Yang Yi
![]() |
- Associate Professor
- Name (Simplified Chinese):Yang Yi
- Name (English):Yang Yi
- Date of Birth:1978-07-04
- E-Mail:
- Education Level:Postgraduate (Postdoctoral)
- Degree:Doctoral degree
- Professional Title:Associate Professor
- Status:Employed
- Teacher College:DZGCX
- Discipline:Signal and Information Processing

- ZipCode:
- PostalAddress:
- OfficePhone:
- Email:
- Scientific Research
She has published more than 50 SCI/EI papers, with more than 1,200 citations on Google Scholar, 4 monographs, and 19 national invention patents (4 PCT patents and 1 Hong Kong patent). She presided over the National Natural Science Youth Fund Project "Research on Speaker Classification and Labeling Based on Distributed Acoustic Sensor Networks and Quantum Optimization Learning"; participated in the National Natural Science Major Research Program/Key Support Project "Speech Separation, Content Analysis and Understanding in Multi-person Multi-party Dialogue", and was mainly responsible for the research on sound source separation and labeling technology; participated in the 863 National High-tech Research and Development Program Project "Research on Humanized Voice Interaction Technology", and was mainly responsible for the research on microphone array voice enhancement and sound source localization technology; participated in the Beijing Municipal Education Commission's key project of science and technology plan "Research on Efficient Voice Enhancement Technology in Complex Scenarios"; was responsible for the research on speech enhancement technology based on speech coding, and achieved China's first entry into the ITU International Standards Organization for speech coding and decoding technology patents, and won the Huawei Gold Team Medal, served as the leader of the AVS audio group test group, formulated domestic AVS coding and decoding technology standards, promoted AVS audio to apply for national standards, and the first inventor patent entered the domestic standard.
She has published more than 50 SCI/EI papers, with more than 1,200 Google Scholar citations, 4 monographs, and 19 national invention patents (4 PCT patents and 1 Hong Kong patent).
- Minimizing Hallucinations and Communication Costs: Adversarial Debate and Voting Mechanisms in LLM-Based Multi-Agents;Applied Sciences,2025,15(7):1-21.
- Emotion-aware scene adaptation: a bandwidth-efficient approach for generating animated shorts;Sensors,2023,24(5):1-20.
- An Overview of Signal Processing Engineering Education in China;2020 IEEE Frontiers in Education Conference,2020
- Long-Sighted Imitation Learning for Partially Observable Control;Proceedings of the 2019 2nd International Conference on Control and Robot Technology,2019
- A DenseNet feature-based loop closure method for visual SLAM system;2019 IEEE International Conference on Robotics and Biomimetics,2019
- Method and Apparatus for Converting Visual Content into Virtual Animation Visual Representation.Chinese Patent No.: CN202410265968.0A.Hong Kong Application No.: 42024095282.0.
- Image-Based Emotion Recognition Method, Apparatus, Device, and Storage Medium.Chinese Patent No.: CN202310637461.9A.
- Rapid Detection Method for Video Text with High Accuracy.Chinese Patent No.: CN202111264126.6A.
- Time-Domain Single-Channel Multi-Speaker Speech Recognition Method and System.Chinese Patent No.: ZL2020100615656
- High-Recall Weakly Labeled Sound Event Detection Method.Chinese Patent No.: ZL20201088914.
- Introduction to Quantum Machine Learning and Blockchain Technology, Electronics Industry Press, 2021
- Introduction to Big Data Information Processing Technology, Electronics Industry Press, 2018
- Cross-Media Information Technology and Applications, Electronics Industry Press, 2014
- Introduction to Cross-Media Information Technology, Electronics Industry Press, 2012
- Principal Investigator of the National Natural Science Foundation of China (Youth Program) project: "Research on Speaker Classification and Labeling Based on Distributed Acoustic Sensor Networks and Quantum Optimization Learning."
- Participant in the National Major Research Plan/Key Support Project: "Speech Separation, Content Analysis, and Understanding in Multi-Party Multi-Speaker Dialogues," mainly responsible for research on sound source separation and labeling technologies.
- Participant in the 863 National High-Tech R&D Program project: "Research on Humanized Speech Interaction Technology," mainly responsible for research on microphone array-based speech enhancement and sound source localization technologies.
- Participant in the Beijing Municipal Education Commission Key Scientific and Technological Project: "Research on Efficient Speech Enhancement Technologies in Complex Environments."
- Previously led research on speech enhancement technologies based on speech coding, achieving China’s first entry into ITU international standards for speech codec technology; awarded Huawei Gold Team Medal.