个人简介
刘娟，博士，特聘副研究员，毕业于中国科学院大学，获模式识别与智能系统博士学位。主要从事多模态智能与脑功能障碍的交叉研究，目前聚焦于言语障碍的认知神经损伤机制建模、脑影像及语音信号等多模态数据分析与智能评估方法。已发表sci期刊与会议论文十余篇。具备计算机科学、心理学与人工智能复合学科背景，致力于在脑科学交叉领域开展原创研究，推动神经功能障碍的智能评估与康复发展。
教育及工作经历
2025.09-至今 华南师范大学脑科学与康复医学研究院 特聘副研究员
2020.09-2025.06 中国科学院大学（中科院深圳先进技术研究院） 博士
2017.09-2020.06 华南师范大学 基础心理学 硕士
2012.09-2016.06 华南师范大学 计算机科学与技术 学士
已发表文章
1. Liu, J., Du, X., Lu, S., Zhang, Y. M., An-ming, H. U., Ng, M. L., ... & Yan, N. (2023). Audio-video database from subacute stroke patients for dysarthric speech intelligence assessment and preliminary analysis. Biomedical Signal Processing and Control, 79, 104161.
2. Liu, J., Ruzi, R., Jian, C., Wang, Q., Zhao, S., Ng, M. L., ... & Yan, N. (2025). Mapping subcortical brain lesions, behavioral and acoustic analysis for early assessment of subacute stroke patients with dysarthria. Frontiers in Neuroscience, 18, 1455085.
3. Liu, X., Du, X., Liu, J., Su, R., Ng, M. L., Zhang, Y., ... & Yan, N. (2025). Automatic Assessment of Chinese Dysarthria Using Audio-visual Vowel Graph Attention Network. IEEE Transactions on Audio, Speech and Language Processing.
4. Liu, J., Liu, X., Yang, Y., Ruzi, R., Zuo, X., Xu, C., ... & Yan, N. (2024, November). The Open-Access Mandarin Subacute Stroke Dysarthria Multimodal (MSDM) Database for Intelligent Assessment. In 2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP) (pp. 131-135). IEEE.
5. Liu, J., Yang, Y., Liu, X., Zuo, X., Li, J., Wang, L., & Yan, N. (2024, November). The ISCSLP 2024 Multimodal Dysarthria Severity Assessment (MDSA) Challenge: Dataset, Tracts, Baseline and Results. In 2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP) (pp. 136-140). IEEE.
6. 刘娟, 赵树之, 招少枫, 王岚, 燕楠. (2025). 基底节不同核团损伤对卒中后构音障碍患者言语处理功能的影响.中华行为医学与脑科学杂志, 34(06), 517-524.
7. 刘娟，苏荣峰，燕楠，王岚，“一种多模态发音数据采集方法与系统”，专利号：ZL 2020 1 1423644.3，申请日：2020年12月08日，授权公告号：CN 114615450 B，授权公告日：2023年02月17日。
8. Lu, S., Du, X., Liu, J., Zhang, Y. M., Zhao, S., Su, R., ... & Yan, N. (2022, October). A new method for predicting severity level of dysarthric speech based on joint feature-sample selection using audio-visual data. In 2022 International Conference on Asian Language Processing (IALP) (pp. 190-195). IEEE.
9. Zhao, T., Du, X., Liu, J., Su, R., Yan, N., & Wang, L. (2022, December). Respiratory and laryngeal influences on voice in post-stroke dysarthria: a pilot study. In 2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP) (pp. 364-368). IEEE.
10. Yang, Y., Wu, X., Liu, X., Liu, J., Zhou, J., Wang, R., ... & Wang, L. (2024, September). Feature Extraction Method Based on Contrastive Learning for Dysarthria Detection. In International Conference on Social Robotics (pp. 272-281). Singapore: Springer Nature Singapore.
11. Jiang, Y., Wang, T., Xie, X., Liu, J., Sun, W., Yan, N., ... & Tian, F. (2024). Perceiver-prompt: Flexible speaker adaptation in Whisper for chinese disordered speech recognition. arXiv preprint arXiv:2406.09873.