Some Japanese researchers have apparently developed what they say is a program that can teach computers to sing (yes, sing) in voices that are “indistinguishable” from human voices.
Tokyo University’s IBA Laboratory, the tech-savvy people behind this development, say they have created a product that has a lot to offer:
For anyone who is bored with the so-called real-life characters that present themselves to TV “talent” shows, an optimized frequency curve and a synthetic vocal could be the new sensation they are looking for, but without the baggage of bad teeth, terrible hair extensions and fictionalized family tragedies.
That quote was included in The Register UK’s post about Vocaloid (that’s what it’s called) and the “computer singers vs real singers” debate. You can read more about the whole thing, including some complicated computer-speak about just how the vocals are modified by reading the rest of the post.
What do you think, are computer singers going to outnumber human singers anytime soon? Weigh in.