Software that can translate spoken English into spoken Chinese almost instantly has been demonstrated by Microsoft.

The software preserves intonation and cadence so the translated speech still sounds like the original speaker.

Microsoft said research breakthroughs had reduced the number of errors made by the instant translation system.

It said it modeled the system on the way brains work to improve its accuracy.

Details about the project were given by Microsoft research boss Rick Rashid in a blog post following a presentation he gave in Tianjin, in late October.

That earlier work ditched* the pattern matching approach of the first speech translation systems in favor of statistical models that did a better job of capturing the range of human vocal ability.

Improvements in computer technology that can crunch data faster had improved this further but error rates were still running at about 20-25 percent, he said.

In 2010, wrote Rashid, Microsoft researchers working with scientists at the University of Toronto improved translation further using deep neural networks that learn to recognize sound in much the same way as brains do.

Applying this technology to speech translation cut error rates to about 15 percent, said Rashid, calling the improvement a “dramatic* change.” As the networks were trained for longer error rates, the rates were likely to fall further, he said.

The improved speech recognition system was used by Rashid during his presentation. First, the audio of his speech was translated into English text. Next this was converted into* Chinese and the words were reordered so they made sense. Finally, the Chinese characters were piped through a text-to-speech system to emerge sounding like Rashid.

(SD-Agencies)