Publications
* denotes equal contribution. Full list on Google Scholar.
2026
- Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal DeploymentTransactions on Machine Learning Research (TMLR)
2024
- Let's Go Real Talk: Spoken Dialogue Model for Face-to-Face ConversationAssociation for Computational Linguistics (ACL)★ Outstanding PaperOral
2023
- Intuitive Multilingual Audio-Visual Speech Recognition with a Single-Trained ModelFindings of the Association for Computational Linguistics: EMNLP
- DiffV2S: Diffusion-based Video-to-Speech Synthesis with Vision-guided Speaker EmbeddingIEEE/CVF International Conference on Computer Vision (ICCV)
- Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability ScoringIEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Lip-to-Speech Synthesis in the Wild with Multi-task LearningIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
2022
- VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature SelectionEuropean Conference on Computer Vision (ECCV)
- SyncTalkFace: Talking Face Generation with Precise Lip-syncing via Audio-Lip MemoryAAAI Conference on Artificial Intelligence (AAAI)Oral
2021
- Speech Reconstruction with Reminiscent Sound via Visual Voice MemoryIEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP)
- CroMM-VSR: Cross-Modal Memory Augmented Visual Speech RecognitionIEEE Transactions on Multimedia (TMM)
- Lip to Speech Synthesis with Visual Context Attentional GANConference on Neural Information Processing Systems (NeurIPS)
- Multi-Modality Associative Bridging Through Memory: Speech Sound Recollected From Face VideoIEEE/CVF International Conference on Computer Vision (ICCV)
- Unsupervised Disentangling of Viewpoint and Residues Variations by Substituting Representations for Robust Face RecognitionInternational Conference on Pattern Recognition (ICPR)
2020
- Comprehensive Facial Expression Synthesis Using Human-Interpretable LanguageIEEE International Conference on Image Processing (ICIP)
- Face Tells Detailed Expression: Generating Comprehensive Facial Expression Sentence Through Facial Action UnitsInternational Conference on Multimedia Modeling (MMM)
No matches.