Yamaha Releases Singing Synthesis Software

loopdloop writes "The world's first singing synthesis software, Vocaloid, was released by Yamaha this month at the Los Angeles NAMM show. Simply type in the lyrics and notate the vocal expressions to create a completely computer-generated singer. There are also audio demos of the product available." Update: 01/26 21:14 GMT by S : An earlier NYT-authored preview of this software has also been covered on Slashdot.

Comments

Human voice

[Anonymous Coward]

Machines can _never_ beat human voice. No matter how much technology advances, it will never happen. We are lucky to have emotions - machines can never become emotional. It's all just fake.

Re:Human voice

[spun]

Machines can have emotions if we want them to. There was even an article in last month's Scientific American by an AI researcher who claims that machines will need emotions for real AI to work. There have been several robotics/AI projects that have attempted to incorporate emotions, Cynthia Breazeal's robot Kismet being the most famous.

Emotions are an information processing system that works holistically, priming the logical parts of the brain for the kind of work they will need to do. Big orange and black stripey thing running towards you? Prime the brain for a flight or fight response rather than curiosity, i.e. "Run, it's a tiger!" not "I wonder if this orange and black stripey thing wants to play?"

There remains the problem of qualia. That is, a robot may look for all intents and purposes as if it is having emotions, but does it feel the same things internally as we do? Unfortunately, there's no real way of knowing if even other humans feel the same thing we do.

When the day comes that a robot belts out a blues song about someone done it wrong and broke it's heart, we will judge it in the same way we judge human singers: Does it look and sound authentic, or is it faking it? If it looks and sounds authentic, I believe that we will take it for granted that it feels the same as we do, just as we take it for granted in other humans.

Re:Human voice

[cduffy]

I've done my time in a "philosophy of AI" class -- and frankly, as far as I'm concerned, the Chinese Room argument and the like are bogus. If it looks like a duck, walks like a duck, quacks like a duck -- it's a duck, at least until someone finds out that it doesn't in fact keel over when given cyanide-laced bread and has to plug itself in to charge its batteries every so often.

Consider: For the purposes of this thread, AI is considered incomplete due to inability to simulate emotions why? Because it's argued that the desired output (emotionally-charged vocalization) is impossible without a precondition which is argued to be impossible. If the output were indeed achieved, then for the purpose of its singing, would the system not for all intents and purposes be emotional, even if one is unable to demonstrate that the system actually experiences qualia? (After all, if we're unable to make this demonstration wrt other humans, why make it a requirement for nonhuman intelligence?)

Granted, I also think that a machine which can pass an unrestricted Turing Test over an extended period can be safely be considered capable of thought, so it's obvious which side of this debate I land on. :)

Re:Anybody ever say to themselves....

[Anonymous Coward]

Well, don't let yourself become stale. Do something innovative on your own time. You're not dead yet...

Mandatory Radiohead quote

[Petronius]

Fitter, happier, more productive
Comfortable
Not drinking too much
Regular exercise at the gym
(3 days a week)
Getting on better with your associate employee contemporaries
At ease
Eating well
(No more microwave dinners and saturated fats)
A patient better driver
A safer car
(Baby smiling in back seat)
Sleeping well
(No bad dreams)
No paranoia
Careful to all animals
(Never washing spiders down the plughole)
Keep in contact with old friends
(Enjoy a drink now and then)
Will frequently check credit at (moral) bank (hole in the wall)
Favours for favours
Fond but not in love
Charity standing orders
On Sundays ring road supermarket
(No killing moths or putting boiling water on the ants)
Car wash
(Also on Sundays)
No longer afraid of the dark or midday shadows
Nothing so ridiculously teenage and desperate
Nothing so childish - at a better pace
Slower and more calculated
No chance of escape
Now self-employed
Concerned (but powerless)
An empowered and informed member of society
(Pragmatism not idealism)
Will not cry in public
Less chance of illness
Tires that grip in the wet
(Shot of baby strapped in back seat)
A good memory
Still cries at a good film
Still kisses with saliva
No longer empty and frantic like a cat tied to a stick
That's driven into frozen winter shit
(The ability to laugh at weakness)
Calm
Fitter
Healthier and more productive
A pig in a cage on antibiotics

Re:So...

[mcpkaaos]

The irony behind your comment is that vocals from "artists" such as Britney Spears, Christina Aguilara (sp), etc, go through extreme re-engineering after recording (beyond the norm of compression, reverb, EQ, etc.) Once the audio is filtered through tools that re-pitch the parts that go off-key and time-stretch the bits that fall out of rhythm, you have an end result that really isn't all that far from a computer generated voice.

Sorry, but,...

[El]

I'm sure Britney's "talent" has absolutely nothing to do with her ability to do vocals, and absolutely everything to do with her abilility to take off her clothes...

walk the walk, or talk the talk

[Doc Ruby]

Talk is cheap, so if you can't implement your invention, punt! Explain it in detail in public, or among a relevant developer group. Then you at least have a chance of being in on the creation, along your lines of vision, and at least get your world bettered, even if you can't cash in by doing the hard part. The joy of coinvention sure beats the bitterness of "coulda, woulda, shoulda". Most of the open source process is based on that crosspollination and mutual assist. Hell, if we all did this better, maybe the docs would get written *first*, rather than never-quite.

Re:Quality

[ackthpt]

If you get rid of the background instruments, the synthetic voice still sounds ... well... synthetic.

So it fits right in with most of the pap on the top 40.

The real sham is all the manufactured music that's been out there for years and increasing. Just program it a dictionary and it'll do rap, too.

RIAA?

[wviperw]

I wonder how long it takes before RIAA gets their grubby little fingers on this bad boy and makes it illegal to type in known lyrics... (copyright infringement!! right? :P)

Re:One for the road...

[psychoticmelody]

why eliminate musicians? is there no room in life for art anymore? also, if those "unskilled morons" flooded the job market, where would you go? musicians put hard work into their jobs too. although, pop idols today don't seem to. sorry, i had an offtopic rant as well. I'd be glad to see less petty musicians as well, but i don't see why all musician should be eliminated.

Is not

[filtersweep]

I have several vocoders, software and hardware, and it is obviously a very different creature if you took the time to listen to the demos. Also, a proper vocoder needs an carrier, and it does not generate the vocal qualities. It merely functions as a formant filter (where the constanants are provided by the vocalist, and the pitch by usually a synthesizer).

Frankly, this thing just really needs a good plug-in format, like TDM or VST and it will be a gold-mine- not unlike those god-awful pitch-correction plugins that were reputed to give Cher that plastic effect to her voice (like she doesn't have enough plastic as it is). As a standalone app, it is doomed.

Re:I'm impressed.

[radish]

Jean Michel Jarre used computer based composition (I believe it was based on some kind of genetic "evolution" mechanism) for one of the tracks on his 1990 album "Waiting for Cousteau". It is, to my ears, rather dull, but there you have it :)

Re:Really Bad Synths

[King_TJ]

Your argument is no more credible than the curmudgeons who said that an electric piano sounds so unlike a real piano that it's a total waste, and nobody would ever perform a legitimate creative work using one.

Think "new tools at an artist's disposal", and "dawn of a new type of digital instrument" instead. If you want this software to sound good in your music mix, you're going to have to invest a considerable amount of time and effort setting it up properly and recording it properly. Therefore, it takes *talent* to make it useful.

Not only that, but the male and female "singer" Yamaha is offering are only the first 2 of what promises to be a whole slew of virtual singer software packages one can purchase. It stands to reason that the first 2 would be the most "generic" - since they're mostly there for proof of concept purposes, and to cover as wide an audience of potential customers as possible.

As a hobbyist-musician myself, I think this is a great step forward. It's not going to *replace* real singers any more than drum machines replaced drummers. Instead, it will provide more options to people trying to create different sounds, plus help musicians work on "rough drafts" of songs without all the other musicians having to be present.

(Actually, with drum machines, I find that real drummers do the best job programming them. I think it will be similar with this software. A real vocalist will know exactly what inflections and volume changes should be programmed in to make the virtual vocalist sound best in an application.)