We use cookies to provide you with a better experience. If you continue to use this site, we'll assume you're happy with this. Alternatively, click here to find out how to manage these cookies

hide cookie message
80,259 News Articles

Instant speech translation ready for mobile phones

Technology on show at Mobile Voice Conference

Instant speech translation, a longtime dream of science-fiction writers, is already feasible in certain situations, according to vendors at the Mobile Voice Conference in San Francisco.

Novauris demonstrated software running on a mobile phone that can instantly translate commonly used phrases, and another company, Fluential, discussed a server-based system that has been used for real-time interpretation in a hospital. Though neither is commercially available yet, both companies said they are technically ready to go.

A universal translator has been a longtime dream in science fiction, including the Star Trek TV series. Google reportedly said earlier this year it was working on one, and the merger of Dial Directions and Sakhr Software last year raised hopes for such a system.

The complexities of grammar and culture, on top of understanding vast vocabularies and processing spoken inputs quickly, have made that vision a hard one to realise. Cisco Systems said in 2008 it expected to offer real-time translation for its Telepresence video collaboration system the following year. The company subsequently said that getting accurate translations was harder than expected and it could not forecast when the feature would be available.

What Novauris and Fluential have developed can't translate all speech, but the software is designed to carry out translation quickly enough that users can converse at a relatively normal rate. Each is designed to overcome communication problems in specific situations.

Novauris CEO Yoon Kim called his company's proof-of-concept software a "flexible phrase translator". The tool is designed to let travellers speak certain phrases into a phone in their own words, without having to memorize a specific wording, and have them translated into the local language and read aloud to the person being addressed. To demonstrate, Kim said, in English, "I think there's a mistake in the bill," and had it automatically translated into a Japanese phrase. Then he said, "I'm afraid there's a mistake in the bill," and it was translated into the same Japanese phrase.

If the user's meaning is obvious enough, the translation happens automatically. If it's less clear, the software will display the standard phrase that it believes the user wanted to say and seek confirmation before it translates and speaks it to the other person, Kim said. The prepared phrases are crafted to make the interaction easier for both parties. For example, the software might use the phrase, "Please point me to the toilet" instead of "Where are the toilets?" because a non-Japanese speaker would not understand verbal directions to the restroom from a Japanese speaker.

The Novauris technology can also do two-way translation, in which each person's phrases are translated into the other person's language. As long as each uses simple phrases and doesn't ask open-ended questions, each party can speak and hear the conversation in his or her native language, Kim said.

Novauris has built in some cultural sensitivity to its system. For example, a blunt phrase stated in one language may be translated into a more polite expression in a language that values politeness, Kim said.

Any current smartphone has enough processing power and memory to run the software, which has been written in versions for Windows Mobile, iPhone and mobile Linux and will soon be adapted to Android. A new language could be added in just a few seconds, Kim said. Novauris is talking with partners, and Kim believes a product may be commercially available next year.

Fluential, which has developed speech translation products with funding from the US Defense Advanced Research Projects Agency (DARPA) and other government sources, showed off a system that uses remote processing to translate a wider range of conversations. Its software can be delivered as a service over a cloud infrastructure, deployed on a workstation in an enterprise's own data centre, or by other methods, said president and CEO Farzad Ehsani. The company is working on a smartphone prototype that would work over a 3G network.

"This is not a universal translator ... It handles 80 to 90 percent of common interactions for a given setting," Ehsani said.

Fluential's software includes both template translation, which handles standard phrases, and statistical translation, which is designed to interpret more open-ended speech. The company has tested it at a hospital in San Francisco, where real non-English-speaking patients used it to describe their ailments to medical professionals, Ehsani said. Nurses were trained for about 90 minutes on how to use it, and patients received about 40 seconds of simple instructions. The system achieved overall translation accuracy of 92 percent, he said.

In a hospital setting, these types of conversations are typically staffed by a human interpreter, at an overall cost of between $0.70 and $2.00 per minute, Ehsani said. With Fluential's system, it would cost about one-tenth or one-twentieth of that, he said.

The company is now preparing to bring to market a first implementation of its product, for conversations between nurses and patients, and Ehsani believes it could be on sale in six to nine months. Versions for other settings, medical and otherwise, are also in the works.

See also:

Mobile phone reviews

Mobile phone buying advice


IDG UK Sites

Samsung Galaxy S6 release date, features and specs rumours: When will the Galaxy S6 come out?

IDG UK Sites

Why people aren't upgrading to iOS 8: new features are for power users, not the average Joe

IDG UK Sites

Free rocket & space sounds: NASA launches archive of interstellar audio on SoundCloud

IDG UK Sites

iPad Air 2 review: Insanely fast and alarmingly thin. Speed tests, camera tests, beautiful...