American Sign Language
PulseAugur coverage of American Sign Language — every cluster mentioning American Sign Language across labs, papers, and developer communities, ranked by signal.
6 day(s) with sentiment data
-
New framework enables zero-shot cross-lingual sign language handshape recognition
Researchers have developed a novel zero-shot cross-lingual framework for recognizing sign language handshapes, enabling the transfer of knowledge from high-resource languages like American Sign Language (ASL) to low-res…
-
Apple unveils DiscoSign for discourse-aware sign language gloss translation
Apple Machine Learning Research has introduced DiscoSign, a novel framework for translating text into sign language glosses that accounts for discourse phenomena. This LLM-based approach addresses spatial coreference re…
-
New SeRV method enhances text-to-American Sign Language generation
Researchers have developed SeRV, a novel Semantic-Aligned Residual Vector Quantization method for generating American Sign Language (ASL) from text. This approach addresses limitations in existing methods by incorporati…
-
DiscoSign framework advances text-to-sign language gloss translation
Researchers have developed DiscoSign, a new framework for translating text into sign language glosses that accounts for discourse-level linguistic phenomena. Unlike previous sentence-level approaches, DiscoSign addresse…
-
New AI models advance sign language recognition and production
Researchers have developed novel methods for sign language recognition and production, moving beyond traditional closed-set classification. One approach uses video captioning and description retrieval to create a revers…
-
AI explored for real-time Mandarin to ASL translation
Researchers are exploring the potential for AI to translate spoken Mandarin into American Sign Language (ASL) in real-time. This ambitious goal aims to bridge communication gaps between Mandarin speakers and the Deaf co…
-
New method improves sign language recognition using temporal alignment
Researchers have developed a novel approach to sign language recognition by employing transfer learning and a domain adaptation method called TA3N. This method utilizes a Temporal Relational Network (TRN) to align multi…
-
Google DeepMind unveils SL2T for real-time sign language-to-text translation
Google DeepMind has introduced SL2T, a novel sign language-to-text model designed to enhance accessibility for deaf and hard-of-hearing users. This AI technology translates American Sign Language (ASL) input directly in…
-
Google DeepMind launches AI for sign language translation in consumer products
Google DeepMind has developed a sign-language-to-text (SL2T) model that translates sign language into written text, aiming to bridge the communication gap for the Deaf and hard of hearing community. This new AI technolo…
-
Google DeepMind enables Pixel 11 to transcribe sign language into text
Google DeepMind has developed a new AI model, SL2T, capable of transcribing sign language into text, which will be integrated into the Pixel 11 lineup. This technology aims to bridge communication gaps for deaf and hard…
-
Netflix adds ASL interpretations to 73 kids' titles via Chrome extension
Netflix has expanded its accessibility features by adding American Sign Language (ASL) interpretations to 73 children's titles, encompassing both shows and movies. This initiative, a collaboration with SignUp Media, pro…
-
AI models show emergent phonological sensitivity in sign language recognition
A new research paper investigates the phonological perception capabilities of deep learning models trained for Sign Language Recognition (SLR), specifically focusing on American Sign Language (ASL). The study probed mod…
-
New study analyzes how conversation shortens ASL signs in STEM discourse
Researchers have developed a new method to study how conversational context influences the articulation of American Sign Language (ASL) in STEM discourse. By collecting motion capture data of ASL dialogues, they observe…
-
MIT wristband uses ultrasound to teach robots human dexterity
MIT researchers have developed an ultrasound wristband that captures human hand and muscle movements. This data is then used to train robots, enabling them to perform complex tasks like housework and surgery with greate…
-
Direct sign language translation model developed using synthetic data
Researchers have developed a novel method for direct translation between different sign languages, addressing a gap in current sign language technology. Their approach utilizes back-translation to create synthetic paral…
-
AI-powered rings translate sign language with 88% accuracy
Researchers have developed electronic rings that can interpret sign language by wirelessly transmitting motion data to an AI system. Unlike previous camera-based or smart glove systems, these rings offer a more practica…
-
New set-based registration framework generalizes across cardiac MRI protocols
Researchers have developed a new set-based groupwise registration framework called \AnyTwoReg for cardiac MRI sequences. This method treats input data as an unordered set, decoupling network design from sequence length …
-
Neuromorphic system achieves low-latency, energy-efficient sign language recognition
Researchers have developed a novel neuromorphic architecture for American Sign Language (ASL) recognition, integrating a spiking visual attention mechanism with a compact spiking neural network on the SpiNNaker platform…
-
Apple AI bootstraps sign language annotation, cutting costs and improving models
Researchers from Apple and Gallaudet University have developed a pseudo-annotation pipeline to significantly reduce the cost and time required for annotating sign language data. This new method uses sparse predictions f…