This scenario is not limited to two devices or two languages. 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. 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. Let’s say you’re a Lebanese business person travelling to Italy and want to have a conversation with an Italian partner. ![]() 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. Start and join live, multilingual conversations with up to 100 people 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 “Many of the conflict-affected youth lack access to learning resources which restricts their opportunities for higher education and dignified work. Their goal is to enable conflict-affected youth to discover and access learning resources anywhere and anytime. ![]() 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. With this service, developers can also customize speech transcriptions, translations, and text-to-speech, before integrating them into their apps, workflows, and websites. 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. We developed an approach to generate synthetic parallel data from monolingual data.” – Hany-Hassan Awadalla, Principal Research Scientist “ 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. ![]() This allowed the team to build a working Levantine to English translation system despite this lack of parallel data. However, our researchers developed a novel approach which utilizes monolingual data to train a system for any spoken dialect. 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. 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. Levantine, our 11 th speech language, is a spoken dialect of Arabic which has over 32 million native speakers. ![]() It will help businesses, educators, travelers, and non-profits communicate across the language barrier with Levantine speakers during meetings, presentations, and Skype calls.Ĭredit: Photo of Beit ed-Dine in Lebanon by Oida666 from Wikimedia Commons Microsoft Translator has released Levantine, an Arabic dialect spoken in countries such as Lebanon, Jordan, and Syria, as its latest AI-powered speech translation language.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |