Phone call translator app to be offered by NTT Docomo

 

Richard Taylor reports on the phone app claiming to translate calls in real time

Related Stories

An app offering real-time translations is to allow people in Japan to speak to foreigners over the phone with both parties using their native tongue.

NTT Docomo - the country's biggest mobile network - will initially convert Japanese to English, Mandarin and Korean, with other languages to follow.

It is the latest in a series of telephone conversation translators to launch in recent months.

Lexifone and Vocre have developed other products.

Alcatel-Lucent and Microsoft are among those working on other solutions.

The products have the potential to let companies avoid having to use specially trained multilingual staff, helping them cut costs. They could also aid tourism.

However, the software involved cannot offer perfect translations, limiting its use in some situations.

Cloud technology

NTT Docomo unveiled its Hanashite Hon'yaku app for Android devices at the Combined Exhibition of Advanced Technologies (Ceatec) show in Japan earlier this month, and plans to launch it on 1 November.

It provides users with voice translations of the other speaker's conversation after a slight pause, as well as providing a text readout.

"French, German, Indonesian, Italian, Portuguese, Spanish and Thai will be added for this application in late November, raising the number of non-Japanese languages to 10," the firm said in a statement.

"Fast and accurate translations are possible with any smartphone, regardless of device specifications, because Hanashite Hon'yaku utilises Docomo's cloud [remote computer servers] for processing."

The caller must subscribe to one of Docomo's packages to be able to use it.

Graphic for NTT Docomo app NTT Docomo's app offers both voice and text translations of phone conversations
Landline translations

NTT Docomo will soon face competition from France's Alcatel-Lucent which is developing a rival product, WeTalk. It can handle Japanese and about a dozen other languages including English, French and Arabic.

Start Quote

We want to allow conferences with 10 people and four different languages, and the system would provide translations in every language needed”

End Quote Gilles Gerlinge Alactel-Lucent

The service is designed to work over any landline telephone, meaning the company has had to find a way to do speech recognition using audio data sampled at a rate of 8kHz or 16kHz.

Other products - which rely on data connections - have used higher 44kHz samples which are easier to process.

Alcatel-Lucent uses a patented technology to capture the user's voice and enhance it before applying speech recognition software. The data is then run through translation software before being run through a speech synthesiser.

The firm said all this could be done in less than a second. However, it has opted to wait before the speaker has stopped talking before starting the translation after experiments carried out with workers at insurance company Axa suggested users preferred the experience.

"We are still working on improving the system," Gilles Gerlinger, the product's co-founder, told the BBC.

"You can do conversations with one person, but we want to allow conferences with 10 people and four different languages, and the system would provide translations in every language needed.

"We also have a project called MyVoice which can have a synthetic voice that sounds like your real one."

Mr Gerlinger suggested that his firm would make money from the product by renting servers with the necessary software to big businesses, and charging smaller ones a fee for the amount of time they used the service.

Converted video chats

Microsoft's Research Labs has also been working on a technology it calls the Translating Telephone. The firm has acknowledged that one of the biggest problems was making the software adapt itself to cope with different ways people pronounce words.

Lexifone graphic Start-up Lexifone charges users for its service depending on the length of their telephone call

"The technologies are still not perfect," said researcher Kit Thambiratnam in 2010.

"But we feel they are good enough for two people to communicate in their native languages, as long as they are willing to speak carefully and maybe occasionally repeat themselves."

Google already has a Translate app that can translate 17 spoken languages, allowing face-to-face conversations with a foreigner, but it is not yet designed to work with telephone calls.

Start-up Israeli company Lexifone is hoping to get a head-start with its own phone conversation product.

It launched earlier this year offering translations between English, Spanish, Portuguese, Italian, French and Mandarin.

Its chief executive, an ex-IBM computer engineer, has ambitions to disrupt the human translation industry which he said was worth $14bn (£8.7bn) a year.

"Our original plan was for annual growth of 200%," Ike Sagie told Reuters last month.

Vocre screenshot The Vocre app won the Audience Choice Award at the Techcrunch Disrupt festival

"The way we see market acceptance and the way we see the market welcoming the technology I think we have the potential for growing faster than that."

The firm is working with BT and Telefonica to offer its service to the phone networks' customers.

Meanwhile California-based MyLanguage, is pursuing another strategy by providing voice and text translations during video chats via its Vocre app for iPhones.

The facility - which is currently being beta tested - means that customers will need an internet connection to use it.

Lost in translation

Despite the ambitions of those involved in the nascent sector, one analyst questioned their chances of success

"These kind of real-time technologies have been 'two to three years away' for the past decade," said Benedict Evans, technology expert at Enders Analysis.

"Both speech recognition and machine translation are sort of there if you're not too fussy.

"But they are generally not as good as speaking the language itself, and my suspicion is that they would not reliable enough to use them for business purposes when you need to be really sure about what the other person said."

 

More on This Story

Related Stories

The BBC is not responsible for the content of external Internet sites

Comments

This entry is now closed for comments

Jump to comments pagination
 
  • rate this
    -1

    Comment number 114.

    This would help my wife and i immensely. Our son lives in Japan and is married to a japanese girl and while she and her father can speak good english the rest of her family cannot so we either have the option of sending letters and having them translated or phoning and talking to our son who translates. It would be great to be able to speak to our sons in-laws directly.

  • rate this
    +1

    Comment number 113.

    I work as a translator in Japanese to English. I would be astounded if this works in practice because so much of Japanese meaning depends on context, and this impacts on the way the language is structured. For instance, in most Japanese sentences, you omit the subject. Instead of saying "I went to the shops" you just say "went to the shops". Who went to the shops? You just know from context.

  • rate this
    +4

    Comment number 88.

    I'm a conference interpreter, and I have seen trials of similar systems. They work ONLY with very simplified use of language and - as yet - cannot cope with either accents or idiom. Neither can they distinguish between what people say and what actually mean. I am not unbiased, but I will be truly amazed if they can be used without fairly serious problems of comprehension. Not yet, anyway.

  • rate this
    +6

    Comment number 77.

    If it really worked then I would be very impressed, since correctly understanding the meaning of similar sounding words depending on the context of the sentence is something that currently only people can do!

    e.g "Where 'Would' the 'Knight' 'Spend' 'Money' if he 'Spent' the 'Night' in the 'Wood'?"

    Other languages would use different words, so one contextual slip could easily generate nonsense!

  • rate this
    +6

    Comment number 50.

    Nice in theory, very difficult in practice.

    Quite a lot of spoken language consists of 'Idioms' with no direct equivalent in other languages, e.g. 'Pulling my leg'.

    Attempts to literally translate idioms just generate gibberish, so whilst this might be OK for simple business transactions, normal social conversations could end up like the 'Monty Python - Dirty Hungarian Phrasebook' sketch ;-)

 

Comments 5 of 8

 

More Technology stories

RSS

Features

  • Man with typewriterLove to Patrick

    The official whose over-familiar letters infuriated his boss


  • Man's hands putting ring on woman's fingerName changer

    Why do wives take a man's name after marriage?


  • Person scratching their arm10 things

    Scratching really does make things itch, and other nuggets


  • Corsican flagCorsican mafia

    Are Corsica's days of mafia and militants over?


  • Mobil canopies on the A6 at Red Hill, LeicestershireEnglish heritage

    Zebra crossings to bus stations: unusual listed buildings


BBC © 2014 The BBC is not responsible for the content of external sites. Read more.

This page is best viewed in an up-to-date web browser with style sheets (CSS) enabled. While you will be able to view the content of this page in your current browser, you will not be able to get the full visual experience. Please consider upgrading your browser software or enabling style sheets (CSS) if you are able to do so.