Xianghu Yue
Papers
1
Total Citations
4
H-Index
1
About
Xianghu Yue is a leading researcher in audio and speech processing, with key contributions to sound source localization (SSL), privacy-preserving machine learning, and acoustic scene analysis. His work bridges the gap between traditional signal processing and modern deep learning approaches, particularly in developing analytic class incremental learning methods for SSL that protect user privacy—a critical advancement for real-world applications like surveillance and robotics. His 2024 paper on this topic has already garnered 4 citations, reflecting its timely impact. Yue’s research also extends to robust speech recognition and multi-modal learning, where he has pioneered techniques for handling noisy environments and limited data. His notable achievements include developing frameworks that enable continuous learning without catastrophic forgetting, ensuring models adapt to new acoustic conditions while safeguarding sensitive information. With a growing citation record and a focus on practical, ethical AI, Yue’s work is shaping the future of intelligent audio systems that are both powerful and responsible.
Research Focus
Key Achievements
Top Papers
- 1