Artificial child's voice 'created'

Scientists claim to be working on a unique project to create an artificial child's voice. A team from Media LT, a company developing tools to assist disabled persons, and Lingit, a software company, says it's developing Norway's first synthesised childlike voice -- the research, in fact, involves converting the master voice into a comprehensible kid's voice.

"We start with what is known as a master voice, which is the product of three or four adult speakers recording several thousands of phrases. Then we record a single child reading a smaller number of phrases aloud.

"We use this recording to modify the master voice, making it sound like a child's voice," said team member Torbjorn Nordgard at Lingit, who is also a professor of linguistics at the University of Nordland.

The phrases recorded by the child have been selected to include a number of the most essential sounds found in Norwegian, according to a release by the Research Council of Norway.

"The master voice still carries the intonation, ie, a phrase's melody. The result sounds rather like a child with unusual elocution skills, but it's still much better than the voice of an adult," said Nordgard.

Everything is now in place to start testing trial versions of the child's voice. "We hope to have a beta version in place this summer," said team member Magne Lunde.