Yimin Deng

Yimin Deng

University of Science and Technology of China

Yimin Deng is a female intern at PAT (Shenzhen) Co., Ltd., currently pursuing a Master’s degree in Computer Technology at the University of Science and Technology of China (USTC). She was selected to participate in the joint cultivation laboratory program between PAT and USTC for the class of 2021 and she was awarded the title of “Outstanding Graduate of the University of Science and Technology of China” in 2024. Her primary research focus is on speech synthesis and voice conversion, particularly emphasizing methods for decoupling speech representations in scenarios with limited or zero samples.

Interests
  • Voice Conversion
  • Talking Face

Publications

  1. Learning Expressive Disentangled Speech Representations with Soft Speech Units and Adversarial Style Augmentation, (2024), †First Author, In IJCNN2024 (CCF-C)
  2. Learning Disentangled Speech Representations with Contrastive Learning and Time-Invariant Retrieval, (2024), †First Author, In ICASSP2024 (CCF-B)
  3. PMVC: Data Augmentation-Based Prosody Modeling for Expressive Voice Conversion, (2023), †First Author, In MM2023 (CCF-A)
  4. CLN-VC: Text-Free Voice Conversion Based on Fine-Grained Style Control and Contrastive Learning with Negative Samples Augmentation, (2023), †First Author, In SpaCCS2023
  5. CP-EB: Talking Face Generation with Controllable Pose and Eye Blinking Embedding (2023) In ISPA2023 (CCF-C)

Events