Speech-to-Speech Translation: DeepMind Deploys New Approach to Train Translatotron 3
Google's DeepMind reports enhanced performance and unsupervised training capabilities in the Translatotron 3 speech-to-speech translation model.
*New* Slator Pro Guide: Scaling an LSP Key Account — Growing Small Clients into Key Accounts
Google's DeepMind reports enhanced performance and unsupervised training capabilities in the Translatotron 3 speech-to-speech translation model.
Zoom call add-ons planned for beta release in September 2021. Transcription available in 30 languages, and translation, in 12, by year-end 2022.
Google researchers say Translatotron 2 outperforms original in terms of speech-to-speech translation quality and naturalness. Plus the new version prevents users from generating speech for deepfakes.
European Live Translator (ELITR) takes speech-to-speech translation one step further, backed by the academe, private sector, and government.
Voice producers fluent in a range of languages will work with synthetic speech to improve Siri — but Apple could be setting the stage for broader use cases, such as dubbing.
Rundown on the latest translation gadgets; from the bestsellers to those that ended up in the gadget graveyard.
Google researchers approach speech-to-speech translation a little differently in a proof-of-concept that completely takes away reference text, but underperforms compared to existing models.
Slator Weekly: Join over 15,800 subscribers and get the latest language industry intelligence every Friday
Tool Box: Join 10,000 subscribers for your monthly linguist technology update.
Your information will not be shared with third parties. No Spam.
This will close in 0 seconds