Google Develops Speech to Speech Translation System

google speech to speech transaltion program

The Search Giant Google has announcement it’s first direct speech to speech translation system called ‘Translatotron’ that can convert verbal communication from one language to another while maintaining the speaker’s voice and tempo.

It’s based on a sequence to sequence network which takes source spectograms, a visual representation of frequencies – as input and generates spectrograms of translated content in the target language, Ye Jia and Ron Weiss, Software Engineer, Google AI wrote in a blog post.

“By incorporating a speaker encoder network, ‘Translatotron is able to retain the original speaker’s vocal characteristics in the translated speech, which makes the translated speech sound more natural and less jarring,” Jia and Weiss said.

The company also said that it is the first end to end model that can directly translate speech from one language into another.