No need to sing like a robot now
( 2003-12-18 11:01) (Agencies)
Imagine having a singer with a world-class voice at your disposal, any hour
of any day. She's just standing there to perform whatever silly song you might
make up for her.
Friends of Madonna or Britney Spears may already have had that pleasure, but
for everyone else, a new technology called Vocaloid may offer the next best
thing.
It was developed at Pompeu Fabra University in Spain and financed by Yamaha
Corp. The software is due to be released to consumers in January, costing about
US$200. It allows users to cast their own or anyone else's songs in an unreal
but incredibly lifelike concert-quality voice.
A computer equipped with Vocaloid will be able to "sing" whatever combination
of notes and words you want it to.
The human voice has proven the most difficult of all sounds to synthesize. It
usually comes out in a boring voice that sounds like a robot. But, Yamaha seems
to have solved the problem.
You can think of the software as a kind of audio font: Musical notes and
lyrics can be translated into the chosen voice, then saved to be played later,
just as a word processor might translate a text into a different font and print
it out.
These fonts are made up of a database of phonemes, the basic sounds that make
up any language. To create the database, technicians record a singer performing
as many as 60 pages of different sounds. The result is a replay of the singer's
voice, says Ed Stratton, managing director of Zero-G, a company in London that
owns the Vocaloid technology.
|
