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.
SlatorCon Zurich is now SOLD OUT — See you on October 4th!
Facebook AI
Meta Unveils Supercomputer to Power Translation in the Metaverse
Meta shoots for completing world’s fastest supercomputer by mid-2022. Here’s what it can do in terms of natural language processing and translation — and what the facility looks like today.
Facebook (You Know, Meta) CTO Hypes WMT 2021 Win as ‘Truly Groundbreaking’
To be fair, this is the first-ever multilingual model to win the international machine translation contest. But major tech companies have been exploring multilingual models for years.
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.
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.
Facebook AI Open Sources New Multilingual Automatic Speech Recognition Data Set
After promising results in English, researchers hope Multilingual LibriSpeech’s 50,000 hours of audio across eight languages will improve automatic speech recognition around the world.
Your information will not be shared with third parties. No Spam.