Researchers Propose New Approach to Many-to-Many Spoken Language Translation
KAIST and Google DeepMind researchers propose training a single model using Unit-to-Unit Translation to achieve seamless cross-language communication.
*New* Slator Pro Guide: Scaling an LSP Key Account — Growing Small Clients into Key Accounts
S2ST
Research on Speech-to-Speech Translation is Booming
In just three months, universities and tech companies released over two dozen papers on speech-to-speech translation (S2ST), highlighting continuing trends, new directions in research.
Meta Releases Large Dataset for Multilingual Speech-to-Speech Translation
Meta has released SpeechMatrix, a large-scale mined corpus of multilingual speech-to-speech translations.
Zoom Launches Translation Feature — But Only for Business Users
Zoom business users can now have their meetings transcribed, translated, and captioned in real time into and out of English from any of 10 languages.
Meta Doubles Down on Direct Speech-to-Speech Translation
Meta eliminates text generation in speech to speech translation; shares code and research with the public.
More Than Hype: Meta Reveals Two-Pronged Machine Translation Roadmap
Part of the billions of dollars going into the Metaverse will undoubtedly go into these two areas of machine translation. Meta AI reveals its MT roadmap and the people working on it.
Facebook AI’s SOTA Speech Translation Models Go Against Grain
As the language industry turns to speech-to-speech translation, Facebook AI partners with “AI community” Hugging Face to release speech-to-text translation models for four languages.
Zoom Opts for Speech-to-Text in New Transcription and Translation Features
Zoom call add-ons planned for beta release in September 2021. Transcription available in 30 languages, and translation, in 12, by year-end 2022.
Facebook Takes a Stab at True Speech-to-Speech Translation via Textless NLP
Facebook sees textless natural language processing (NLP) as rendering automatic speech translation (ASR) obsolete by working in true end-to-end fashion: from speech input to speech output.
Google Ups Ante in Speech-to-Speech Translation With ‘Robust’ Translatotron 2
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.
Zoom Bolts on Speech Translation in What Is Only Its Second-Ever Acquisition
Zoom acquires German simultaneous speech translation provider, Kites, to provide multilingual speech translation to Zoom users; explores opening R&D center in Germany.
Here’s Europe’s Latest Attempt at End-to-End Speech Translation
European Live Translator (ELITR) takes speech-to-speech translation one step further, backed by the academe, private sector, and government.
Behold, the Translatotron! Google’s Latest Move in Speech Translation
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.
Your information will not be shared with third parties. No Spam.