91Ó°ÊÓ

Dr. Jianyuan Sun is a Lecturer in AI and Games at De 91Ó°ÊÓ University in Leicester, UK. Previously, she was a Research Associate with Prof. Jon Barker on an EPSRC-funded project focusing on hearing aid signal processing within the Speech and Hearing (SpandH) Group at the University of Sheffield. She also worked as a Research Fellow with Prof. Wenwu Wang and Prof. Mark D. Plumbley on a British Council-funded project related to automated audio captioning for the hearing impaired at the Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey. Additionally, she was a Research Associate with Dr. Hongchuan Yu and Prof. Jianjun Zhang on the EU H2020-funded project focusing on vision computing for animation at the National Centre for Computer Animation (NCCA), Bournemouth University. Jianyuan earned her Ph.D. in Computer Science from the Ocean University of China in 2019.

Dr. Jianyuan's research focuses on explainable artificial intelligence methods, 3D reconstruction in computer vision, automated audio captioning, speech-in-noise signal processing, pattern recognition in computer vision and signal processing, and AI game/animation technology. She has led several research projects funded by the Grantham Centre for Sustainable Futures, UK, the Shandong Province Youth Innovation and Technology Support Plan for High Education Institutions, China, and other sources. Her work has been published in top-tier international journals, such as IEEE Trans. on Cybernetics, IEEE Trans. on Industrial Electronics, IEEE Trans. on Emerging Topics in Computing, IEEE/ACM Trans. on Audio, Speech, and Language Processing. She has also published and presented at leading signal processing conferences, including INTERSPEECH and ICASSP. She serves as a committee member or technical chair for international conferences, such as the Virtual Conference on Computational Audiology (VCCA), and as a guest editor for international journals.

Selected Publications:

Journal articles

1. Xinhao Mei, Xubo Liu, Jianyuan Sun, Mark D. Plumbley and Wenwu Wang. (2024). Towards Generating Diverse Audio Captions via Adversarial Training [J]. in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, pp. 3311-3323, doi:
10.1109/TASLP.2024.3416686.
2. Sun, Jianyuan, Yu, Hongchun, Zhang, JianJun, Dong, Junyu, Yu, Hui & Zhong, Guoqiang. (2022). Face image-sketch synthesis via generative adversarial fusion. Neural Networks. 154, 179-189.
3. Wu, Z., Ji, Y., Song, L. and Sun, Jianyuan, (2022). Underwater Image Enhancement Based on Color Correction and Detail Enhancement. Journal of Marine Science and Engineering, 10(10), p. 1513.
4. Sun, Jianyuan, Yu, Hongchun, Zhong, Guoqiang, Dong, Junyu, Zhang, Shu & Yu, Hui. (2020). Random shapley forests: cooperative game-based random forests with consistency [J]. IEEE Transactions on Cybernetics. 52(1): 205-214.
5. Sun, Jianyuan, Wang, Zidong, Yu, Hui, Zhang, Shu, Dong, Junyu, & Gao, Pengxaing (2020). Two-stage deep regression enhanced depth estimation from a single RGB image. IEEE Transactions on Emerging Topics in Computing. 10(2): 719-727.
6. Sun, Jianyuan, Zhong, Gyoqiang, Huang, Kaizhu, & Dong, Junyu (2018). Banzhaf random forests: Cooperative game theory based random forests with consistency [J]. Neural Networks. 106, 20-29.
7. Dong, Xinghui, Dong, J, Zhou, H., Sun, Jianyuan, & Tao, Dacheng. (2017). Automatic Chinese postal address block location using proximity descriptors and cooperative profit random forests [J]. IEEE Transactions on Industrial Electronics. 65(5), 4401-4412.
8. Sun, Jianyuan, Zhong, G., Dong, J., Saeeda, H., & Zhang, Q. (2017). Cooperative profit random forests with application in ocean front recognition [J]. IEEE Access, 5, 1398-1408.
9. Zhang, Q., Sun, Jianyuan, Zhong, G., & Dong, J. (2017). Random multi-graphs: a semi-supervised learning framework for classification of high dimensional data [J]. Image and Vision Computing, 60, 30-37.

Conference proceedings papers

1. Jianyuan Sun, Wenwu Wang, Mark D. Plumbley. (2024). PFCA-Net: Pyramid Feature Fusion and Cross Content Attention Network for Automated Audio Captioning [C].Interspeech. pp. 1130-1134, doi: 10.21437/Interspeech.2024-1268.
2. Sun, Jianyuan, Liu, Xubo, Mei, Xinhao, Plumbley, Mark D., Kilic, V., & Wang, Wenwu. (2023). Dual Transformer Decoder based Features Fusion Network for Automated Audio Captioning [C]. Interspeech. pp. 4164-4168, doi: 10.21437/Interspeech.2023-943.
3. Liu, Xubo, Huang Qiushi, Mei Xinhao, Haohe Lou, Jianyuan Sun et al. (2023). Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention. Interspeech. pp. 2838-2842, doi: 10.21437/Interspeech.2023-914.
4. Sun, Jianyuan, Liu, Xubo, Mei, Xinhao, Zhao, Jin., D. Plumbley, Mark, Kılıç, Volkan, Wang, Wenwu. (2022). Deep Neural Decision Forest for Acoustic Scene Classification [C]. EUSIPCO. pp. 772-776, doi: 10.23919/EUSIPCO55093.2022.9909575.
5. Mei, Xinhao, Liu, Xubo, Sun, Jianyuan, D. Plumbley, Mark, Wang, Wenwu. (2022). Diverse Audio Captioning via Adversarial Training [C]. ICASSP. pp. 8882-8886, doi: 10.1109/ICASSP43922.2022.9746894
6. Sun, Jianyuan, Lin, Q., Zhang, X., Dong, J., & Yu, H. (2018, July). Kinect Depth Recovery via the Cooperative Profit Random Forest Algorithm [C]. International Conference on Human System Interaction (HSI). pp. 57-62. IEEE.

Book Chapter

1. Qin Zhang, Jianyuan Sun, Guoqiang Zhong, Junyu Dong. (2018). Chapter 2: Random multi-graphs: a semi-supervised learning framework for classification of high dimensional data. Nova Science Publishers.

Audio and Speech Signal Processing, Computer Vision, Game/Animation AI, Human-Centered AI

AI and Games

GAMR1530 Maths and Computer Systems (MSc,) CSIP5304 Fuzzy Logic & Evolutionary Computing (MSc)

• The Sustainability Fellow award in Institute for Sustainability, University of Surrey, UK, Feb 2023.
• The Global Talent Endorsement award in Royal Academy of Engineering, UK, Aug 2023.
• The Best Journal Paper Award in Shandong Artificial Intelligence Society, China, Oct 2023.

"A new mobile technology for hearing-impaired", (PI), Research Grant, £10k, Funded by the Grantham Centre for Sustainable Future, UK, 02/2024-01/2025.
"Non-negative matrix decomposition algorithm based on global and local correlation of data", (CO-PI), Research Grant, £30k, Funded by the Shandong Province Youth Innovation and Technology Support, China, 10/2022-01/2024.

I welcome potential PhD students or one year academic visitors from around the world who are strongly motivated by computer vision, audio signal processing, and Games AI. Please feel free to contact me (jianyuan.sun@dmu.ac.uk). 

"A new mobile technology for hearing-impaired", (PI), Research Grant, £10k, Funded by the Grantham Centre for Sustainable Future, UK, 02/2024-01/2025.
"Non-negative matrix decomposition algorithm based on global and local correlation of data", (CO-PI), Research Grant, £30k, Funded by the Shandong Province Youth Innovation and Technology Support, China, 10/2022-01/2024.

As a member of the Clarity Team, I helped organise the 3rd Clarity Enhancement Challenge which was part of the Clarity Project (). The challenge aimed to organise open evaluations for hearing aid algorithms and to champion novel machine learning approaches to hearing aid speech-in-noise processing. The challenge attracted numerous speech enhancement research groups from both industry and academia worldwide.