icassp2024

icassp2024 arxiv

README.md

@@ -12,6 +12,30 @@ license: cc-by-nc-4.0
 
 
 ```
+@misc{zhang2024emotalker,
+      title={EmoTalker: Emotionally Editable Talking Face Generation via Diffusion Model}, 
+      author={Bingyuan Zhang and Xulong Zhang and Ning Cheng and Jun Yu and Jing Xiao and Jianzong Wang},
+      year={2024},
+      eprint={2401.08049},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+@misc{tang2024edtts,
+      title={ED-TTS: Multi-Scale Emotion Modeling using Cross-Domain Emotion Diarization for Emotional Speech Synthesis}, 
+      author={Haobin Tang and Xulong Zhang and Ning Cheng and Jing Xiao and Jianzong Wang},
+      year={2024},
+      eprint={2401.08166},
+      archivePrefix={arXiv},
+      primaryClass={eess.AS}
+}
+@misc{deng2024learning,
+      title={Learning Disentangled Speech Representations with Contrastive Learning and Time-Invariant Retrieval}, 
+      author={Yimin Deng and Huaizhen Tang and Xulong Zhang and Ning Cheng and Jing Xiao and Jianzong Wang},
+      year={2024},
+      eprint={2401.08096},
+      archivePrefix={arXiv},
+      primaryClass={cs.SD}
+}
 @misc{wang2023dqrtts,
       title={DQR-TTS: Semi-supervised Text-to-speech Synthesis with Dynamic Quantized Representation}, 
       author={Jianzong Wang and Pengcheng Li and Xulong Zhang and Ning Cheng and Jing Xiao},