Amazon Alexa’s new feature translates conversations in real-time

Initially, the Live Translation feature will work with six language pairs- English and Spanish, French, German, Italian, Brazilian Portuguese, or Hindi on Amazon Echo devices with locale set to English US.


Devdiscourse News Desk | Seattle | Updated: 15-12-2020 14:48 IST | Created: 15-12-2020 13:11 IST
Amazon Alexa’s new feature translates conversations in real-time
Representative Image Image Credit: ANI
  • Country:
  • United States

Amazon has launched a new Live Translation feature for the Alexa voice assistant that initiates a translation session for a pair of languages in real-time.

Leveraging several existing Amazon systems including Alexa's automatic-speech-recognition (ASR) system, Amazon Translate, and Alexa's text-to-speech system along with the overall architecture and machine learning models, the new feature allows individuals speaking in two different languages to converse with each other, with Alexa acting as an interpreter and translating both sides of the conversation.

Once the session has started, customers can speak phrases or sentences in either language and Alexa will automatically identify which language is being spoken and translate each side of the conversation.

Initially, the Live Translation feature will work with six language pairs- English and Spanish, French, German, Italian, Brazilian Portuguese, or Hindi on Amazon Echo devices with locale set to English US.

Amazon says it is exploring several approaches to improving the Live Translation feature further.

"To improve the fluency of the translation and its robustness to spoken-language input, we are also working on adapting the neural-machine-translation engine to conversational-speech data and generating translations that incorporate relevant contexts such as tone of voice or formal versus informal translations. Finally, we are continuously working on improving the quality of the overall translations and of colloquial and idiomatic expressions in particular," Amazon said in a blog post.

Give Feedback