it would sing because it was a machine), it would sing all the time (never got tired) and it was prettier to look at (because it was artificial). He banished the real bird.
Then one day the spring broke in the mechanical bird. A watchmaker was able to fix it only to the point where it could sing once a year. The emperor became ill and death came to his heart.
The real bird came back from banishment one night. She sang to him and gave him hope so that death left his heart. He wanted to reward the bird but she said that the tears of joy he shed when she sang for him were the reward of a real singer.
Thanks go to Dorothy Dorothy (http://www.rdorothywayneright.com/intro.shtml) for making me aware of this story.
Listen to this one. The Amazing Grace and the middle sample from the press release site are ok, but the one I linked to is rather amazing.
How old is this person posting?
Many artist industries have been revolutionized if not replaced by technologies over the past 20 years:
Typesetter - both for corporate and newpaper work. (yes it is very artistic and professional in years past)
Graphic Artist - Today most people/companies just do quick stuff in photoshop.
TV field - producers/content editors..once was very artistic and you had to get it right the
first time. Digital video editing has changed this field enormously.
Radio Field - Disc Jockey used to be a much great artistic venue. Today almost all has been automated, and one disc jokey probably supports many many local stations on average.
Sound Audio Engineer - The field for recording professional audio and editing used to be much harder and more artistic. Todays digital editors and software systems make this field much less
artistic.
Architecture - used to be one of the hardest disciplines to master the praticle and artistics components. Today, computer modeling has changed
this industry significantly. (also included is fields such as interior design and landscaping)
Writing - althought less admited to, the computer word processing advances have revolutioned the aspects of writing from the most commercial writing to the most artistic.
Photography - This field used to be very artistic, with the need to get the picture just right the first time around...today with digital photography, much of the original artistic skills are not required.
Please add to this list, if you agree.
Over the past few decades, advances in computer hardware and software have eliminated many jobs... some technical, some menial, but none artistic
Ever hear of a cel animator?
Punctanym: alternate spelling of words using punctuation or numerals in place of some or all of its letters; see 'leet'
It blows away any keyboard-synth voice I've ever heard before, but it's still not perfect. There's nothing wrong with the tone of the voice for background vocals, but the area they really need to work on is in the vibrato. Hearing a perfectly-oscillating vibrato is a dead-set giveaway and really detracts from the music, especially music that's trying to be old-skool and authentic.
Having said that though, I'm sure they'll have tweaks for that sort of thing in no time.
Ladies, form queue here -->
The only bright side is that I could eventually have the chance to delete Celine Dion.
im sorry but you are obviously not a vocalist or musician. britney and milli vanilli: whatever.
but christina can *sing*. like you wouldnt believe.
not to mention she cowrote pretty much all the songs on her new album and is credited as a co
producer, executive producer and arranger.
and then there is the story of her making a famous producer cry because he wasnt getting her vision.
hardly sounds like qualities of a dumb talentless puppet.
If anyone is wondering what this sounds like, there are some sample here: http://www.vocaloid.com/en/sample.html
Although pretty convincing, i think it has a way to go before it would be perfect.
In America we are imprisoned by our fear of them.
Classic singers stay as close as possible to the "absolute" quality line - it's perfect for being mathematically modeled and it's a matter of time such models will be apparead, even if their implementations will take some hardware resources.
Pop singers make sound anyway far away from being called as an art. It's perfect for being implemented in embeded solutions. It's a matter of time first cyber-singers will be cloned like cheap "made-in-China" electronic (sorry, my oriental friends, although nothing personal or racial in this comment).
Jazz is still an art, like classical music, but its improvizations are very unpredictable. Jazz singers will be last ones to go. Even more - Jazz improvizators will be eventually involved to prototype new cyber-singers. Hmm, I can even imagine special programming languages for singer-modelling: "bebop", "blues", "swing" :)
Less is more !
Some friends and I tried to do something like this about 15 years ago, but the state of the art was not there (we were having to develop custom hardware with multiple DSPs, and it would have been at least 2U in size), and a couple of lawsuits scared us off. The nail in the coffin was one lawsuit that really seemed to be on point for us, was a Mercury Sable ad. Bette Middler did not want to sing it for them, so the license only covered the song. The ad agency hired someone else, whose voice sounded identical to hers, to sing Do You Want to Dance. She won big time and had the commercial yanked from the airwaves. Think of a Mercury Sable doing figure 8s and spins (on water) with that song in the background: beautiful ad.
For those who care, its a harder challenge than regular speech synthesis by a couple orders of magnitude.
the implications for the phone sex industry are staggering. Imagine the provider being able to use YOUR NAME in the call with a unique new script each time you call. If only I were a pornographer...
Just because you have this does not mean these robotic singers have rhythm. Theres more to singing than just melody.
People don't exist to serve systems, systems exist to serve people.
This reminds me vaguely of David Cope's Experiments in Musical Intelligence.
See, Cope's a composer that hit some artistic blockage, and so wrote a nice little proggy
to help him along. It ended up, though, as a program that composes its own music. No vocals,
though, and a lot of it ends up being played by people, the computer just writes the music.
It's interesting stuff. Check it out here (Cope's website).
You can even download some of the stuff in mp3 format.
Buy Steampunk Clothing Online!
Many people here have already commented that the voice isn't quite there yet in terms of realism. Many here have pointed out that the technology doesn't seem new -- they're just taking more sound samples and blending them together (albeit in the frequency domain, with smoothing).
One area that really needs quite a bit more work is the vowels. When singers sing "ee" (as in "saved a wretch like me," for example), they usually soften it so it sounds a bit more like "meh." When I used synthesized voices before on a Mac, I had to specifically spell the lyrics as "meh" so that the program would articulate those vowels properly.
Of course, maybe the sample of "Amazing Grace" I heard was recorded by a singer who really liked to pronounce such vowels as "ee" rather than soften them to "meh," but it doesn't seem likely.
Gan Family Homepage
But this works for anybody. If you can synthesize music from MIDI and vocal models, you can use that deal. The RIAA can't stop you from doing this.
A synthesized music web site could even buy blanket ASCAP and BMI licenses, which aren't too expensive, and allow music downloads. The going rate seems to be about $5000 per million downloads, or about $0.005 per song.
This is a real threat to the RIAA. If the technology works.
Perform illegal operations with child processes?
...of that anime I saw a long time ago. Macross Plus, I think. The universe's greatest singer was a computer, and people came from far and wide to attend these huge concerts to see it sing. It also produced a hologram of some made-up woman to go along with it.
Considering that normal speech synthesis has not been done well, singing seems to be hard. Already people can take a bad singer and turn them into a good singer but complete synthesis seems unlikely.
Furthermore, this tech is likely not going to be what you think. What makes a singer good is their INTERPRETATION of the notes. Even with proper synthesis, at its best, it will be like computer animation. It could be very good and maybe even perfect but it would be TIME CONSUMING. Watch the making of Making Nemo on the DVD to get an idea of how hard it is to understand emoting.
You would really need to spend a large amount of time figuring out how to make the voice sound EMOTIONAL.
Sunny
Be my Friend
yes... i don't know how happy i am about this...
Synthesized voice doesn't matter, they could also hire a cheap Indian or offshore singing at all.
You didn't think *anyone* was impervuous to outsourcing?
And all our yesterdays have lighted fools The way to dusty death. --Will
But does it run Linux?
But no... that was bioscience producing clones for the music industry... how many geneticists its going to put out of work?
Looks like I picked the wrong week to stop sniffing glue!
Too late to be known as Bush the First, he's sure to be known as Bush the Worst.
You will need:
- a shitload of Silly Putty(tm)
- a human skeleton
- some wire
- a wig
- sunglasses
- a Brillo(tm) pad [optional]
1) First, get a human skeleton. Be sure the bones are free of flesh, gore, and carrion. The best way to do this is to boil the bones for two hours - but be sure to label the bones before you disassemble for boiling, otherwise it can be tricky to reassemble it.
2) Wire all the bones together so that the joints move freely. This step is important - even if the original ligaments are still holding the joints together, they will eventually rot away, so you'll need the wire in place to maintain the skeletal structure of your future love slave.
3) Cover the skeleton with silly putty. Mold and sculpt the sill putty until it looks like a hot, sexy, 22-year-old porn star. Don't forget to make a hole between the legs - this will be the "vagina," for those of you who surf Slashdot all the fucking time.
4) Add the wig on top of the head.
5) Put sunglasses on your doll. Human eyes are hard to emulate, so sunglasses will hide their absence. Also, the sunglasses confer a look of unruffled nonchalance, which will be essential for when you and your German shepard are double-teaming your plasticine playmate.
6) Fluff up the Brillo pad and press it into the flesh around the vagina to create pubic hair as desired. For the porn-friendly "landing strip" look, you will only need about 1/3 of the brillo pad. Pedophiles can skip this step entirely.
7) Voila! You can now lose your virginity and begin the only healthy sexual relationship you're ever likely to have. Enjoy!
Blowing your own trumpet there ? ;-)
"If someone came to us and said, `We want Elvis to sing this new song,' we'd have a lot to contemplate," he said. "We tried to retain the integrity of his original song with the remixes. Now you're talking about a whole new vocal performance of a song he never sang or knew? How do we know he'd want to sing it?"
Why not just ask for a synthetic version of an Elvis impersonator to sing the song? That should sound pretty close.
bananas like monkeys.
At present, you still need a human artist to create the art, just not a human artist to perform it.
Here's where the Yamaha software products are available online - for windoze XP or 2000- starting in December.
Vocaloid LOLA - Female Soul Vocalist. $329.95
Vocaloid LEON - Male Soul Vocalist. $329.95
Vocaloid MIRIAM - Virtual Female Vocalist. $399.95
Has a screenshot and description of the process of constructing a song track.
Note that each virtual singer's voice description file is referred to as a "font". B-)
Bantam Dominique roosters crow a four-note song. Once you've heard it as "Happy BIRTHday" you can't NOT hear it that way
linus torvalds sucks a dick
Try it out now, using actual singers: http://www.sr.se/cgi-bin/p1/src/sing/default.asp :)
The folks over at myriad-online.com have software that has been doing this for a couple of years now (virtual singer)... I have used their technology. I have a few demos over at: http://www.view3d.tv click on gallery and then click the music button (its flash based) on left side... Regards, Daniel
stereoscopic multimedia pioneer view3d.tv
I think your dreams of persecution are premature. This is technology, not a replacement for creativity. Your fears should focus on AI, but genarally I believe creativity will always be as spontainious and unpredicatable as it is today, so there's no need to worry about our future robot masters somehow diminishing our ability (read: need) to think creatively.
;-)
And as far as this particular technology goes, by the time it has advanced enough to be used in pop songs you can surely bet that it will be missused by the contemporary equivalent of Autechre or some such.
Every technology gets hacked and thats just irrepressible creativity at work for you.
Quack, quack.
Speaking as a musician, I've fretted many a time over whether my skills will one day be co-opted by synths and automata. I stopped worrying about it when I got into Electronic Music techniques, probably about 7 years ago.
The reason why synths have not replaced instrumentalists, and why I don't think it will ever happen, is that the majority of people out there using synthetic approximations of acoustic instruments do so out of laziness. Every jackass with a sampler conjours up this warm and toasty image of a 'symphony in my keyboard'. It's supposed to make everything easy. You'll never get a realistic(and more properly, dynamic facsimile of an acoustic instrument in reducing it to a simple method of performance.
I don't doubt that we're steadily approaching a time where one can fully model the human voice and all it's eccentricities, or the tuba, violin or piano for that matter. Physical Modeling synthesis is an exciting frontier right now. But once we get there, it's going to take someone of an exceptional(read virtuoso) skill to make it sound like a virtuoso. Why? Partly what makes the sound of these instruments so compelling and dynamic is that there are so many variables being controlled. In playing the violin you have bow pressure, speed, bowing technique, finger vibrato(which has IMO never been adequately reproduced by algorithm), and host of other things going on. To reduce all this to a single keypress on a keyboard, which is one of the least expressive controllers out there, leaves you with a dramatic loss of information.A good friend of mind said it best, when I expressed my misgivings in taking an AI in music class. The task of effectively tackling the problem of making a computer autmoatically do all the work of a human musician is so daunting, and would involve so much finesse, that the very act of accomplishing it would itself be art of the highest form. If things like this replace real singers, you'd better believe that their operators are going to have to be just as artistically and technically skilled as those they're replacing. It's sort of a beautiful circle when you think about it.
Apparently you and I have different definitions of impressive. Give me an e-ChrisRobinson or an e-Bjork and we'll talk. This sounds like your next door neighbor with a speech impediment... more or less on key but absolutely soulless and you don't know what the hell she's trying to say.
Most major corporations are moving their customer service support lines to a new voice-responsive menu system where the "operator" understands what you say. Companies like Verizon even go so far as to have the computer respond in natural language "okay, let me make sure i got that right....5..5..5...1..2..3..4".
If you told people in the 1950s that human operators could be replaced with computer programs, they'd tell you you were insane.
Seeing pop stars going digital seems logical. Pop stars are all about image. What better image than a "star" that doesn't have to manage his/her physical appearance, can "perform" at any venue or tv show, never grows old or tired, and, perhaps most importantly to the industry, is cheaper than a contract with a human performer.
And since most pop stars seldom write their own music, lyrics or even their own choreography, it just takes the fake "human" and replaces it with a digital substitute.
Up, Up, Down, Down, Left, Right, Left, Right, B, A, START
Be warned using a Brillo pad can cause some uncomfortable chafing although it does have a useful "self cleaning" function which must also be considered.
The talent and skill of an accomplished singer like Callas or Vickers is not likely to be matchable or then manipulatable by your savvy tech dude at his computer console. There are infinite varieties of color and phrasing and style possible, only select combinations in unique contexts are tasteful or even plausible. Music so far defies being mapped into a synthetic ADC despite the very mechanical nature of instruments. The human voice is all the more complex of a problem. No, music is not so discreet as the digital chess, and is far from being mastered by Man's Meta-Thinking, to say nothing of the rigor and training vested in any least professional musician, and I mean genuine musician, not those plugged-in puppets whose stuff is endlessly refined and perfected during mix. Perhaps this kind of thing can however can be used to replace the voices of people who determine to destroy their voice by belting. Ughh.
Isn't this what MTV is all about? I always knew those fsck-me-songs and fsck-me-dances are not for real...
Musically illiterate as I am, I was really starting to get my hopes up that a Text-to-Speech program could sing using synthesized pitch.
If Festival can do inflected languages, e.g. Chinese, then why not make such a plugin?
...at your disposal, any hour of any day. She's just standing at the ready, game to perform...
Sounds good to me! Going to order one of these.
Ceterum censeo Microsoftem esse delendam
Theee coh. maydor ahhmiigahh... ws dooweng theez. Ten yeez ah. go.
Iduro
I wouldn't worry just yet. All of these performances would royally suck. Most decent singing is the result of an endeavor that involves the creative cooperation of the song writer and the singer. Singing is usually as much about interpretation as it is about getting the notes right. Sort of like cooking. A great cook is not someone who can read the recipes and execute them. A great cook is someone who can do that, improvise stuff, and come up with ideas. And seek out stuff that they think they could pull off well.
I want Diana Krall to be the voice of my PDA. I want her to sing my appointments to me. I want her to offer sultry condolences when I forget important dates, like anniversaries. Heck, I want her voice to teach me to sing. Maybe my shower could sing to me?
geeks are cats who dig a certain kind of cool
In my experience anything to teach a singer he or she "could" be redundant just makes me feel... so... good... especially since if this is really viable (Which it's not) it could get rid of alot of amature singers ego's...
/. standards,
Yeah.. Turn up 4hrs late to practice again.. I'll teach you...
All honesty; It's cool, but not really that amazing especially by
Ow!! my Bic lighter just burned my thumb.
This is great news!
Movies have so much computer generated graphics that most panaramic or long distance shots are actually similated images using computers. It's still easy to tell the difference, but the MPAA doesn't seem to care about that.
With computers telling what pop music will be a hit, it won't be long before they start generating the music itself.
I read long ago, before the internet, that they were already using computers to generate Soap Opera plots. Unfortunately I can't find anything via google.
Why is this great news? Because will the increasing ease by which Corporations can replace real people with simulated drones we will either quickly become something out of some dark-sided science fiction novel (which would be bad) or we become so fucking sick and tired of the constant attempts to bullshit us into spending hard earned and increasingly rare mony that we won't spend it on anything except live performances (plays, concerts) where people have to actually play their own fucking instruments and really sing like their life depended upon it
In short, this is good because the level of bullshit that Media Moguls is pushing on us is reaching what I hope to be an eventual breaking point.
If we really are that stupid to buy into it then I guess we deserve it as we're all sheep bleating for our freedom but unable to lift the gate latches with our nose.
The music studio Fruity Loops has had a singing plug-in for a little while now; you don't have a lot of (easy) control over the pitch, so it's really more of a toy most of the time. But combined with some simple audio processing, you can easily get results like these:
http://www.antics.org.uk/mp3/green/ntk_copyright.m p3 (1mb MP3)
http://www.antics.org.uk/mp3/green/ntk_eod.mp3 (646kb MP3)
I'm sure it's nowhere near the league of the featured developments, but it's still a very impressive feature in an affordable package...
nt
Some presenters are really just auto-cue readers but there are some that grow on everyone and become famous personalities. These people dont have to worry about their jobs. The same seems to go for singers/groups - there are some that sound so generic that theres no point to them, but some that stand out. Unfortunately (Kym Marsh) they all have pretty much the same level of ego.
This comment does not represent the views or opinions of the user.
Bill: "How does he stay so current?"
Marty: "Don't praise the machine..."
Who did what now?
Not that I ever put much stock in voice recognition software anyway. From the Vocaloid FAQ:
"It is not easy"? Yeah, right. Not for long. Actually, this is something I've been waiting for since I saw a programmer mixing and encoding phonics in Hypercard, back in 1994. Of course, it won't be out for a while, and even longer for Macs. But oh, the suspense! :-D
D'oh!
I'm with you 99%.
from the article - "Barbra Streisand covering Iron Maiden."
Had this been a feature on windows, we would have called it the anti-viagra.
Of course, since its on Mac,..we've got geeks getting wood instead!
Pavlov says 'sit'.
zack
I am not sure why this would be scary. For those of us who don't have a singer on staff, it is pretty cool! (Particularly once the price comes down and when it becomes even more sophisticated).
This will *increase* the artistry and creativity of many people and of the population as a whole. How many people are good song writers? Quite a lot. How many of them can sing too. Not as many. This will eventually let those who can write do recordings too.
It lets more people be creative. It is called freedom.
So how long until we have a computer to do the job of record executive? Muahahahah.
"Learning is not compulsory... neither is survival."
--Dr.W.Edwards Deming
Britney's problem isn't that she can't sing, it's that she's lost her soul to the crap pop music machine and so she's only made to sing crap as a minor adornment to her manufactured pop idol image. She does at least have a voice, unlike some other manufactured "artists" ... Jennifer Lopez comes to mind.
You're absolutely right though, the way things are currently --- she might as well be replaced by Vocaloid.
[So combine] this with the story "Decoding the Algorithm for Pop Music" and a synthetic DJ and who needs the radio anymore?
Indeed. I haven't bothered with radio (for music, anyway) in years.
Downmodding is the refuge of the weak. Don't downmod, make a better argument!
This sounds very useful, except for the following little detail in the statute:
In order for a compulsory mechanical license to be valid, the copyright owner must have authorized the commercial release of the song
So, it seems that the publishers/studios/RIAA could plug this loophole simply by not providing the required authorization to the party that applies for the mechanical license.
She never really recreated instruments, but she did some interesting things with alternate tunings, which created an entirely different timbre.
First of all, the write-up is misleading. We are nowhere near having machines that can sing indistinguishably from humans.
:)
Secondly, even if we did have such synthesizers, it certainly wouldn't put conventional artists out of work. For example, we have computer-controlled tools and painting equipment that can create flawless furniture, or paint a perfect, photo-realistic portrait.
But what kind of furniture/paintings are pulling in the big-bucks at auctions? That's right - the ones made by humans. "Hand-made" furniture costs quite a premium over the "perfect," mass-produced stuff. Trust me - my wife and I are trying to furnish a house.
People don't just like Eminem for the sounds he puts on his CDs - they like his persona, his attitude, the ambiance he embodies. They're buying Eminem, not just some tones, optically encoded onto a slab of plastic-laminated aluminum. It's the artist that sells, every bit as much as the work itself.
Like woodworking? Build your own picture frames.
That's really good anime.
We are Turing O-Machines. The Oracle is out there.
You folks can stop poo-pooing this technology. The software won't compose the damn song for you. You still gotta compose the melody, write lyrics, ... THEN you use the voice "font" and have it sing the melody.
Alot of composers today will sing their own vocals temporarily and then re-record with a pro singer when they're done tweaking the song. THis software lets them have much higher quality vocals for that interim stage.
No, it would make NSync a Beowulf cluster of this.;)
Is this a sigs-optional kind of place? 'Cause I am totally down with that if you know what I mean.
Only test pilots need fear the result, fear not.
And credit to her. Using technology to process the signal from physical instruments (within reason) preserves the nuances that make them sound real and interesting, if we were limited to basic instruments and simple microphones then life would not be nearly as varied.
My objection to the OP is that they were promoting the replacement of an instrument (the human voice here) from the ground up with synthetic technology, and I stand by my previous assertation that this is not a good idea because it produces very sterile music.
MP
The techno-classical music in A Clockwork Orange. You can tell there's some human element in the creation of the work, but the execution / production is very 'mechanical'.
Eerie, if you ask me.
Who put this thing together? Me, that's who.
since when was this new technology? plenty of geek bands have been using midi-synced text-to-speech technology for years (console, 386dx, etc)... granted, text-to-speech is still not that great, but it's only a matter of time...
i guess this is the way most things are... a certain technology could be available for years.. but it's not officially "new" until some newspaper says so
???!?!?!?!!?
I suppose "an on-camera performer in television" might not think the following list is "artistic":
1) Animation artists replaced by programming
2) Drummers replaced by Drum Machines
3) Orchestras replaced by sampling music workstations
4) Composers replaced by sampled digital tracks by older artists
5) Horn players replaced by sampled recordings in keyboards
Just my short list -- you can add others. While the virtual singing is an interesting bit of news, the replacement of artists by machines started more than 20 years ago.
Sleep is for the Weak
If you can synthesize music from MIDI and vocal models, you can use that deal. The RIAA can't stop you from doing this.
No, but if you use a MIDI sequence that you didn't create yourself, the mechanical copyright administrators (ASCAP, BMI) might come after you on the grounds that the MIDI sequence is a derivative work of the artist's original piece.
In Slashdot terms, it would be kind of like using GPL'ed code in your software and then distributing it without making source available.
Now the RIAA and/or its members can kill off all of their top selling artists and raise the prices of the late artists' albums and perpetually discover "previously unreleased tracks".
Artists will sing more than the exhaustion of all the breath given to them for the spans of their lives, and the RIAA will have the copyrights until their great-grandchildren's great-grandchildren die... or longer.
I am certain that the investors' board will be happy.
It is such a great time to be a monopolist!
All data is speech. All speech is Free.
Finally we can be done with these pop start idiots. These people drive me nuts. They don't have a band, they don't write their own music, they just sing and look pretty, make videos and tell kids on MTV what's "cool". I hope one day the RIAA can replace them all. That might cause me to throw a little respect back their way. As for real bands, you know, where people play instruments and some sing and they actually, gasp, write thier own music, they won't ever be replaced.
Can "Synthesized Idol" be far behind? Oh wait, isn't that redundant?
By reading this sig, you agree to the terms of my sig license.
True story.
From the article: Digital technology can produce something clear enough to convey meaning, but only in a clipped monotone that sounds more like a robot than a real live person.
Did it occur to the author that perhaps the reason these synthesized voices "sound like a robot" is that robots really don't have much of a choice?
Suprisingly, Hawking's complaints are not that he "sounds like a robot", but that he sounds like an American.
Soon our robots will be able to sing with style, but will still talk funny.
like g-a-r-y, only different
Singing is probably easier to model than speech. This is because the sounds (phonemes, what have you) are simpler. In fact, certainly languages are probably easier to synthesize than English because there are less sounds.
At any rate, pop crap doesn't demand emotion in the first place; that's why it's pop crap. Replace Britney with a synthesizer and who could tell the difference?
The article's very sketchy, unfortunately. I'd be interested in knowing what this system uses for input. A standard score (five-line staves, syllables associated to notes?) or a custom representation system with both full phonetic transcription and enhanced MIDI-type musical information?
It's one thing to generate a computerized singing voice. Even if you need to tweak it, it's a cool achievement and may be useful to composers. But it's another thing entirely to have all the text-to-speech and intonation work without any human intervention.
As others have said, computer singing has been done before. Here's one example:
Virtual Singer
Alexandre http://enkerli.wordpress.com/
Hmmm. Fonts. Sounds like they want to do to singers what computers did to typesetters...
"Learning is not compulsory... neither is survival."
--Dr.W.Edwards Deming
Seriously, I think this stuff would only be useful for "special effects" like Cher used on that "Life after Love" song.
I can get results almost as good just using the Mac speech synthesizer.
I love Pizzicato Five's songs in English as much as the Japanese. Even "Happy Sad," where Maki Nomiya sings in very convincing English, right up until the line:
:-)
"Don't care if I'm mad or grad / make me feel so happy sad"
She was doing so well, too...
"The musician acquires craft in order to operate in the world. The requirement to enter a craft is that we allow the craft to enter us. To enter the musical life, we allow the music to enter us. The aim of the musician is to be played by music. If this is so, the musician has two concerns: First, being available and open to music when the musical current turns on; Second, having sufficient skill to place at the service of the musical impulse."
- Robert Fripp, "Guitar Craft", Guitar Player, 1986.
Man, I've been talking about something like this for years, telling my friends the potential of something like this.
Think of the possibilities -
1. Yeah, you can have Elvis sing you some GWAR.
2. Have James Earl Jones read you bedtime stories from any ebook.
or
2a. Have ol' James reprise his role 50 year from now in a Star Wars remake.
3. Save HUGE amounts of storage space - a midi file vs a wav or mp3 file...10k midi, 5,000k mp3, 50,000k wav.
4. And, save bandwidth - you could download full albums or audio commentary in split seconds instead of minutes or hours.
5. Real-time voice translation. Talk into a mic, use voice recognition software to convert to text, straight to this output in a different voice - ever wanted to sound like Les Claypool? How about Marlon Brando? Easy with this...and in real-time.
5a. Potential for VoIP here?
If we can 'map' each person's voice, not necessarily through samples but through descriptive equations (I believe eventually it will be done - a 3d characteristic model of the larynx and anything pertaining to voice that makes us distinct), we could attach that as a header to a text file, or if you want feeling, a voice-midi file with more descriptive info. It's make for some crazy pranks, but could also be hugely benificial.
I've been itchin with this idea for a while, hope I see it come to light.
Hi folks:
h ive/169.html
v e/062.html
v oice-sy nthesis/example/
e /234.html
Here are some more examples of computer singing of the past, some of them featured on the great 365 days project. Note: all those samples will be removed in January 2004.
DECTALK voices sing Lee Hazelwood obscurity:
http://www.otisfodder.com/365days/arc
The original "Daisy":
http://www.otisfodder.com/365days/archi
Daisy again , duetting with Perry Cook's SPASM/Singer (NeXT).
Note: this is a NeXT snd file.
http://www.funet.fi/pub/sci/audio/singing-
also, this fine fake singer:
http://www.otisfodder.com/365days/archiv
There are plenty of singing computer links out there if you look!
happy listening!
-- Real Stupidity is the Artificial Intelligence of the 21st century
Get out of the studio and in front of an audience, then.
Let's put you and your bitchin' sampler rig up in front of a crowd. A small but attentive one. Throw down, ace. Do something that will really connect with these folks and make them remember you.
I work with musicians. Real ones. Some are international names, others may only be recognizable to their local bar crowds. But they can all play music, without programming (or even electricity if necessary) at a moment's notice. And for some strange reason, people seem to still dig this.
All the technology in the world won't replace basic communication skills. I'll take one good picker over a room full of DP 4.1s any day of the week. He'll be better conversation after the gig.
In other news, astrophysicists have announced that they now know what all that dark matter is: it's stupidity.
This is not text. (stupid lameness filter)
Caveat Emptor is not a business model.
I have seen this program called Virtual Singer and it has been doing something similar for a while. I tried to get a sample mp3 from their website, but the links weren't working.
As far as I know this program is actually synthesizing rather than basing it on samples and they have a "Real Singer" module that does it based on samples. It has a score that you can make and it will sing to the notes on your score.
A distinctive mark, characteristic, or sound indicating identity
I am not saying that other types of music were bad or non-creative. The nature of Jazz and yes traditionally played Baroque (I didn't bother mentioning it because today the "Purists" took over the music and play it as written and it normally played that way), is hard to to brake down mathematically, thus hard for a computer to come up with a good approximation (thus the topic of the article). MIDI is a poor example of computer generated music. MIDI was designed to give a good approximation with small amount of storage, and yes the rhythm and pitch is perfect, but the sound isn't, if you listened something done by a master with csound or some more advanced tools, the artist of csound portrays the feeling in the music.
If something is so important that you feel the need to post it on the internet... It probably isn't that important.