Latest Articles for Accessibility

A new system helps blind viewers understand short videos better.

Innovative approaches are improving access to education for underserved communities.

New techniques enhance ASR systems for better long speech recognition.

Text simplification helps improve access to information for diverse readers.

A study on making scientific images accessible for those with color vision deficiency.

This project enhances real-time speech translation and automatic subtitling systems.

MAIDR helps blind users access data visualizations through sound, touch, and text.

Exploring advancements in automated audio captioning and its impact on accessibility.

Chart4Blind transforms complex charts into formats accessible for visually impaired users.

A look into how AVQA technology answers questions using video and audio.

Research reveals preferences of BLV users for video access.

A method to help the visually impaired recognize sounds in mixed reality.

A new model improves speech-to-text efficiency in real-time applications.

Our model generates hint-text to improve usability for visually impaired users.

New methods improve accessibility and accuracy in audio captioning.

RASSAR app improves home safety and accessibility using advanced technology.

New methods aim to improve communication for the deaf community.

A method for enhancing speech recognition accuracy in Kannada and Telugu languages.

A new approach to generate more informative captions for images.

RALL-E enhances text-to-speech synthesis for clearer, more natural speech.

A new method enhances clarity and expressiveness in sign language.

Introducing a new approach to improve text layout analysis in images.

Learn how enhancing UI agents can create better user experiences.

A new method directly creates subtitles, improving accessibility for diverse audiences.

Examining how technology can better express emotions in communication.

New methods improve how AI connects text and images for better results.

A study reveals user frustrations and preferences regarding CAPTCHAs on websites.

Introducing a model that generates synchronized audio and video with mixed noise levels.

This system helps visually impaired individuals shop more independently using a robotic cane.

A new method enhances how machines convey visual information to humans.

Seed-TTS creates lifelike speech from text for various applications.

A new method creates better video captions by focusing on narratives and causality.

A new approach to audio captioning reduces reliance on paired data.

A new approach to predict mobile app UI changes based on user actions.

Using sound to make astronomical data more accessible and engaging for all.

A project blends dance and technology for creative expression.

ReadCtrl allows language models to better match text complexity to reader abilities.

GigaSpeech 2 offers a vast dataset for low-resource languages to improve speech recognition.

Examining the need for context in accurate sign language translation.

A system combines audio and video to enhance speaker detection accuracy.