Papers
1
Total Citations
83
H-Index
1
About
Xingfeng Li is a leading researcher in affective computing and human-robot interaction, with a core focus on speech emotion recognition. His most cited work, "Speech Emotion Recognition Using 3D Convolutions and Attention-Based Sliding Recurrent Networks With Auditory Front-Ends" (2020, 83 citations), introduces a novel deep learning architecture that mimics the human auditory system. By integrating 3D convolutions with attention-based sliding recurrent networks, Li’s model effectively captures the temporal dynamics of emotional speech—tracking intensity and fundamental frequency shifts that humans naturally perceive. This contribution significantly advances how robots interpret speaker intentions, moving beyond simple text or tone analysis to more nuanced, context-aware emotional understanding. Li’s work bridges cognitive science and machine learning, demonstrating that biologically inspired auditory front-ends can enhance emotion recognition accuracy. His research has direct applications in developing empathetic social robots and improving human-computer interaction systems. With a growing citation impact, Xingfeng Li is establishing himself as a key innovator in making machines more perceptive of human emotional states, paving the way for more natural and intuitive human-robot communication.
Research Focus
Key Achievements
Top Papers
- 1