Mr. Shanggerile Jiang, University of Shanghai for Science and Technology, China.
Shanggerile Jiang 🎓 is a Research Assistant at the University of Shanghai for Science and Technology, specializing in Opto-electronic Information Science and Engineering. His work focuses on Affective Computing, Signal Processing, and Vocal Technique Assessment using Deep Learning 🧠. He has published in SCI-indexed journals 📚 and serves as a reviewer for reputed journals. A passionate IEEE student member ⚡, he collaborates with leading professors to bridge technology and education through innovative AI applications 🤖.
Profile
ORCID
🎓 Early Academic Pursuits
Shanggerile Jiang began his academic journey at the University of Shanghai for Science and Technology, earning a Bachelor’s degree from the School of Optical-Electrical and Computer Engineering in 2024. His foundational interest in engineering and technology set the stage for his focus on Opto-electronic Information Science and Engineering. His academic trajectory showcases a strong orientation toward computational and signal-based disciplines. 🎓🔬
🧪 Professional Endeavors
Currently serving as a Research Assistant, Jiang is associated with the University of Shanghai for Science and Technology. His work centers on interdisciplinary research that combines optical communication, affective computing, and signal processing. He actively collaborates with esteemed professors and contributes to ongoing lab research and publications. 🧑🔬👨💻
🔬 Contributions and Research Focus On Machine Learning
His primary research contributions include developing a Dense Dynamic Convolutional Network (DDNet) that surpasses traditional CNN and Transformer models in vocal technique assessment. His study explores EEG-based data augmentation using CWGAN and deep neural networks, reflecting his technical command over AI-based voice analysis and emotion recognition. 🗣️📊🧠
🌍 Impact and Influence
Jiang’s work has made measurable progress in enhancing the accuracy and performance of Bel Canto vocal technique assessments, with potential applications in remote education and voice training. His top-1 accuracy of 90.11% and mAP of 41.89% establish his contribution as both reliable and practical. 🎯📈
🧠 Research Skills
Jiang is proficient in Deep Learning, Machine Learning, and Artificial Neural Networks. He is also skilled in using computer-aided analytical tools for signal processing and affective computing tasks. His technical portfolio includes CWGAN implementation, dynamic CNN modeling, and EEG signal extraction. 🤖🧮
🏅 Awards and Honors
He has submitted his nomination for the Best Researcher Award. While major awards are in the future pipeline, his editorial reviewer roles for Education and Information Technologies and Biomedical Signal Processing and Control demonstrate early recognition and trust in his peer-review capabilities. 🏅📑
🔮 Legacy and Future Contributions
Poised at the frontier of AI-based voice diagnostics and education, Jiang aims to further explore the intersection of neurotechnology and audio processing. His work holds long-term potential to redefine how affective computing can be used in educational and therapeutic environments. 🌍🚀
Publications Top Notes
📘 1. Classic Vocal Performance Training Through C-VaC Method
Journal: Journal of Voice
Year: 2024
📅 Published on: October 14, 2024
🎵 Focus: Vocal performance, core muscle stability, computer-aided analysis
📄 2. Transfer Learning in Vocal Education: Technical Evaluation of Limited Samples Describing Mezzo-soprano
Journal: ArXiv (Preprint)
Year: 2024
📊 WOSUID: PPRN:118941218
💡 Focus: Transfer learning, vocal data, mezzo-soprano classification