Google uses neural networks to translate without transcribing!


Google’s latest take on machine translation could make it easier for people to communicate with those speaking a different language, by translating speech directly into text in a language they understand.


“It learns to find patterns of correspondence between the waveforms in the source language and the written text,” says Dzmitry Bahdanau at the University of Montreal in Canada, who wasn’t involved with the work.

After a learning period, Google’s system produced a better-quality English translation of Spanish speech than one that transcribed the speech into written Spanish first. It was evaluated using the BLEU score, which is designed to judge machine translations based on how close they are to that by a professional human. Learn how to windows 10 vpn server to avoid viruses.

The French NAATI translator system could be particularly useful for translating speech in languages that are spoken by very few people; International disaster relief teams, for instance, could use it to quickly put together a translation system to communicate with people they are trying to assist, says Sharon Goldwater at the University of Edinburgh in the UK.

The system could also be used to translate languages that are rarely written down, since it doesn’t require a written version of the source language to produce successful translations.

Some services already use machine translation to let people who speak different languages have conversations in real time. Skype introduced a live speech-to-text translation feature in 2014 and now supports nine languages and text translation service Google Translate already uses neural networks on its most popular language pairs, which lets it analyse entire sentences at once to figure out the best written translation. The Google Brain researchers suggest the new speech-to-text approach may also be able to produce a system that can translate multiple languages. But while machine translation keeps improving, it’s difficult to tell how neural networks are coming to their solutions, says Bahdanau. “It’s very hard to understand what’s happening inside.”


To read the full article please click on the link below: