8 papers
Machine Translation for Sign Languages
Ozge Mercanoglu Sincan, Anton Pelykh, Edward Fish +7
Sign language machine translation has progressed substantially over the past decade, evolving from isolated sign recognition to end-to-end translation systems. Advances in pose est…
SignRefine: Adapting Foundational Video Models for Sign Language Generation
Anton Pelykh, Edward Fish, Ozge Mercanoglu Sincan +1
Sign language video generation demands precise hand and facial articulation, yet modern video diffusion models, trained predominantly on spoken-language video, produce artifacts th…
Beyond BLEU: A Case for Redefining Sign Language Translation Benchmarks
Oline Ranum, Edward Fish, Simon Hadfield +1
BLEU-4 is the standard metric for evaluating sign language translation (SLT), but spoken-language metrics may not adequately reflect sign language proficiency. The multimodal, low-…
BackTranslation2.0 -- A Linguistically Motivated Metric to Assess Sign Language Production
Oliver Cory, Maksym Ivashechkin, Karahan Sahin +6
Sign Languages (SLs) are the primary means of communication for millions of deaf individuals, yet existing evaluation metrics for generated SL remain simplistic and poorly aligned…
SignBind-LLM: Multi-Stage Modality Fusion for Sign Language Translation
Marshall Thomas, Edward Fish, Richard Bowden
Current sign language translation (SLT) systems attempt to learn all aspects of signing---manual gestures, high-speed fingerspelling, and asynchronous non-manual facial cues---with…
SLRTP2025 Sign Language Production Challenge: Methodology, Results, and Future Work
Harry Walsh, Ed Fish, Ozge Mercanoglu Sincan +19
Sign Language Production (SLP) is the task of generating sign language video from spoken language inputs. The field has seen a range of innovations over the last few years, with th…
Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation
Edward Fish, Richard Bowden
Recent progress in Sign Language Translation (SLT) has focussed primarily on improving the representational capacity of large language models to incorporate Sign Language features.…
VALLR: Visual ASR Language Model for Lip Reading
Marshall Thomas, Edward Fish, Richard Bowden
Lip Reading, or Visual Automatic Speech Recognition (V-ASR), is a complex task requiring the interpretation of spoken language exclusively from visual cues, primarily lip movements…