Kohei Sugiyama | Searcharxiv

arXiv2025

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

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

cs.HC↗

arXiv2014

Motivating Smartphone Collaboration in Data Acquisition and Distributed Computing

This paper analyzes and compares different incentive mechanisms for a master to motivate the collaboration of smartphone users on both data acquisition and distributed computing applications. To collect massive sensitive data from users, we propose a reward-based collaboration mechanism, where the master announces a total reward to be shared among collaborators, and the collaboration is successful if there are enough users wanting to collaborate. We show that if the master knows the users' collaboration costs, then he can choose to involve only users with the lowest costs. However, without knowing users' private information, then he needs to offer a larger total reward to attract enough collaborators. Users will benefit from knowing their costs before the data acquisition. Perhaps surprisingly, the master may benefit as the variance of users' cost distribution increases. To utilize smartphones' computation resources to solve complex computing problems, we study how the master can design an optimal contract by specifying different task-reward combinations for different user types. Under complete information, we show that the master involves a user type as long as the master's preference characteristic outweighs that type's unit cost. All collaborators achieve a zero payoff in this case. If the master does not know users' private cost information, however, he will conservatively target at a smaller group of users with small costs, and has to give most benefits to the collaborators.

cs.GT↗