Last year Microsoft announced the release of its Neural Network based translation system for 10 languages: Arabic, Chinese, English, French, German, Italian, Japanese, Portuguese, Russian, and Spanish. Today, Korean is being added to the list.

Neural Network translation uses the full context of a sentence to translate words based not only on a few words before and after it, but on the full sentence, generating more fluent and more human sounding translations. This new AI-powered technology delivers the most significant improvement in machine translation quality since statistical machine translation became the industry standard 10 years ago.

Thanks to these improvements in quality and fluency, translations are the closest they have ever been to human generated ones.

HOW IT WORKS

At a high level, Neural Network translation works in two stages:

1. The first stage models the word that needs to be translated based on the context of this word (and its possible translations) within the full sentence, whether the sentence is 5 words or 20 words long.
2. The second stage then translates this word model (not the word itself but the model the neural network has built), within the context of the sentence, into the other language.

Neural Network translation uses models of word translations based on what it knows from both languages about a word and the sentence context to find the most appropriate word as well as the most suitable position for this translated word in the sentence.

One way to think about neural network-based translation is to think of a fluent English and French speaker that would read the word “dog” in a sentence: “The dog is happy”. This would create in his or her brain the image of a dog. This image would be associated with “le chien” in French. The Neural Network would intrinsically know that the word “chien” is masculine in French (“le” not “la”). But, if the sentence were to be “the dog just gave birth to six puppies”, it would picture the same dog with puppies nursing and then automatically use “la chienne” (female form of “le chien”) when translating the sentence.

Here’s an example of the benefits of this new technology used in the following sentence: (one of the randomly proposed on our try and compare site: http://translate.ai)

M277dw에 종이 문서를 올려놓고, 스마트폰으로 스캔 명령을 내린 뒤 해당 파일을 스마트폰에 즉시 저장할 수 있다.

Traditional Statistical Machine Translation would offer this translation:

“M277dw, point to the document, the paper off the file scan command Smartphone smartphones can store immediately.”

Neural Network translation, in comparison, generates this clear and fluent sentence:

“You can place a paper document on M277DW, and then save the file to your smartphone immediately after the scan command.”

The Neural Network translation systems are available for you to use through many entry points:

• Browser: We’d love your feedback on the new Neural Network Korean translation system vs. the legacy statistical one! Visit our try & compare site: http://translate.ai
• Microsoft Translator live feature: When using our new personal universal communicator feature, Microsoft Translator live, neural translations will also be used. For instance, if you use this feature to translate a live presentation from any of the nine supported speech languages to any of the 11 NN-powered translation systems, subtitles will be delivered using Neural Network technology: http://translate.it 
• Instant Messages in Skype: Translate instant messages (from and to any of these 11 languages) using the Skype Translator feature in Skype desktop and Skype Preview for Windows 10.

In addition, developers can easily integrate Microsoft Translator Neural Network systems by using the category “generalnn” in their API calls. There is no extra cost in using our neural network models vs. the existing statistical ones so don’t hesitate to use them!

For speech translation projects, the Microsoft Translator speech API already uses neural network translations from any of our 9 speech translation languages to all the 11 neural network powered languages.

Learn More:

How Neural Network translation works?
Microsoft Translator live feature: the personal universal translator
Microsoft Translator apps
Microsoft AI

The post Korean Becomes Microsoft Translator’s 11th Neural Network Translation Language appeared first on Microsoft Translator Blog.

During Nadella’s conversation with Kara Swisher and Walt Mossberg of the Re/code tech website relating to a new era of personal computing, he asked Gurdeep Pall, Microsoft Corporate Vice President for Lync and Skype, to join him on stage. While on stage, Pall demonstrated for the first time publicly the Skype Translator app, with Pall conversing in English with German-speaking Microsoft employee Diana Heinrichs.

Watch the Demo

Your browser does not support iframes.

Speech has been a natural evolution of the translation work that Microsoft has been delivering to consumers and businesses across a broad number of products and solutions. The work represents over a decade of work within Microsoft Research that has become a reality through a series of remarkable research advances in translation, speech recognition, and language processing. This demonstration is the next step in delivering the real time speech translation experience to users that Rick Rashid, then the worldwide head of Microsoft Research, demonstrated a year and a half ago.

The Skype Translator app will available first on Windows 8 later this year as a limited beta.

It has been an exciting day as we unveil this remarkable technology advancement that brings people one step closer to removing barriers of communication regardless of language or location!

Learn More about Skype Translator

• Skype Translator from Microsoft Video
• TechNet Blog Post from Gurdeep Pall, Corporate Vice President of Skype and Lync at Microsoft
• Microsoft Research Feature Story: Enabling Cross-Lingual Conversations in Real Time
• Code Conference Coverage of the Demo

The post Unveiling Breakthroughs in Real-Time Translation with Skype Translator appeared first on Microsoft Translator Blog.

A couple of weeks back, at the 14th annual Computing in the 21st Century Conference, attendees saw a glimpse of where else these technologies are taking us – and loved it. Rick Rashid, who heads up Microsoft Research worldwide, went up on stage and in the span of eight sentences, got the 2000+ strong crowd up on their feet and cheering. It was a moment where technology was indistinguishable from magic – and one that would spur science fiction writers to start thinking of bigger challenges for researchers to tackle 🙂

Watch the video to see for yourself:

A combination of powerful technologies were employed to make this amazing demonstration possible: Deep Neural Network based processing combined with high performance computing allowed a significant jump in accuracy of speech recognition. The Microsoft Translator technology that you use each day was customized to best fit Rick’s speech content. New speech synthesis technology that allows personalization of acoustic characteristics was able to create “Rick’s voice” in a language he does not speak. You can read Rick’s blog post here.

Some of these technologies are already available today, especially the industry-leading translation (Microsoft Translator) with customization capabilities (Translator Hub). If you are a Windows Phone user, you have been enjoying the most innovative translation app on any phone for over a year now, which includes an early speech translation experience that has been tuned for travel situations. The audio output that you hear on Bing Translator website uses some of the newer speech synthesis engines coming out of our Speech research. Deep-Neural-Net research is also behind our audio/video indexing service – MAVIS, which is available commercially.

The excitement that has been rippling across the web in response to this demonstration is an indicator of how much everyone wants to experience this ‘magic’. There is much work to do, but you will see the benefits of this amazing research in our products in our future releases.

Vikram Dendi
Director
Microsoft/Bing Translator & Microsoft Research

The post Breakthroughs in Translating Speech from our Research Teams appeared first on Microsoft Translator Blog.