This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program, CFDA 47.070, will develop adaptive artificial intelligence systems to provide accessible audio captioning of non-speech sounds in digital media content. The $237,141 award to New York University aims to ensure that all citizens can fully participate in digital education, entertainment, and civic life by creating tools to make non-speech audio cues, such as environmental sounds and speaking styles, accessible to viewers who are deaf, hard-of-hearing, or experience hearing decline. The 3-year project will involve user research, dataset development, and the creation of a steerable machine learning framework for prioritizing, decoding, and adapting non-speech audio captions to individual viewer needs and preferences. The project's outputs will include publicly available tools, guidelines, datasets, and machine learning frameworks to improve accessibility and inclusion in digital media.
Mod # | Description | Reason For Modification | Federal Obligation (Click to sort descending) | Date (Click to sort ascending) |
|---|---|---|---|---|
| Not listed | $237.1k | 7/7/25 |