#NMT #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. It also makes use of two other separately trained components:...
https://ai.googleblog.com/2019/05/introducing-translatotron-end-to-end.html

a neural vocoder that converts output spectrograms to time-domain waveforms, and, optionally, a speaker encoder that can be used to maintain the character of the source speaker’s voice in the synthesized translated speech." Can already imagine it for #dubbing together w #deepfake

Translatotron is the culmination of years of related work, though it’s still an experiment. Google's been looking into the possibility of direct speech-to-speech #translation for years, but only recently have those efforts borne fruit worth harvesting. https://techcrunch.com/2019/05/15/googles-translatotron-converts-one-spoken-language-to-another-no-text-involved/

(and now I need to listen to these samples https://google-research.github.io/lingvo-lab/translatotron/