Google Introduces Translatotron for End-to-End Translation

Google has introduced Translatotron, an end-to-end, speech-to-speech translation model that converts speech directly into another language without needing an intermediate text translation. The model has several advantages over the current method used, including:

  • increased speeds
  • fewer translation errors
  • retention of the original speaker’s voice
  • better handling of names and proper nouns that don’t need to be translated.

The current cascade models in use first transcribe the speech as text, translate that text into another language, then use text-to-speech synthesis to translate the text into speech, wrote Ye Jia and Ron Weiss, software engineers at Google AI, in a recent blog post. Translatotron, on the other hand, is the first model that can translate speech from one language directly into speech from another language, while preserving the speaker’s tone and voice.

Google’s Translatotron translates speech directly into another language

Translatotron Builds on Google Assistant’s Bilingual Feature

Google announced their bilingual feature for the Google Assistant at the 2018 International Franchise Association conference. Aside from English, the feature allows the Assistant to recognize Spanish, French, German, Japanese, and Italian, allowing for voice commands in those languages. The feature does not allow for multiple languages to be used at once, according to a post from Google’s artificial intelligence blog.

Polish Added to Google Assistant

At the beginning of 2019, Google added Polish to the Assistant, programming it not only with voice commands but also with Polish culture. Users can ask the Google Assistant for data regarding Polish history, pop culture, songs, and more, according to a blog post from Google. The technology uses LangID, which identifies spoken language and uses neural networks to recognize speech and voices to distinguish between languages. With multiple updates each week, it is expected that Google will only further increase the Assistant’s language abilities in terms of both voice commands and translations.

Aliza Vigderman

Aliza Vigderman

Aliza is a journalist living in Brooklyn, New York. Throughout her career, her work has spanned many intersections within the tech industry. At SquareFoot, a New York-based real estate technology company, she wrote about the ways in which technology has changed the real estate industry, as well as the challenges that business owners face when they want to invest in property. At, an education technology website, Aliza created digital content for lifelong learners, exploring the ways in which technology has democratized education. Additionally, she has written articles for The Huffington Post as well as her own content on Medium, the online publishing platform. Aliza’s love of journalism and research stems from the excellent Journalism program at Brandeis University. At Brandeis, Aliza interned as a research assistant at the Schuster Institute for Investigative Journalism, a non-profit “news room without walls”. There, Aliza was paired with an investigative journalist and used academic databases to obtain data on everything from the suicide rates in Bhutan to local Boston court cases. Her last position was as an account executive at Yelp, educating business owners on the power of technology to increase revenue. Throughout, however, her heart remained with tech journalism, and she’s thrilled to be writing for Security Baron. When she’s not keeping afloat of the latest tech trends, Aliza likes to cook, read, and write. A former high school “Class Clown,” Aliza has completed two feature-length screenplays, a pilot, and countless comedic sketches. On her days off you can find her relaxing in Prospect Park, trying the latest flavors at Ample Hills Ice Cream, and spending time with friends and family.

Trending News

Follow Us