Soon, computer-generated songs comparable to human singing (re-issue)

Washington, May 8 (ANI): Making computer-generated vocals a success has been a distant dream, since the tweaking of the frequency curve is labor intensive and prone to human error.

But now, Japanese scientists have refined the production of synthetic vocals by copying the frequencies of human voices.

Akio Watanabe and Hitoshi Iba have devised an algorithm that takes eight frequency curves from human samples with random parameters and feeds them into a Vocaloid program.

First, production of the first generation involves making eight individual curves with random parameters and feeding them into Vocaloid.

The second step is for the music producer to listen to the effect of each curve on their synthetic vocal and to move slider bars in the software interface to reflect how well each curve works.

In the third stage, the best curves are used as the "parents" to create a new generation of curves. Finally, the second generation curves undergo crossover and random mutation and the process repeated from step 2.

Eventually, the fittest frequency curves will emerge that endow the synthetic vocal with the most realistic characteristics of human singing. (ANI)