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
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
"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. (> <)
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?
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.
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)
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
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
Combine these synthetic vocals with some randomized instrumentals and pipe it into your 'hitablity` algorith (covered here and here) and generate endless pop music!
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.
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?
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
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.
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.
What is wonderful about this is that (initially at least) it will devalue the type of generic boy/grrl band trash music which so saturates the current pop market. That's got to be scary for organisations like the RIAA, who actively market the interchangeable swill.
When pitch perfection and standardised voices are available from a $300.00 software package, music made by people with interesting voices and offbeat musical philosophies will be that much more valuable.
After all, it seems unlikely that there'll be a software Tom Waits or a digital Johnny Rotten in our immediate future. Punk revival anyone?
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
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.
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 -->
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 !
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...
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?
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
Theee coh. maydor ahhmiigahh... ws dooweng theez. Ten yeez ah. go.
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...
Only test pilots need fear the result, fear not.
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.