We knew Microsoft's text-to-speech model VALL-E can mimic a voice with little training data. Now VALL-E X adds translation, foreign accent control, emotion maintenance, and more.
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 has released SpeechMatrix, a large-scale mined corpus of multilingual speech-to-speech translations.
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 call add-ons planned for beta release in September 2021. Transcription available in 30 languages, and translation, in 12, by year-end 2022.
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 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 acquires German simultaneous speech translation provider, Kites, to provide multilingual speech translation to Zoom users; explores opening R&D center in Germany.
European Live Translator (ELITR) takes speech-to-speech translation one step further, backed by the academe, private sector, and government.
Dating powerhouse Match Group (Match.com) makes biggest purchase to date: Korean tech startup Hyperconnect; pays USD 1.73bn or about 8.6x 2020 revenues for app built on Google Translation API.
Japanese researcher-developers created an open-source all-in-one speech-to-speech translation toolkit to help machine translation researchers, and it’s publicly available on GitHub.
Two research scientists from Apple surveyed 30 years worth of research into speech translation and here’s what they found.
Team of Amazon AI researchers combines various deep-learning models to build automatic dubbing system. Viewer feedback reveals unnaturalness of speaking rate as main problem.
MT and speech recognition company AppTek expands natural language understanding (NLU) capabilities with acquisition of speech technology provider Ignite-Tek.
Chinese e-learning provider Youdao files to go public in New York, seeking to raise USD 300m. Youdao’s suite of products centers around online dictionaries and machine translation tools.
Slator Weekly: Join over 15,500 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
