Prof. Fengpei Ge | Artificial Intelligence | Best Researcher Award
Reseacher at Beijing University of Posts and Communications, China
Dr. Fengpei Ge is a distinguished researcher in the field of signal and information processing, specializing in audio information processing, deep learning, intelligent human-computer interaction, and intelligence analysis. With a strong background in both theoretical and applied research, she has contributed significantly to various national and industrial research projects. She currently serves as an Associate Researcher and Master’s Supervisor at Beijing University of Posts and Telecommunications. Dr. Ge is an active member of IEEE, ISCA, and the China Computer Federation, holding key positions in specialized committees related to artificial intelligence and speech processing. She has also been a reviewer for numerous high-impact journals and conferences, further establishing her influence in the academic community.
Profile
Education
Dr. Ge earned her Bachelor’s degree in Electronic Information Engineering from Tianjin University in 2005, where she was part of the first cohort of the high-level engineering experimental class. She pursued a Ph.D. in Signal and Information Processing at the Chinese Academy of Sciences (CAS), completing her doctoral studies in 2010 under the mentorship of Researcher Yonghong Yan. She then expanded her research expertise as a Visiting Scholar at Georgia Institute of Technology from 2015 to 2017, working with Professor Chin-Hui Lee on speech recognition algorithms based on deep learning in far-field interaction modes. Her research at Georgia Tech led to significant advancements in multi-channel-condition strategies and joint optimization algorithms, which were published in leading conferences such as INTERSPEECH and ICASSP.
Experience
Dr. Ge has held multiple academic and research positions throughout her career. She served as an Assistant Researcher at the Chinese Academy of Sciences from 2010 to 2013 before becoming an Associate Researcher and Master’s Supervisor at the same institution. In 2019, she joined Beijing University of Posts and Telecommunications as an Associate Researcher, where she continues to teach and mentor graduate students. She was also a visiting scholar at Georgia Tech between 2015 and 2017, further enriching her international research experience. Her work spans national and industry research projects, including collaborations with the National Natural Science Foundation of China, the Central Military Commission Equipment Development Department, and the National Computer Network Emergency Response Technical Team.
Research Interests
Dr. Ge’s research primarily focuses on audio information processing, deep learning applications in speech recognition, intelligent human-computer interaction, and intelligence analysis. Her work in far-field speech recognition and acoustic scene classification has led to the development of novel algorithms and frameworks for robust speech processing. She has played a crucial role in advancing deep learning-based approaches for speech enhancement, wake-word detection, and speaker recognition. Her research contributions have been widely recognized, with publications in prestigious journals and conferences such as IEEE JOURNAL, INTERSPEECH, ICASSP, and China Communications.
Awards and Honors
Dr. Ge has received several prestigious awards in recognition of her research excellence. She was part of a research team that won the Chinese Academy of Sciences’ Outstanding Scientific Achievement Award in 2014, one of the most competitive awards granted biennially. Her doctoral dissertation was recognized with the CAS Outstanding Doctoral Student Award, an honor given to only the top 2% of doctoral graduates. Additionally, she has received multiple grants and funding awards, including a National Natural Science Foundation grant in 2022 for her work on federated transfer learning in far-field automatic speech recognition.
Publications
Ge, F., Pan, F., Liu, C., Yan, Y. (2008). “Effective Acoustic Modeling for Pronunciation Quality Scoring of Strongly Accented Mandarin Speech.” IEICE Transactions on Information and Systems, 91(10): 2485-2492. (SCI Q4, Cited by 15)
Ge, F., Pan, F., Dong, B., Yan, Y. (2010). “Experimental Investigation of Putonghua Pronunciation Quality Assessment System.” Chinese Journal of Acoustics, 35(2): 261-266. (EI, Cited by 10)
Ge, F., Guo, Y., Li, M., Lin, M. (2023). “Research on Named Entity Recognition for Spoken Language Understanding Using Adversarial Transfer Learning.” Electronics, 12(4): 884. (SCI Q3, Cited by 8)
Feng, T., Fan, H., Ge, F., Cao, S. (2023). “Speaker Recognition Based on the Joint Loss Function.” Electronics, 12(16): 3447. (SCI Q3, Cited by 5)
Ge, F., Wu, B., Li, K., Huang, Z., Siniscalchi, S. M., Lee, C.-H. (2017). “An End-to-End Deep Learning Approach to Simultaneous Speech Dereverberation and Acoustic Modeling for Robust Speech Recognition.” IEEE Journal of Selected Topics in Signal Processing, 11(8): 1289-1299. (SCI Q1, Cited by 20)
Bai, H., Ge, F., Yan, Y. (2018). “DNN-Based Speech Enhancement Using Soft Audible Noise Masking for Wind Noise Reduction.” China Communications, 15(9): 235-243. (SCI Q2, Cited by 12)
Qi, Y., Pan, F., Ge, F., Yan, Y. (2015). “Investigation on Discriminative Maximum a Posteriori Linear Regression for Speaker Adaptation.” Transactions of Beijing Institute of Technology, 35(9): 946-950. (EI, Cited by 7)
Conclusion
Dr. Fengpei Ge’s contributions to the fields of speech processing and artificial intelligence have been instrumental in advancing deep learning applications for human-computer interaction. Her research has led to numerous innovative methodologies for speech recognition, speaker verification, and acoustic modeling. Through her work as an educator, she has mentored the next generation of researchers, shaping the future of AI-driven speech technology. Her active involvement in national and international research communities continues to foster interdisciplinary collaboration and technological advancements in the field.