Yuchi Yahagi

PaperWave

Abstruct

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. To explore this potential, we developed PaperWave (https://paperwave.app), a prototype that transforms academic paper PDFs into conversational podcasts. Our autobiographical design with a field study involving 11 participants (including the authors) documents the nuanced understanding of the design process and the shifts in engagements with knowledge. The findings highlight the importance of considering listeners’ interaction with their environment when designing document-to-audio systems.

Publications

  1. Yuchi Yahagi, Rintaro Chujo, Yuga Harada, Changyo Han, Kohei Sugiyama, Takeshi Naemura: “PaperWave: Autobiographical Design of a System to Listen to Research Papers as Conversational Podcasts,” the Transactions of Human Interface Society, vol. 27, no. 4, pp. xx–xx (2025.11). (in print)

  2. [Free Access] Yuchi Yahagi, Rintaro Chujo, Yuga Harada, Changyo Han, Kohei Sugiyama, and Takeshi Naemura: “Temporal Perspectives on Exploring PaperWave: a Document-to-Audio Adaptation System powered by LLMs,” in Research Products and Time: When, For How Long, And Then What? Workshop in CHI 2025, Yokohama, Japan (2025.4.27).

  3. [Free Access] Yuchi Yahagi, Rintaro Chujo, Yuga Harada, Changyo Han, Kohei Sugiyama, and Takeshi Naemura: “PaperWave: Listening to Research Papers as Conversational Podcasts Scripted by LLM,” in Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA ‘25), Yokohama, Japan (2025.4.29). Acceptance rate: 23.7%

    [Demo] [YouTube] [Slide (CHI2025)] [GitHub (CLI)] [GitHub (Web)]

  4. [Free Access] Yuchi Yahagi, Rintaro Chujo, Yuga Harada, Changyo Han, Kohei Sugiyama, Takeshi Naemura: “Developing PaperWave: A System for Adapting Research Papers into Conversational Podcasts with LLMs,” IEICE Technical Report, HCG Symposium 2024 (2024.12.11). 🏆 Best Interactive Presentation Award (Top 3.9%)

    [Demo] [YouTube] [GitHub (CLI)] [GitHub (Web)]

Awards

  1. Best Presentation Award, IIW Poster Session by PhD Students in 2024, 2025.1.6. (Top 4.3%, 3/69) (PaperWave, 1st author)

  2. Best Interactive Presentation Award, HCG Symposium 2024, 2024.12.13. (Top 3.9%, 5/129) (PaperWave, 1st author)