Specific Audience
Research on specific audiences focuses on understanding and adapting to diverse user needs and characteristics across various applications. Current efforts concentrate on developing AI-powered tools that personalize learning experiences, extract target speakers from complex audio, and tailor information delivery to different age groups and knowledge levels, often employing large language models and deep learning architectures. This work is significant for improving accessibility and effectiveness in education, communication technologies, and information dissemination, while also addressing biases and promoting fairness in AI systems. The ultimate goal is to create more inclusive and efficient systems that cater to the specific needs of their users.
Papers
From Passive Watching to Active Learning: Empowering Proactive Participation in Digital Classrooms with AI Video Assistant
Anna Bodonhelyi, Enkeleda Thaqi, Süleyman Özdel, Efe Bozkir, Enkelejda Kasneci
WeSep: A Scalable and Flexible Toolkit Towards Generalizable Target Speaker Extraction
Shuai Wang, Ke Zhang, Shaoxiong Lin, Junjie Li, Xuefei Wang, Meng Ge, Jianwei Yu, Yanmin Qian, Haizhou Li