Papers
2
Total Citations
88
H-Index
2
About
Zhi Zhu is a leading researcher in affective computing and human-robot interaction, with a primary focus on speech emotion recognition. Her work bridges auditory perception and deep learning to enable robots to understand human emotional states from vocal cues. Zhu’s most influential contribution, “Speech Emotion Recognition Using 3D Convolutions and Attention-Based Sliding Recurrent Networks With Auditory Front-Ends” (2020, 83 citations), introduces a novel architecture that mimics the human auditory system’s ability to track emotional dynamics. By combining 3D convolutions with attention mechanisms, her model effectively captures salient temporal features in speech, significantly improving recognition accuracy. In earlier work, “Dimensional Emotion Recognition from Speech Using Modulation Spectral Features and Recurrent Neural Networks” (2019, 5 citations), she pioneered the use of modulation spectral features for tracking continuous emotional dimensions like arousal and valence. Zhu’s research is particularly notable for its focus on naturalistic interaction—her systems are designed to process frame-level acoustic sequences in real time, a critical requirement for responsive human-robot communication. With growing citation impact, her work is shaping next-generation socially aware robots capable of empathetic interaction.
Research Focus
Key Achievements
Top Papers
- 1
- 2