PaperWave: Listening to Research Papers as Conversational Podcasts Scripted by LLM

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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-10
Hauptverfasser: Yahagi, Yuchi, Chujo, Rintaro, Harada, Yuga, Han, Changyo, Sugiyama, Kohei, Naemura, Takeshi
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
ISSN:2331-8422