Nakagawa Shohei
Papers
1
Total Citations
2
H-Index
1
About
Dr. Shohei Nakagawa is a researcher in affective computing and human–robot interaction, with a primary focus on speech-based emotion recognition. His work addresses a critical challenge in enabling natural human–robot communication: the variability of prosodic features across different speakers and contexts. In his most cited paper, "Prosodic Feature Normalization for Emotion Recognition by Using Synthesized Speech" (2012), Nakagawa proposed a novel normalization technique that mitigates the drastic changes in prosodic features—such as pitch and intensity—that often degrade emotion recognition performance. By leveraging synthesized speech as a reference, his method improves the robustness and generalizability of emotion classifiers. Although his citation count is modest (2 citations for this key work), the contribution is notable for its foundational approach to a persistent problem in the field. Nakagawa’s research bridges signal processing and machine learning, offering practical insights for developing more empathetic and responsive robotic systems. His work continues to inform efforts in adaptive speech analysis and affective computing, making him a thoughtful contributor to the advancement of emotionally intelligent machines.
Research Focus
Key Achievements
Top Papers
- 1