Sign Language Translation

The task of converting between a sign language and a spoken or written language, in either direction. Sign-to-spoken/written translation (e.g., ASL to English) involves recognizing signs from video and producing equivalent text or speech. Spoken/written-to-sign translation (e.g., English to ASL) involves generating sign language output, typically through animated avatars or video. Translation between sign and spoken languages is fundamentally different from transcription — sign languages have their own grammar, syntax, and structure that do not map directly to spoken languages. For example, ASL uses a topic-comment structure, spatial grammar, and simultaneous multi-channel expression that has no direct English equivalent. The Deaf community has identified signed-to-spoken real-time translation as a top priority, as it would enable real-time access in situations where interpreters are unavailable.