The software synthesizes speech in a foreign language but keeps it in a voice that sounds like yours. It was demonstrated at Microsoft's Redmond, Washington, campus on Tuesday by research scientist Frank Soong.
He was able to show the software reading out text in Spanish using the voice of his boss Rick Rashid, and then demonstrated a Mandarin translation using the voice of Microsoft's chief research and strategy officer, Craig Mundie.
"For a monolingual speaker traveling in a foreign country, we'll do speech recognition followed by translation, followed by the final text to speech output [in] a different language, but still in his own voice," said Soong.
The new software could be used to help students learning a foreign language too. The system needs about an hour of training to develop a model capable of reading out in a person's voice.
Hear demonstrations of translations at MIT's Technology Review website.
Written by: James Delahunty @ 11 Mar 2012 11:14
