Publications

đź“” 2026

  1. Zhe Li, Man-Wai Mak, Mert Pilanci, Hung Yi Lee, and Helen Meng, “Towards a Unified View of Parameter-Efficient Speech Pretrained Models for Speaker Verification,” in IEEE Transactions on Audio, Speech and Language Processing. (Accepted to appear)
  2. Zezhong Jin, Shujie Liu, Zhe Li, Chong-Xin Gan, Zilong Huang, Man-Wai Mak, and Kong Aik Lee, “Distilling Attention Knowledge for Speaker Verification,” in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2026), Barcelona, Spain. (Accepted to appear)
  3. Liting Jiang, Di Wu, Zhe Li, Yanbing Li, and Hao Huang, “2I-Instruct: Generative Joint Empathy Detection and Empathy Intent Classification via Inter-Task and Inter-Instance Interactions,” in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2026), Barcelona, Spain. (Accepted to appear)

đź“” 2025

  1. Xiaozhe Qi, Liang He, Zhe Li, et al., “WhisMultiNet: Advancing End-to-End Speech Topic Classification with Whisper and MultiGateGNN” in IEEE/ACM Transactions on Audio, Speech and Language Processing.
  2. Zhe Li, Man-Wai Mak, Jen-Tzung Chien, Mert Pilanci, Zezhong Jin, and Helen Meng, “Disentangling Speech Representations Learning with Latent Diffusion for Speaker Verification,” in IEEE/ACM Transactions on Audio, Speech and Language Processing.
  3. Zezhong Jin, Shubhang Desai, Xu Chen, Biyi Fang, Zhuoyi Huang, Zhe Li, Gan, Xiao Tu, Man-Wai Mak, Yan Lu, Shujie Liu. TrInk: Ink Generation with Transformer Network. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), Main Conference.
  4. Zhe Li, Man-Wai Mak, Mert Pilanci, and Helen Meng, “Mutual Information-Enhanced Contrastive Learning with Margin for Maximal Speaker Separability,” in IEEE/ACM Transactions on Audio, Speech and Language Processing. SCI Q1 Top.
  5. Jiabao Sheng, Zhe Li, Jiang Zhang, Saikit Lam, Zhi Chen, Lei Xing, and Jing Cai, “Boosting Generalizability in NPC ART Prediction via Multi-Omics Feature Mapping,” presented at the Proc. of International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Daejeon, South Korea, Sep. 2025.
  6. Zhe Li, Man-Wai Mak, Jen-Tzung Chien, Mert Pilanci, Zezhong Jin, and Helen Meng, “Disentangling Speaker and Content in Pre-trained Speech Models with Latent Diffusion for Robust Speaker Verification,” in Proceedings of Interspeech, Rotterdam, Netherlands, 2025. CCF C
  7. Chong-Xin Gan, Zhe Li, Zezhong Jin, Zilong Huang, Man-Wai Mak, Kong Aik Lee, IDIR: Identifying and Distilling Informative Relations for Speaker Verification, Proceedings of InterSpeech, Rotterdam, Netherlands, 2025. CCF C
  8. Tiquan Gu, Zhenzhen He, Zhe Li, and Yaling Wan, “Information-assisted and sentiment relation-driven for aspect-based sentiment analysis,” Expert Systems with Applications, vol. 278, p. 127308, 2025. SCI Q1 CCF C.
  9. Zhe Li, Man-Wai Mak, Mert Pilanci, Hung Yi Lee, and Helen Meng, “Spectral-Aware Low-Rank Adaptation for Speaker Verification,” in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025. CCF B.
  10. Zezhong Jin, Youzhi Tu, Zhe Li, Zilong Huang, Chongxin Gan, and Man-Wai Mak, “Denoising Student Features with Diffusion Models for Knowledge Distillation in Speaker Verification”, in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025. CCF B.
  11. Liting Jiang, Di Wu, Zhe Li, Shuangyong Song, Yanbing Li, and Hao Huang, “Utterance as A Bridge: Few-shot Joint Learning of Empathy Detection and Empathy Intent Classification”, in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025. CCF B.
  12. Ivan Villa-Renteria, Mason Wang, Zachary Shah, Zhe Li, Soohyun Kim, Neelesh Ramachandran, and Mert Pilanci, “Subtractive Training for Music Stem Insertion using Diffusion Models,” in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025. CCF B.

đź“” 2024

  1. Chenyu Zhou, Xiuhong Li, Zhe Li, et al., “Enhancing multimodal rumor detection with statistical image features and modal alignment via contrastive learning,” in Proceedings of the Pacific Rim International Conference on Artificial Intelligence (PRICAI), 2024. CCF C. Best Student Paper Runner-Up Award
  2. Tianchi Qiu, Xiuhong Li, Zhe Li, et al., “Locate, enhance and fuse: a progressively optimized network for camouflaged object detection,” Multimedia Tools and Applications, vol. xxx, no. xxx, pp. xxx-xxx, 2024. SCI Q3 CCF C.
  3. Xiaofan Wang, Xiuhong Li, Zhe Li, et al., “Multimodal sentiment analysis model based on alignment prompt learning,” in Proceedings of the Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2024. CCF C.
  4. Zhe Li, Man-Wai Mak, Hung Yi Lee, and Helen Meng, “Parameter-efficient fine-tuning of speaker-aware dynamic prompts for speaker verification,” in Proceedings of InterSpeech, 2024. CCF C.
  5. Guinan Li, Jiajun Deng, Zhe Li, et al., “Joint speaker features learning for audio-visual multichannel speech separation and recognition,” in Proceedings of InterSpeech, 2024. CCF C.
  6. Zhenzhen He, Jiong Yu, Zhe Li, et al., “Cardinality estimation for property graph queries with gated learning approach on the graph database,” Multimedia Tools and Applications, 2024. SCI Q3 CCF C.
  7. Wandi Wang, Mahdi Motagh, Zhe Li, et al., “A framework for automated landslide dating utilizing SAR-derived parameters time-series, an enhanced transformer model, and dynamic thresholding,” International Journal of Applied Earth Observation and Geoinformation, vol. 129, 2024. SCI Q1 Top.
  8. Songlin Li, Xiuhong Li, Zhe Li, et al., “Dual guidance enhancing camouflaged object detection via focusing boundary and localization representation,” in Proceedings of IEEE International Conference on Multimedia and Expo (ICME), 2024. CCF B.
  9. Dan Yang, Xiuhong Li, Zhe Li, et al., “Prompt fusion interaction transformer for aspect-based multimodal sentiment analysis,” in Proceedings of IEEE International Conference on Multimedia and Expo (ICME), 2024. CCF B.
  10. Songlin Li, Xiuhong Li, Zhe Li, et al., “Boundary-guided fusion of multi-level features network for camouflaged object detection,” in Proceedings of the International Joint Conference on Neural Networks (IJCNN), 2024. CCF C.
  11. Fan Chen, Xiuhong Li, Zhe Li, et al., “Multimodal rumor detection via multimodal prompt learning,” in Proceedings of the International Joint Conference on Neural Networks (IJCNN), 2024. CCF C.
  12. Zhe Li, Man-Wai Mak, and Helen Meng, “Dual parameter-efficient fine-tuning for speaker representation via speaker prompt tuning and adapters,” in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024. CCF B.
  13. Di Wu, Liting. Jiang, Lili Yin, Kai Wang, Haoxiang Su, Zhe Li, and Hao Huang, “Dual level intent-slot interaction for improved multi-intent spoken language understanding,” in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2024. CCF B.

đź“” 2023

  1. Zhe Li, Man-Wai Mak, and Helen Meng, “Discriminative Speaker Representation via Contrastive Learning with Class-Aware Attention in Angular Space,” in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece, 2023. CCF B.
  2. Jiabao Sheng, Zhe Li, Sai-Kit Lam, Jiang Zhang, Xinzhi Teng, Yuanpeng Zhang, Jing Cai, “Multi-view Contrastive Learning with Additive Margin for Adaptive Nasopharyngeal Carcinoma Radiotherapy Prediction,” in Proceedings of the 2023 International Conference on Multimedia Retrieval, 2022. CCF B.
  3. Feng Yan, Zhe Li, Yanbing Li, Wushour Silamu, “Knowledge-aware Image Understanding with Multi-level Visual Representation Enhancement for Visual Question Answering,” Machine Learning, pp. 1-17, 2023. SCI Q1 CCF B.
  4. Jun Shi, Zhe Li, “Knowledge Transfer via Leveraging Teacher-Student Network with Visual Attention to Enhance Atmospheric Sand Image Restoration,” in Proceedings of Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2023. CCF C.
  5. Chenyu Zhou, Xiuhong Li, Zhe Li, “Multimodal Rumor Detection by Using Additive Angular Margin with Class-aware Attention for Hard Samples,” in Proceedings of Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2023. CCF C.
  6. Songlin Li, Xiuhong Li, Zhe Li, “Emphasizing Boundary-Positioning and Leveraging Multi-Scale Feature Fusion for Camouflaged Object Detection,” in Proceedings of Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2023. CCF C.
  7. Qinglang Guo, Yong Liao, Zhe Li, et al., “Neighborhood-Aware Convolutional Models for Effective Link Prediction in Knowledge Graph Embedding,” in IJCAI Workshop, 2023. CCF A.
  8. Zhenzhen He, Jiong Yu, Zhe Li, et al., “Query cost estimation in graph databases via emphasizing query dependencies by using a neural reasoning network,” Concurrency and Computation: Practice and Experience, vol. 35, no. 23, e7817, 2023. SCI Q2 CCF C.
  9. Di Wu, Liting Jiang, Lili Yin, Zhe Li, and Hao Huang, “CEA-Net: A Co-interactive External Attention Network for Joint Intent Detection and Slot Filling,” Neural Computing and Applications, pp. 1-13, 2023. SCI Q2 CCF C.
  10. Yan Ke, Wanghao Mo, Zhe Li, Ruyi Cao, and Wendong Zhang, “MDCN: Multi-scale Dilated Convolutional Enhanced Residual Network for Traffic Sign Detection,” in Proceedings of International Conference on Advanced Data Mining and Applications, Springer Nature Switzerland, pp. 584-597, 2023. CCF C.
  11. Zhenyu Yang, Yu Wang, Guojing Liu, Zhe Li, and Xingang Wang, “Recommendation Model Based on Multi-grained Interaction that Fuses Users’ Dynamic Interests,” International Journal of Machine Learning and Cybernetics, pp. 1-15, 2023. SCI Q1.
  12. Qinglang Guo, Yong Liao, Zhe Li, et al., “Multi-Modal Representation via Contrastive Learning with Attention Bottleneck Fusion and Attentive Statistics Features,” Entropy, vol. 25, no. 10, 2023, pp. 1421. SCI Q2.
  13. Qinglang. Guo, Yong. Liao, Zhe Li, et al., “Convolutional Models with Multi-Feature Fusion for Effective Link Prediction in Knowledge Graph Embedding,” Entropy, vol. 25, no. 10, 2023, pp. 1472. SCI Q2.

đź“” 2022

  1. Zhe Li and Man-Wai Mak, “Speaker Representation Learning via Contrastive Loss with Maximal Speaker Separability,” in Proceedings of the 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 962-967, 2022.
  2. Huiru Wang, Xiuhong Li, Zhe Li, et al., “Survey of multimodal pre-training models,” Journal of Computer Applications, vol. 43, no. 4, pp. 991, 2023.
  3. Chunming Ma, Xiuhong Li, Zhe Li, et al., “Survey of event extraction,” Journal of Computer Applications, vol. 42, no. 10, pp. 2975, 2022.

đź“” 2021

  1. Zunwang Ke, Jiabao Sheng, Zhe Li, Wushour. Silamu, and Qinglang Guo, “Knowledge-Guided Sentiment Analysis Via Learning From Natural Language Explanations,” IEEE Access, vol. 9, pp. 3570-3578, 2021. SCI Q1.
  2. Zeyu Ren, Zhenchao Wang, Zunwang Ke, Zhe Li, and Wushour Silamu, “A survey of multimodal data fusion,” Computer Engineering and Applications, vol. 57, no. 18, pp. 49-64, 2021.
  3. Yuze Li, Xin Luan, Zunwang Ke, Zhe Li, and Wushour Silamu, “A survey of knowledge-guided pre-trained language models,” Computer Engineering, pp. 18-33, 2023.
  4. Wanyue Liu, Aishan Wumaier, Zhe Li, Yue Han, Daren Zhang, Nian Yi. Neural Machine Translation Based on Multi-sub-word Sequence Fusion. Journal of Chinese Information Processing. vol. 37, no. 2, pp. 87-96, 106, 2023.

đź“” 2020

  1. Zhe Li, Xiuhong Li, Jiabao Sheng, et al., “AgglutiFiT: Efficient Low-Resource Agglutinative Language Model Fine-Tuning,” IEEE Access, vol. 8, pp. 148489-148499, 2020. SCI Q1.
  2. Zhe Li, Mieradilijiang Maimaiti, Jiabao Sheng, et al., “An Empirical Study on Deep Neural Network Models for Chinese Dialogue Generation,” Symmetry-Basel, vol. 12, no. 11, p. 1756, 2020. SCI Q2.
  3. Xiuhong Li, Zhe Li, Jiabao Sheng, et al., “Low-Resource Text Classification via Cross-lingual Language Model Fine-tuning,” in Proceedings of the 19th Chinese National Conference on Computational Linguistics, pp. 994-1005, 2020. [C]
  4. Qing Yu, Zhe Li, Jiabao Sheng, et al., “YuQ: A Chinese-Uyghur Medical Domain Neural Machine Translation Dataset Towards Knowledge-driven,” in Proceedings of the 16th China Conference on Machine Translation (CCMT), 2020. [C]
  5. Zunwang Ke, Zhe Li, Chenzhi Zhou, et al., “Rumor Detection on Social Media via Fused Semantic Information and a Propagation Heterogeneous Graph,” Symmetry-Basel, vol. 12, no. 11, p. 1806, 2020. SCI Q2.
  6. Jiabao Sheng, Aishan Wumaier, Zhe Li, “POISE: Efficient Cross-Domain Chinese Named Entity Recognization via Transfer Learning,” Symmetry-Basel, vol. 12, no. 10, p. 1673, 2020. SCI Q2.
  7. Xiangpeng Kong, Wushour Silamu, Qimeng Yang, and Zhe Li, “Uyghur Named Entity Recognition via Transfer Learning,” Journal of Northeast Normal University (Natural Science Edition), vol. 52, no. 2, pp. 58–65, 2020.