Google Pixel 11 gains DeepMind sign language transcription model
New SL2T model lets Pixel 11 users transcribe American Sign Language to text in real time via Gboard and Live Transcribe.
Conversation activity · last 16 hours peak 6/30m
Latest coverage newest 6 of 14 items
Summary, timeline and people extracted by Claude from 14 items across 5 sources · 14h ago. Quotes are verbatim.
What to know
- Pixel 11 integrates DeepMind's SL2T model into Gboard and Live Transcribe for real-time American Sign Language to English transcription.
- Model trained on 100,000+ hours of multilingual sign language data; translates directly to text without intermediate glosses, improving accuracy for non-linear aspects of sign language.
- Currently supports ASL-to-English only; Google plans expansion to additional languages and devices soon.
- Privacy-preserving design converts video to geometric coordinate wireframes processed on-device before server transmission.
How it unfolded
-
Engadget, SiliconANGLE, Unite.AI, and Digital Trends publish coverage of the new sign language translation capability, each highlighting the model's training on 100,000+ hours of data and current ASL-to-English support.
-
Google launches the Pixel 11 family with embedded DeepMind sign-language-to-text (SL2T) model in Gboard and Live Transcribe, supporting American Sign Language to English transcription.
“Deaf people can benefit from sign language processing in the same way that hearing people benefit from spoken language processing, plus the technology opens new possibilities for bridging the communication gap between Deaf and hearing…”
DeepMind · Press ↗ -
Coverage explains that users can open the Translate app and tap the sign language icon in Gboard to activate real-time ASL transcription, with text displayed on both the main and cover screens of the Pixel 11 Pro Fold.
What people are saying verbatim
“Deaf people can benefit from sign language processing in the same way that hearing people benefit from spoken language processing, plus the technology opens new possibilities for bridging the communication gap between Deaf and hearing communities.”
DeepMind, Developer · Engadget ↗
“Glosses fail to capture rich, non-linear aspects of sign languages such as non-manual markers and spatial constructions. Translating directly from landmarks removes artificial vocabulary limits and allows translation quality to scale directly with data.”
DeepMind, Developer · Engadget ↗
“There is great diversity among deaf people in terms of their level of proficiency in signing, speaking, reading, and writing, so it is important to support access in all modalities.”
DeepMind, Developer · Engadget ↗
“The model can 'see' and understand physical movement, including the movement of a user's hands, arms, torso, head, and face. It uses this information to understand the meaning being conveyed through the sign language and translate it into English.”
Google, Pixel 11 manufacturer · Android Authority ↗
Voices from the web unedited
-
But can Tech Talk Thursday's ( https:// majors.house/ttt ) Syn outperform it?! DeepMind's newest model allows Pixel 11 devices to transcribe sign language into text - Engadget https://www. engadget.com/2234618/deepmind- newest-model-allows-pixel-11-devices-to-transcribe-sign-language-into-text/ # DeepMind # Google # AI # Pixel11 # SignLanguage #…
-
SL2T is our breakthrough sign language-to-text model powering new features for Deaf and hard of hearing users on @Android. Starting with American Sign Language-to-English on Pixel 11, people can sign directly into Gboard and Live Transcribe instead of typing. [video]