
Microsoft demonstrated a software that can translate spoken English into spoken Chinese almost instantly. 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 modelled the system on the way brains work to improve its accuracy. Details about the project were given during a presentation in Tianjin, China. Spoken words were almost instantly turned into Chinese by piping the spoken English through Microsoft’s translation system. The machine-generated version of the words can even maintain some of the spoken style …
The earlier work from Microsoft ditched the pattern matching approach of the first speech translation systems in favour of statistical models that did a better job of capturing the range of human vocal ability. The company researchers working with scientists at the University of Toronto improved translation further using deep neural networks that learn to recognise sound in much the same way as brains do. Applying this technology to speech translation cut error rates to about 15 percent, the software giant calling the improvement a “dramatic change“.
The improved speech recognition system first translate the audio speech into English text. Next this was converted into Chinese and the words reordered so they made sense. Finally, the Chinese characters were piped through a text-to-speech system to emerge sounding like the native tongue from the speaker. There are still likely to be errors in both the English text and the translation into Chinese, and the results can be humorous. Still, the technology has developed to be quite useful. We are wondering could the system handle a Chinese to English vice versa.
SOURCE: BBC
POPULAR STORIES







FEATURED VIDEO
RECENT UPDATES


M.I.C. REVIEWS




LATEST M.I.C. PRODUCTS
HOT ARCHIVES
LATEST COMMENTS
STAY IN TOUCH