Google DeepMind 开发了 SL2T，一个旨在帮助 Android 设备上的聋哑及听障用户的手语到文本模型。这项新技术使得在 Pixel 11 手机上的 Gboard 和 Live Transcribe 中可以直接输入美国手语 (ASL)，将手部、身体和面部动作翻译成文本。该开发与聋哑社区进行了密切合作，包括聋哑的 Google 员工和人工智能手语咨询委员会，以克服以往在手语 AI 中的技术挑战和误解。 AI
影响 通过实现直接的手语输入进行交流和转录，增强了移动设备的辅助功能。
排序理由 这是特定 AI 应用的产品发布，而非前沿模型发布或重大的行业转变。
AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →
We built SL2T with the Deaf community - guided by Deaf Googlers and our AI Sign Language Advisory Committee. Bringing ASL input to phones is just the beginning and we’re working to expand this technology to more sign languages and applications. Find out more → https://t.co/jwN…
SL2T is state-of-the-art on academic benchmarks, plus it's optimized for real-world use like one-handed signing while holding a phone. To protect privacy, it tracks body poses on-device, while our servers translate them into text. https://t.co/6AkxT6mO3D
For years, building AI for sign language has been slow due to complex technical challenges and misconceptions about how the languages work. We addressed this by training a model to translate simultaneous movements of the hands, body, and face directly into text, using huge
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. https://t.co/p9Vx7t…