Researcher Wuhan University of Technology China
Zi Yunfei is a distinguished researcher specializing in voiceprint recognition and artificial intelligence, affiliated with the Wuhan University of Technology. His expertise lies in developing advanced speaker verification systems and acoustic feature extraction methods, especially within IoT contexts. Currently, he is concluding his Ph.D. under the guidance of Professor Xiong Shengwu.
Profile
Orcid
Google scholar
Education 🎓
- Ph.D. in Computer Science and Technology (2019–2023) – Wuhan University of Technology
- M.Eng. in Information and Communication Engineering (2016–2019) – Beijing University of Graphic Arts
- B.Eng. in Computer Science and Technology (2011–2015) – Northeast Petroleum University
Experience 💼
Zi has led and contributed to various research initiatives, including a Huawei NRE project and significant AI advancements in IoT voiceprint recognition and military voice monitoring. His technical contributions have been instrumental in enhancing acoustic feature extraction and system integration on Huawei’s deep learning platform, MindSpore.
Research Interests 🔍
- Voiceprint Recognition
- Short Utterance Speaker Verification
- Artificial Intelligence & Deep Learning
- Acoustic Feature Enhancement
- IoT Smart Services
Awards 🏆
- Outstanding Academic Achievement Award – Beijing University of Graphic Arts, 2018
- Outstanding Master’s Thesis Award – Beijing University of Graphic Arts, 2019
- Huawei Smart Base Future Star Award – Ministry of Education-Huawei, 2021
- Outstanding Doctoral Thesis Award – Wuhan University of Technology, 2024
Publications Top Notes📚:
Multi-Fisher and Triple-Domain Feature Enhancement-Based Short Utterance Speaker Verification for IoT Smart Service – IEEE Internet of Things Journal (2024) [DOI:10.1109/JIOT.2023.3309659]
Joint Filter Combination-based Central Difference Feature Extraction – Expert Systems with Applications (2023) [DOI:10.1016/j.eswa.2023.120995]
Fisher Ratio-Based Multi-Domain Frame-Level Feature Aggregation – Engineering Applications of Artificial Intelligence (2024) [DOI:10.1016/j.engappai.2024.108063]
Short-Duration Speaker Verification by Joint Filter Superposition – IEEE Transactions on Consumer Electronics (2024) [DOI:10.1109/TCE.2024.3411116]
Aggregating Discriminative Embedding by Triple-Domain Feature Joint Learning – Biomedical Signal Processing and Control (2023) [DOI:10.1016/j.bspc.2023.104703]