教育经历（按时间倒序）：

• 2018-2022：谢菲尔德大学 计算机科学 博士学位（全日制）
• 2017-2018：爱丁堡大学 人工智能 硕士学位（全日制）
• 2013-2017：上海大学 通信工程 学士学位（全日制）

 

工作经历（按时间倒序）：

• 2026-现在： 深圳河套学院 语言模型与人机交互 助理教授
• 2022-现在：伦敦国王学院 工程系 客座研究员
• 2022-2025：荷兰代尔夫特理工大学智能系统 助理教授（tenured）
• 2021-2022：伦敦国王学院 工程系 博士后研究员

包容性语音处理与识别、语音生成与转换、智能影视配音、端侧语音语言大模型、临床语音智能与可解释AI 核心研究领域：
1、 包容性语音处理与识别：面向低资源、病理、儿童与老年人语音的鲁棒建模与自动语音识别
2、 语音生成与转换：语音合成（TTS）、语音转换/音色迁移与可控生成
3、智能影视配音：电影/短视频智能配音、跨语言配音、本地化与口型/时序对齐
4、端侧语音语言大模型：语音与语言大模型的压缩、加速与端侧部署
5、临床语音智能与可解释AI：多模态语音生物标志、认知障碍检测与临床可解释建模（XAI），结合语音基础模型与大语言模型用于医疗对话与辅助交互

跨学科研究领域：AI + 数字健康/康复医学/言语语言病理学（Speech-Language Pathology）、AI+现代智能影院, 可及性与助残技术（Assistive Technology）与人机交互（HCI）、低资源语言与弱势人群的包容性数据采集与评测方法。

https://zhengjunyue.github.io//

zhengjunyue@slai.edu.cn

岳政君，博士，现任深圳河套学院LIMA中心助理教授。博士毕业于英国谢菲尔德大学（玛丽居里奖学金），曾在伦敦国王学院担任EPSRC博士后，后任荷兰代尔夫特理工大学助理教授。研究聚焦面向医疗健康与福祉的包容性语音技术：病理/儿童/老年人语音处理与识别、认知障碍、检测低资源语言与弱势人群语音建模、助残与辅助交互技术、多模态生物标志，以及结合大语言模型/语音基础模型的可解释与生成式AI。同时也对智能现代影院感兴趣。主持参与欧盟H2020和荷兰NOW项目，在IEEE TASLP、Computer Speech and Language, ICASSP, Interspeech等顶级期刊/会议发表论文20余篇。欢迎人工智能、语音语言技术等领域合作及优秀学生加入。

Z. Yue*, E. Loweimi, Z. Cvetkovic, J. Barker and H. Christensen (2025). Raw Acoustic-articulatory Multimodal Dysarthric Speech Recognition. Computer Speech & Language, Vol. 95, pp. 101839. DOI:10.1016/j.csl.2025.101839.
E. Loweimi, Z. Yue*, P. Bell, S. Renals, and Z. Cvetkovic (2023). Multi-stream Acoustic Modelling using Raw Real and Imaginary Parts of the Fourier Transform. IEEE/ACM Transaction on Audio, Speech and Language Processing (TASLP), Vol. 31, pp. 876 - 890. DOI: 10.1109/TASLP.2023.3237167.

Z. Yue*, E. Loweimi J. Barker, H. Christensen, and Z. Cvetkovic. (2022). Modelling from Raw Source and Filter Components for Dysarthric Speech Recognition. IEEE/ACM Transaction on Audio, Speech and Language Processing (TASLP), Vol. 30, pp. 2968 - 2980. DOI: 10.1109/TASLP.2022.3205766.

Z. Yue*, M. Barberis, T. Patel, J. Dineley,W. Doedens, L. Stipdonk, E. Witte, E. Loweimi, H. Van hamme, D. Satoer, M. Ruiter, LM. Velazquez, N. Cummins, O. Scharenborg. (2025). Challenges and practical guidelines for atypical speech data collection, annotation, usage and sharing: A multi-project perspective. In INTERSPEECH. pp. 3943–3947. ISCA. 17-21 August, Rotterdam, the Netherlands. DOI: 10.21437/Interspeech.2025-2774. (Shortlisted Best Theme Paper Award.)

Z. Yue*, H. Christensen, and J. Barker (2020). Autoencoder bottleneck features with multi-task optimisation for improved continuous dysarthric speech recognition. In INTERSPEECH, pp. 4581-4585. ISCA. 25-29 October, Virtual. DOI: 10.21437/Interspeech.2020-2746.

Z. Yue*, F. Xiong, H. Christensen, and J. Barker (2020). Exploring appropriate acoustic and language model choices for continuous dysarthric speech recognition. In ICASSP, pp. 6094-6098. IEEE. 04-08 May, Barcelona, Spain. DOI: 10.1109/ICASSP40776.2020.9054343。

Z. Yue*, D. Kayande, Z. Cvetkovic, E. Loweimi. (2026). Probing Whisper for Dysarthric Speech in Detection and Assessment. In IEEE ICASSP 2026. DOI: 10.48550/arXiv.2510.04219.

D. Groot, T. Patel, D. Kayande, O. Scharenborg, Z. Yue*. (2025). Objective and Subjective Evaluation of Diffusion-Based Speech Enhancement for Dysarthric Speech. In INTERSPEECH. pp. 2025-2768. ISCA. 17-21 August, Rotterdam, the Netherlands. DOI: 10.21437/Interspeech.2025-2768.

F. Xiong, J. Barker, Z. Yue*, and H. Christensen (2020). Source domain data selection for improved transfer learning targeting dysarthric speech recognition speech recognition. In ICASSP, pp. 7424-7428. IEEE. 04-08 May, Barcelona, Spain. DOI: 10.1109/ICASSP40776.2020.9054694.

Z. Yue*, E. Loweimi, Z. Cvetkovic, H. Christensen, and J. Barker (2022). Multi-modal Acoustic-articulatory Feature Fusion for Dysarthric Speech Recognition. In ICASSP, pp. 7372-7376. IEEE. 23-27 May, Singapore. DOI: 10.1109/ICASSP43922.2022.9746855.

Z. Yue*, E. Loweimi, Z. Cvetkovic (2022). Raw Source and Filter modelling for dysarthric speech recognition. In ICASSP, IEEE. 23-27 May, Singapore. DOI: 10.1109/ICASSP43922.2022.9746553.

Z. Yue*, E. Loweimi and Z. Cvetkovic. (2023). Dysarthric speech recognition, detection and classification using raw phase and magnitude spectra. In INTERSPEECH, ISCA. 20-24 August, Dublin, Ireland. DOI:10.21437/Interspeech. 2023-222.

C. Li, E. Yeo, K. Choi, PA. Pérez-Toro, M. Someki, RK. Das, Z. Yue*, J. Rafael Orozco-Arroyave, E. Nöth, DR Mortensen. (2025). Towards Inclusive ASR: Investigating Voice Conversion for Dysarthric Speech Recognition in Low-Resource Languages. In INTERSPEECH. pp. 2025-2768. ISCA. 17-21 August, Rotterdam, the Netherlands. DOI: 10.48550/arXiv.2505.14874.

Z. Yue*, Y. Zhang. (2025). End-to-end acoustic-articulatory dysarthric speech recognition leveraging large-scale pretrained acoustic features. In ICASSP, pp. 1-5. IEEE. 06-11 April, Hyderabad, India. DOI: 10.1109/49660.2025.10888412.