Google’s Translatotron can translate speech in the speaker’s voice

Google’s Translatotron can translate speech in the speaker’s voice

Google has announced its first direct speech-to-speech translation system that can convert verbal communication from one language to another while maintaining the speaker’s voice and tempo. Translatotron is based on a sequence-to-sequence network which takes source spectrograms as input and generates spectrograms of the translated content in the target language.

Simone
Simone
Str8aura
Str8aura 1 year

This is a tall order, but huge if they can pull through and perfect it.

Top in Tech
Get the App