Google DeepMind has developed a sign-language-to-text (SL2T) model that translates sign languages into written text, aiming to bridge the communication gap for Deaf and hard of hearing individuals. This new model powers features like sign-to-text dictation in Gboard and Live Transcribe on Pixel devices, initially supporting American Sign Language (ASL) to English. The SL2T model is trained on over 100,000 hours of data across more than 50 sign languages, addressing the complex challenges of visual perception and true machine translation inherent in sign languages. AI
IMPACT Enables sign language users to interact with devices and digital services more naturally, potentially increasing accessibility and digital inclusion.
RANK_REASON Frontier-lab model release with system card. [lever_c_demoted from frontier_release: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
