Listening to audio content, such as podcasts and audiobooks, is one of the ways people engage with knowledge. Listening affords people more mobility than reading by seeing, thus broadening learning opportunities. This study explores the potential applications of large language models (LLMs) to adapt text documents into audio content, addressing the lack of listening-friendly materials for niche content like research papers. LLMs can generate scripts of audio content in various styles tailored to specific needs, such as the duration of the content and whether it is a monologue or dialogue. To explore this potential, we developed PaperWave, a prototype that transforms academic paper PDFs into conversational podcasts. Our two-month investigation involving 11 participants (including the authors) employed autobiographical design, a field study, and a design workshop. The findings highlight the importance of considering listeners' interaction with their environment when designing document-to-audio systems.
View on arXiv