Jang-Sik Cho

Papers

Total Citations

H-Index

About

Jang-Sik Cho is a pioneering researcher in the field of affective computing and human-robot interaction, with a specific focus on emotion recognition from speech. His work centers on developing Bayesian-based methods for detecting emotions in human voice, particularly for application in *Kansei* (sensitivity) robots—machines designed to perceive and respond to human emotional states. Cho’s major contribution lies in his innovative use of Bayesian modeling of prosodic features (such as pitch, tone, and rhythm) to infer a dialogist’s emotion, enabling more natural and empathetic human-robot communication. His most cited paper, "Bayesian-Based Inference of Dialogist's Emotion for Sensitivity Robots" (2007, 5 citations), lays the groundwork for this approach, followed by "Bayesian Method for Detecting Emotion from Voice for Kansei Robots" (2009, 4 citations) and "A Biphase-Bayesian-Based Method of Emotion Detection from Talking Voice" (2008, 3 citations). While his citation counts are modest, Cho’s work is notable for its early and systematic application of probabilistic reasoning to emotional speech analysis, a precursor to modern affective AI systems. His research remains a foundational reference for scholars exploring Bayesian frameworks in human-robot interaction.