Yoshinori Shiga

Kyoto Seika University, National Institute of Information and Communications Technology

Papers

Total Citations

H-Index

About

Yoshinori Shiga is a leading researcher in human-robot interaction, specializing in cloud robotics and speech synthesis for service robots. His work addresses a critical challenge in robotics: making robot speech sound natural, engaging, and human-like rather than monotonous and robotic. Shiga pioneered non-monologue speech synthesis using Hidden Markov Models (HMMs), a breakthrough that moves beyond traditional text-to-speech systems designed for reading. By collecting and modeling speech corpora in a conversational, dialogue-oriented style, he enabled robots to produce utterances that feel interactive and friendly—essential for real-world service applications. His most-cited paper, "A cloud robotics approach towards dialogue-oriented robot speech" (2015, 18 citations), and its 2014 precursor (14 citations) have laid foundational work for cloud-based, non-monologue speech generation. Though his citation counts reflect a focused, emerging field, Shiga’s contributions are notable for shifting robot speech from passive narration to active, natural dialogue. His research is pivotal for students and engineers developing more socially adept robots, demonstrating how cloud computing can enhance speech quality and user experience in human-robot communication.