“Software Morphs Rapper Prodigy Into Global Cipher”
Rapper Prodigy’s new album could conceptually be delivered any any of almost 1500 languages IN HIS OWN VOICE thanks to speech conversion software.
“The prospect of having fans understand what I’m saying and repeat it in their language (drew me to) the company,” said Prodigy in a phone interview just before he began a jail term for illegal gun possession. “Now, fans will like more than just the beat or the rhythm. They’ll understand what I’m saying and relate to it.
(excellent paragraph)
Here’s how the Voxonic translation process works. After translating the lyrics by hand, the text is rerecorded by a professional speaker in the selected language. Proprietary software is used to extract phonemes, or basic sounds, from Prodigy’s original recording to create a voice model. The model is then applied to the spoken translation to produce the new lyrics in Prodigy’s voice.
What?!
“A 10-minute sample is all we need to imprint his voice in Spanish, Italian or any language,” said Deutsch.
Now thats just scary-cool. I wonder what famous speeches were culled and parsed for phoneme samples, and what the developers had the orators saying.
Conceivably, you could arrange phoneme samples like beats for a song and re-articulate anything. A video artist in Germany has already done a similar project using video samples from Michael Jackson interviews. The end result was an eerily realistic digital Michael Jackson who would accurately say anything the artist “asked” him to, gestures and all.
Voxonic’s software is able to convert any bit of recorded text into 1,468 different languages with 99 percent accuracy, according to the company.
One audiobook, translated into several languages; one album translated hundreds of times over. A contemporary point-and-click babelfish. Goodbye to overdubs.
Click here to read the rest of the article at Wired.
