手話AI「SL2T」とは？Pixel 11でアメリカ手話を英語に翻訳

"Introducing sign-language-to-text (SL2T), our breakthrough model powering new sign language features for Deaf and hard of hearing users."／"Today, we’re introducing a massively multilingual sign-language-to-text (SL2T) translation model that marks a breakthrough in quality and generality. With it, we are bringing sign language AI out of the lab and into consumer products for the first time: SL2T powers sign-to-text dictation in Gboard and Live Transcribe on Pixel 11 , starting with American Sign Language (ASL) to English. More devices are coming soon, and additional languages will follow."／"You can experience SL2T in Gboard and Live Transcribe first on Pixel 11 , with more devices coming soon — all at no additional cost." — Google DeepMind 公式ブログ（2026年8月12日）冒頭と「Looking ahead」節より

"Similarly to how hearing users can use dictation to speak instead of typing, this feature enables Deaf users to sign to their phone anywhere they’d normally type. You can sign to search the web, draft messages or documents, and ask Gemini to solve queries or execute tasks. In Live Transcribe, you can sign responses in conversations instead of having to type back and forth. According to our testers, signing in ASL is faster, more natural, and more delightful than typing in English." — Google DeepMind 公式ブログ（2026年8月12日）冒頭より

"The feature, which supports both one-handed and two-handed signing, lets signers use their native language to express themselves when using Live Transcribe or across their device with Gboard."／"To use this feature on a Pixel 11 device, add sign-to-text to your Gboard toolbar, and sign in ASL to the front camera. The translations will appear on the outer display." — Google 公式ブログ（2026年8月21日）より

"AI's ability to process spoken languages has advanced rapidly over recent decades, enabling automatic translation, dictation, and conversational interfaces that feel effortless to hearing users. Yet this technological revolution has not reached the world’s more than 200 sign languages — and the estimated 70 million Deaf and hard of hearing people who use them."／"Sign languages are the primary languages of Deaf communities around the world and the cornerstone of Deaf cultural identity. 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."／"Despite this opportunity for positive social impact, progress in sign language AI has been slow — both because building AI for sign languages presents complex challenges and because widespread misconceptions exist about how the languages themselves work." — Google DeepMind 公式ブログ 冒頭と「Why sign languages matter」節より

"Compared to spoken language transcription, sign language translation presents two core challenges."／"SL2T is designed to deliver both." — Google DeepMind 公式ブログ「Why sign languages matter」節より

"Compared to spoken language transcription, sign language translation presents two core challenges. First, transcribing speech is a matter of performing a sequential mapping from sound to text in the same language, whereas sign languages are independent, natural languages with their own distinct grammars and lexicons. As a result, they require true machine translation rather than a sequential process of sign-to-word transformations."／"Given this background, it is easy to understand why some early attempts at sign language technology, like sign language gloves, were fundamentally limited: sign languages aren't simply “English on the hands.”" — Google DeepMind 公式ブログ「Why sign languages matter」節より

"Second, the model must learn to “see” and understand physical movement. Sign languages convey meaning through simultaneous movements of the hands, arms, torso, head, and face. Accurately tracking these at high frame rates is a difficult and computationally demanding computer vision task."／"They require complex visual perception of fine-grained whole-body movements and full-fledged language translation. SL2T is designed to deliver both." — Google DeepMind 公式ブログ「Why sign languages matter」節より

"We built SL2T by combining a user-centric, culturally informed approach with massive data scaling. The model is trained on over 100,000 hours of data across more than 50 sign languages — with roughly a quarter of the data in ASL. Training jointly on diverse languages, dialects, and proficiency levels causes the model to learn shared underlying structures, outperforming single-language models in our experiments." — Google DeepMind 公式ブログ「How SL2T works」節より

"To protect user privacy, SL2T sees sign language as a sequence of pose landmark locations rather than a raw camera feed. An on-device model ( MediaPipe Holistic ) tracks the location of points on the signer, and only these geometric coordinates are sent to the server for translation, allowing the original video to be discarded immediately."／"SL2T sees sign language inputs as points on the signer's body and translates them into streaming text outputs." — Google DeepMind 公式ブログ「How SL2T works」節と図の説明より

"SL2T translates this coordinate sequence directly into text, bypassing intermediate annotations known as “glosses” that are widely used in prior work on sign language translation. 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." — Google DeepMind 公式ブログ「How SL2T works」節より

"SL2T is the most capable sign language translation model to date according to key benchmarks like FLEURS-ASL (sd-test), which assesses ASL to English translation quality." — Google DeepMind 公式ブログ「How SL2T works」節より

"SL2T is the most capable sign language translation model to date according to key benchmarks like FLEURS-ASL (sd-test), which assesses ASL to English translation quality. SL2T achieves a remarkable zero-shot score of 70 BLEURT, which is significantly higher than any previously reported score. But optimizing academic benchmarks alone doesn’t guarantee usability in real-world applications" — Google DeepMind 公式ブログ「How SL2T works」節より

"But optimizing academic benchmarks alone doesn’t guarantee usability in real-world applications, so we worked hard on practical issues like minimizing streaming latency, preventing hallucination on non-signing inputs, ensuring fairness for the 10% of signers who are left-handed, and improving performance for one-handed signing, which is used while holding a smartphone in the other hand." — Google DeepMind 公式ブログ「How SL2T works」節より

Examples from the FLEURS-ASL benchmark. SL2T accurately translates complex ASL into fluent English. Occasional errors remain in rare signs, rapid fingerspelling ("prey" → "grey"), passive constructions, classifier depictions (dropping "claws"), and tense without context ("kicked off" → "start").／The Cook Islands do not have any cities but are composed of 15 different islands.／The Cook Islands have no cities and consist of 15 islands.／This fully feathered, warm blooded bird of prey was believed to have walked upright on two legs with claws like the Velociraptor.／This creature is warm-blooded, eats grey, and is covered in feathers.／It is believed that it walks on two legs like a velociraptor.／The games kicked off at 10:00am with great weather／Games start at 10 a.m. in great weather. — Google DeepMind 公式ブログ（FLEURS-ASL の翻訳例と図表説明）より

"We believe in building with the Deaf community, not just for it."／"Achieving universal accessibility means reaching full parity with spoken and written languages." — Google DeepMind 公式ブログ「Building with the community」節と「Looking ahead」節より

"We believe in building with the Deaf community, not just for it. Deaf perspectives have shaped every stage of this project — from conceptualization by Sam Sepah, a Deaf Googler, to data collection with Deaf partners, evaluation in Deaf user studies, and impact assessment of the technology with Deaf experts."／"To guide responsible real-world deployment, we established the AI Sign Language Advisory Committee (AISLAC), bringing together many global Deaf organizations and subject-matter experts. Through this participatory governance model, the communities most impacted by our technology directly influence our development priorities. We co-authored a joint impact report for the release of SL2T 1.0 in Gboard and Live Transcribe, transparently detailing the technology's capabilities and current limitations — a collaborative approach we plan to continue for all major sign language releases."／"This work was done jointly by teams from Google DeepMind and Android." — Google DeepMind 公式ブログ「Building with the community」節と謝辞より

"SL2T builds upon decades of foundational research across academia and industry, but bringing ASL input to users’ phones is only the beginning."／"Achieving universal accessibility means reaching full parity with spoken and written languages. Our team is working to expand this technology into additional sign languages, sign language generation, and frontier AI capabilities. We look forward to sharing our progress responsibly in order to make access through sign languages standard across the digital landscape."／"More devices are coming soon, and additional languages will follow." — Google DeepMind 公式ブログ「Looking ahead」節と冒頭より