Time-Traveling Conversations: Designing Robots to Imitate Speaking Styles of Historical Figures
Recipient
Chen Li
Aalborg University
Project number:
00058627
Grant amount
1.992.186 DKK
Year
2023
Project description
With assistance of Deep Learning (DL) and Natural Language Processing (NLP), acquiring insights into the events and social, cultural, and political settings of the past through historical figures can be more precise and less biased. However, no research has been done on simulating historical figures' speaking styles through conversational robots to create immersive conversational experiences with them in order to make historical research more accessible to a wider audience, including students, educators, and the general public. This includes the most recent sophisticated conversational robot chatGPT). To close this gap, this project attempts to answer the following questions:
- Is it possible to use data-driven approaches to collect all relevant information, including the documents, letters, speeches, and videos, of selected historical figures? Answering this question will pave the way for creating a more accurate representation of the historical figure being simulated. This can lead to a more engaging and informative conversation for users.
- Is it possible to design a conversational robot that imitates the speaking styles of historical figures? The answer to this question must take into account not just the technological feasibility of design and implementation such conversational robots, but also user experience design, which takes into account factors like conversation flow, response time, and conversational naturalness. Successful answering this question will pave the way for creating an immersive conversational experience for users. However, this is a challenging task, particularly when dealing with complex historical topics or sensitive celebrity issues. The innovation of this project lies in enabling people to have virtual conversations with historical figures in a way that is engaging, informative, and personalized. This innovation has the potential to transform the way people learn about history and engage with historical figures, and it could pave the way for new forms of immersive entertainment and education.