Papers
4
Total Citations
134
H-Index
3
About
Zhichao Peng is a leading researcher in speech emotion recognition, a field critical for enabling natural human-robot interaction. His work focuses on developing advanced computational models that allow machines to perceive and interpret the emotional content of human speech, moving beyond simple word recognition to understand the speaker's underlying intentions and affective state. Peng’s major contributions lie in the innovative integration of biologically inspired auditory features with deep learning architectures. He pioneered the use of modulation-filtered cochleagram features—which mimic the human auditory system’s ability to track temporal dynamics like pitch and intensity—and combined them with recurrent neural networks and attention mechanisms. His most impactful work, "Speech Emotion Recognition Using 3D Convolutions and Attention-Based Sliding Recurrent Networks With Auditory Front-Ends," has garnered 83 citations, demonstrating its influence on the field. Peng has also advanced dimensional emotion recognition, enabling the tracking of continuous emotional shifts over time, a key capability for responsive robots. His multi-level attention-based models represent a significant step toward more accurate and context-aware affective computing systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4