showSidebars ==
showTitleBreadcrumbs == 1
node.field_disable_title_breadcrumbs.value ==

PhD Dissertation Defense by Rosiana NATALIE | Creating and Delivering Video's Audio Descriptions

Please click here if you are unable to view this page.

 
 

Creating and Delivering Video's Audio Descriptions

Rosiana NATALIE

PhD Candidate 
School of Computing and Information Systems 
Singapore Management University 
 

FULL PROFILE

Research Area

Dissertation Committee

Research Advisor

Dissertation Committee Member

External Member

  • Hernisa KACORRI, Associate Professor, College of Information Studies, University of Maryland – College Park
 

Date

29 May 2024 (Wednesday)

Time

9:00am – 10:00am

Venue

Meeting room 4.4, Level 4 
School of Computing and Information Systems 1, Singapore Management University, 80 Stamford Road Singapore 178902

Please register by 28 May 2024.

We look forward to seeing you at this research seminar.

 

ABOUT THE TALK

Despite regulations mandating audio descriptions (ADs), most online videos remain inaccessible to blind and low-vision (BLV) individuals due to absent or inadequate ADs. Professional AD authorship is costly and impractical for casual creators, and existing ADs often fail to meet diverse BLV preferences. My dissertation addresses these issues by developing cost-effective methods for high-quality ADs and an interface for AD customization. 

The research includes three main threads: designing and evaluating ViScene, a tool for collaborative AD authoring with sighted novices and blind reviewers; integrating automatic feedback mechanisms using video scene recognition and natural language processing to improve novice-authored scene descriptions; and designing and evaluating CustomAD, a prototype for customizing AD properties. My studies showed the proposed prototypes and workflows reduce costs and enhance video understanding, immersion, and information navigation for BLV users. 

This dissertation contributes by creating a quality assessment codebook for AD reviews, developing ViScene for collaborative authorship, providing insights into mixed-ability collaboration, designing a human-machine collaboration interface for real-time feedback, evaluating semi-automated SD methods, outlining design implications for future AD authoring tools, investigating BLV customization needs, and demonstrating the benefits of AD customization for video comprehension and immersion.

 

ABOUT THE SPEAKER

Rosiana NATALIE is a Ph.D. candidate in the School of Computing and Information Systems at Singapore Management University. She is working with Assistant Professor Kotaro HARA. Prior to joining the Ph.D. program, she received her Master of Science Degree from National Tsing Hua University, Taiwan, in 2018. Her research interest lies in the intersection of Accessibility, Collaborative work, and Human-Computer Interaction. Her current research focuses on exploring and designing a collaborative method that is cost-and time-effective to author and deliver audio descriptions for blind people.