credit: Photo of Beit ed-Dine in Lebanon by Oida666 from Wikimedia Commons

Levantine, our 11^th speech language, is a spoken dialect of Arabic which has over 32 million native speakers.  Since it’s a spoken language that is rarely written, it lacks the large amount of parallel data required to train a usable machine translation system. As with any AI system, without the appropriate amount of data to train the neural machine translation model, the system won’t be able to produce translations that are good enough for real-life use.

However, our researchers developed a novel approach which utilizes monolingual data to train a system for any spoken dialect. This allowed the team to build a working Levantine to English translation system despite this lack of parallel data.

“We adapted a system trained on standard Arabic-to-English translation to be used on a spoken Arabic dialect (Levantine) using only monolingual data of the spoken dialect. We developed an approach to generate synthetic parallel data from monolingual data.” – Hany-Hassan Awadalla, Principal Research Scientist 

Levantine is now available as a supported speech translation language through the Translator apps, Presentation Translator for PowerPoint, the Skype Translator feature in Skype for Windows 10, and the unified Speech translation service, an Azure Cognitive Service. With this service, developers can also customize speech transcriptions, translations, and text-to-speech, before integrating them into their apps, workflows, and websites.

Recently, Microsoft has partnered with the No Lost Generation Tech Task Force, led by NetHope, and one of its members – Norwegian Refugee Council – to co-create an AI-powered solution linking youth affected by Syrian and Iraqi conflicts with educational resources. Their goal is to enable conflict-affected youth to discover and access learning resources anywhere and anytime.

“Many of the conflict-affected youth lack access to learning resources which restricts their opportunities for higher education and dignified work. Levantine support in Microsoft Translator opens up opportunities for them to learn in their native language through real-time translation of online courses and remote mentoring.” – Leila Toplic, NLG Tech Task Force Lead, NetHope

Start and join live, multilingual conversations with up to 100 people

Using the Translator app’s live conversation feature, users can have live, real-time conversations with people who speak other languages, on their own device, in their chosen language.

Let’s say you’re a Lebanese business person travelling to Italy and want to have a conversation with an Italian partner. You can speak Levantine into your phone or PC, and the Levantine audio will be translated into Italian text and speech on your partner’s phone or PC. This also works in reverse: the Italian speaker can speak into their device and have real-time multilingual conversations, and the listener receives the response in Arabic. This scenario is not limited to two devices or two languages. It can support up to 100 devices, across 11 speech translation languages, and over 60 text translation languages. To learn more about the Translator live feature go to http://translate.it or watch this how-to video.

Use your phone as a personal, Levantine translator

Levantine speakers can also have translated, bilingual conversations using only one device by tapping the microphone icon and using the split-screen conversation feature in the app.  Simply select your speech languages, German and Levantine for instance, and use the app’s microphone button to speak in your chosen language. Translated text appears on the split-screen in each language.

Download the Microsoft Translator app.

Present in PowerPoint in Levantine and add translated subtitles in over 60 languages

Presentation Translator allows users to offer live, subtitled presentations straight from PowerPoint. As you speak, the add-in powered by the Microsoft Translator live feature, allows you to display subtitles directly on your PowerPoint presentation in any one of more than 60 supported text languages. This feature can also be used for audiences who are deaf or hard of hearing.

Additionally, up to 100 audience members in the room can follow along with the presentation in their own language, including the speaker’s language, on their phone, tablet or computer. This can also be used with the presenter’s language to support accessibility scenarios.

For example, if you’re presenting to a Levantine speaking audience and speak Spanish, you can choose Spanish as your speech translation language, and Arabic as the subtitle language. As you speak Spanish, your words will get translated to Arabic subtitling in real-time on the screen.

Levantine speakers can now also join and use their phone to ask questions, in Levantine, once the presenter unmutes the audience. This feature is useful for Q&A sessions after a presentation.

If there are audience members who speak other languages, they can follow along with the presentation in their chosen language in the Translator app or at http://translate.it.

API for Developers: Speech translations with the unified Speech services (preview)

Levantine is also available for developers through the Azure Cognitive Services Speech service.  In addition to using the default speech translation models from Levantine, developers can also customize speech transcriptions and translation models using the Custom Speech (http://customspeech.ai) and Custom Translator (http://customtranslator.ai) services.

Developers can then easily integrate speech translation into their apps using the new speech SDK available in several popular programming languages.

To learn more about Microsoft Translator for business, visit the Microsoft Translator site.

The post Microsoft Translator launches Levantine Arabic as a new speech translation language appeared first on Microsoft Translator Blog.

It applies to the following text translations:

English <-> Chinese Simplified, Traditional, and Cantonese

English <-> Japanese

Chinese (all) <-> Japanese

In addition to this new capability, all speech translations are already using neural translations for the ten supported speech translation languages (Arabic, Chinese (Mandarin), English, French, German, Italian, Japanese, Portuguese, Russian and Spanish) in both the Microsoft Translator live and Skype Translator features.

Neural translations generate more fluent and more human sounding translations by using the context of a full sentence rather than just a few adjacent words. Using a multi-dimensional representation (a) of each word for a given translation pair (e.g. English-Chinese), multiple layers of the neural network build a larger multi-dimensional representation of this word within the context of the full sentence (b). The last layer uses these representations to translate words with the most appropriate translation given the sentence and in the most logical order in the target language sentence(c).

Microsoft’s AI-powered translation system delivers the most significant improvement in machine translation quality since statistical machine translation became the industry standard ten years ago. These improvements in quality and fluency have resulted in translations that are the closest they have ever been to human-generated ones.  You can compare the improved translations on all 11 available languages at http://translate.ai.

The post Microsoft Translator Apps Switch all Chinese and Japanese Language translations to Neural Network Technology appeared first on Microsoft Translator Blog.

Today, Microsoft Translator announces the availability of its 10^th speech translation language: Japanese. This new language is now available across all Microsoft Translator supported technologies and products along with the already released nine other speech translation languages: Arabic, Chinese, English, French, German, Italian, Portuguese, Russian and Spanish.

Microsoft Translator is the first end-to-end speech translation solution optimized for real-life conversations (vs. simple human to machine commands) available on the market. It is one of the services in Microsoft’s portfolio of artificial intelligence technologies designed to make AI accessible to all.

Speech translation is a hard problem to solve, as is always the case when machines are trying to mimic a deeply human capability.  It uses two neural-network based Artificial Intelligence (AI) technologies: Automatic Speech Recognition and Machine Translation. It also uses a unique natural language processing technology (TrueText) and a speech synthesizer, aka “Text to Speech”, which enables users to hear, and not only read, the translation.

These technologies are then connected to perform the speech translation function:

1. The sound is transcribed into text through the speech recognition AI
2. TrueText then processes this text to remove unnecessary speech elements, such as redundant words or fillers like “um” (English) or “eto” (Japanese), that would generate poor translations
3. The machine translation AI then translates each word using the context of the full sentence
4. Finally, the text to speech generates the audio output from this translated text

With this release, businesses, developers, and end users alike will be able to use Japanese in the various apps and services offered or powered by Microsoft Translator:

• For presentations, meetings or any other multi-devices translation use cases with the Microsoft Translator live feature. This personal universal translator feature is available at http://translate.it and on the Windows, Android,  iOS, and Amazon Fire Translator apps
• Microsoft Translator API for developers to add speech translation to their applications
• The Skype Translator feature in Skype for Windows desktop and the
  Windows 10 Skype Preview app to call between Skype clients or from Skype to any phone number in the world with a Skype Out subscription (available in the Skype Preview app only)

You can translate any of the supported 10 Translator speech languages into any of the supported 60+ Translator text languages.

In addition to the availability of Japanese as a speech translation language, starting today, all text translations from English to Japanese (and vice-versa) in Microsoft products and services will exclusively use these new and improved neural network translations system. Whether you translate a webpage in Edge, an email in Outlook, or a simple sentence on www.bing.com/translator, all of your translations will be performed with our state of the art neural network systems.

Read more about this news in our Microsoft Japan blog (in Japanese)

Learn More

• What is machine translation?
• Microsoft Translator Speech API
• Microsoft Translator apps
• Microsoft Translator FAQ
• Microsoft Cognitive Services

The post Japanese becomes the 10th speech translation language supported by Microsoft Translator appeared first on Microsoft Translator Blog.