Prof. Thomas Fang Zheng
Tsinghua University, China
Email: [email protected]
Qualifications
1997 Ph.D.,Tsinghua University, China
1992 M.S.,Tsinghua University, China
1990 B.S.,Tsinghua
University, China
Publications (Selected)
-
Wu, Xiaolong, et al. "A Chinese natural speech complex emotion dataset based on emotion vector annotation method: X. Wu et al." Language Resources and Evaluation 59.3 (2025): 3029-3050.
-
Wu, Xiaolong, et al. "ISL-MED: A General Iterative Self-Learning Framework for Speech Complex Emotion Detection." 2025 International Joint Conference on Neural Networks (IJCNN). IEEE, 2025.
-
Investigation of Zero-shot Text-to-Speech Models for Enhancing Short-Utterance Speaker Verification
-
Zhao, Qiuming, et al. "Speaker Adaptive Mixture of Weight-Decomposed LoRA Experts for On-Device End-to-End ASR." IEEE Transactions on Audio, Speech and Language Processing (2025).
-
Abu, Turi, et al. "Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language." ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2025.
-
Zhao, Qiuming, Guangzhi Sun, and Chao Zhang. "Low-rank and sparse model merging for multi-lingual speech recognition and translation." arXiv preprint arXiv:2502.17380 (2025).
-
Wu, Xiaolong, et al. "Emotional Atmosphere Soft Label for Emotion Recognition in Conversations." International Conference on Neural Information Processing. Singapore: Springer Nature Singapore, 2024.
-
Huang, Runze, Mingxing Xu, and Thomas Fang Zheng. "Advancing Respiratory Sound Classification: Integration of Audio Spectrogram Transformer with ConnectMix and NEFTune Augmentation." International Conference on Neural Information Processing. Singapore: Springer Nature Singapore, 2024.
-
Feng, Chang, et al. "Constructing Multi-detector Decision Forest for Fake Speech Detection." International Conference on Neural Information Processing. Singapore: Springer Nature Singapore, 2024.
-
Feng, Chang, et al. "Hierarchical Multi-Path and Multi-Model Selection For Fake Speech Detection." 2024 IEEE Spoken Language Technology Workshop (SLT). IEEE, 2024.
-
Zhao, Yiyang, et al. "Whisper-pmfa: Partial multi-scale feature aggregation for speaker verification using whisper models." arXiv preprint arXiv:2408.15585 (2024).
-
Xing, Xujiang, Mingxing Xu, and Thomas Fang Zheng. "A joint noise disentanglement and adversarial training framework for robust speaker verification." arXiv preprint arXiv:2408.11562 (2024).
-
Zhao, Qiuming, et al. "Speaker Adaptation for Quantised End-to-End ASR Models." arXiv preprint arXiv:2408.03979 (2024).
-
Zhao, Qiuming, et al. "Saml: Speaker adaptive mixture of lora experts for end-to-end asr." arXiv preprint arXiv:2406.19706 (2024).
-
Zhao, Qiuming, et al. "Enhancing quantised end-to-end asr models via personalisation." ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2024.
Profile Details
https://www.bnrist.tsinghua.edu.cn/bnristen/info/1246/3067.htm
https://scholar.google.com/citations?user=H3MX_8IAAAAJ&hl=en
https://www.sciencedirect.com/author/55663034600/thomas-fang-zheng
WoS Researcher ID:CKL-3283-2022