Prof. Dr. Chengli Sun is a distinguished scholar in the field of signal and information processing, widely recognized for his significant contributions to intelligent acoustic technology and next-generation speech systems.To date, his work has accumulated 336 citations across 303 documents, demonstrating the broad recognition and adoption of his research outcomes by both domestic and international peers. With 46 published documents spanning high-impact journals His research encompasses speech recognition, speech enhancement, acoustic scene analysis, and computer vision, with a strong focus on advancing human–machine voice interaction under complex and noisy environments. He has led a series of high-impact scientific projects, including major National Natural Science Foundation of China grants and key provincial and municipal initiatives, driving breakthroughs in generative adversarial network models, dual-diffusion speech enhancement, sustainable learning-oriented vehicle voice interaction, and speaker-specific keyword spotting. These research outcomes have enabled practical advancements in intelligent transportation, robotics, smart devices, and public safety. Alongside his research achievements, Prof. Dr. Chengli Sun plays an integral role in academic development and scientific service by contributing to expert review committees and supporting the progress of information processing and acoustics disciplines. He remains committed to high-level talent cultivation through leadership in first-class undergraduate teaching programs and the promotion of interdisciplinary innovation in artificial intelligence and signal processing. Collectively, his sustained research efforts, academic influence, and dedication to education position him as a leading figure shaping the future of intelligent voice technologies.
-
Sun, M., Sun, C., Zou, C., Zhang, J., & Xiang, D. (2025). Modeling of multi-electrode epicardial electrograms for conductivity estimation in atrial fibrillation. IEEE Access.
-
Li, J., Xiang, D., Li, C., Mao, S., Chen, Y., Sun, M., He, W., Deng, Y., & Sun, C. (2025, December 3). Learning student knowledge states from multi-view question–skill networks. Symmetry.
-
Leng, Y., Zhang, E., Zhuang, J., Shen, C., Sun, C., Yuan, Q., & Pan, J. (2025, October). A topic-specific representation learning framework for acoustic scene classification. Applied Soft Computing.
-
Rao, Z., Sun, C., Sun, J., Chen, F., Leng, Y., Sun, M., & Guo, Q. (2025, October 16). A new speech enhancement model based on residual denoising diffusion. Circuits, Systems, and Signal Processing.
-
Wan, M., Zhu, J., Sun, C., Yang, Z., Yin, J., & Yang, G. (2024). Tensor low-rank graph embedding and learning for one-step incomplete multi-view clustering. IEEE Transactions on Multimedia.