Google DeepMind has developed a new model, SL2T, capable of transcribing sign language into text, launching initially on Pixel 11 devices. Integrated into Gboard and Live Transcribe, the model supports American Sign Language (ASL) to English transcription, aiming to improve communication for deaf and hard-of-hearing individuals. The system processes video by converting it into geometric coordinates to protect user privacy before translating directly into text, bypassing intermediate "glosses" for more nuanced translation. AI
IMPACT Enhances accessibility on mobile devices by enabling sign language transcription, potentially improving communication for millions.
RANK_REASON The release is a specific feature integration into a consumer device, not a core frontier model release or significant industry-wide event.
Read on Mastodon — mastodon.social →
AI-generated summary · Google Gemini · from 4 sources. How we write summaries →
