Publications

Thesis

1. Data-Efficient Approaches for Audio Classification and Separation Zhepei Wang Doctoral Dissertation in Computer Science, University of Illinois Urbana-Champaign 2023 [PDF] [Slides]

Peer-Reviewed Articles

1. Unsupervised Improvement of Audio-Text Cross-Modal Representations Zhepei Wang, Yusuf Cem Subakan, Krishna Subramani, Junkai Wu, Tiago Tavares, Fabio Ayres, and Paris Smaragdis In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2023 [PDF] [Video] [Poster] [Code]
2. A Framework for Unified Real-time Personalized and Non-Personalized Speech Enhancement Zhepei Wang, Ritwik Giri, Devansh Shah, Jean-Marc Valin, Michael M. Goodwin, and Paris Smaragdis In IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2023 [PDF] [Video] [Poster]
3. Compute and Memory Efficient Universal Sound Source Separation Efthymios Tzinis, Zhepei Wang, Xilin Jiang, and Paris Smaragdis In Journal of Signal Processing Systems 2022 [PDF] [Code]
4. Learning Representations for New Sound Classes With Continual Self-Supervised Learning Zhepei Wang, Yusuf Cem Subakan, Xilin Jiang, Junkai Wu, Efthymios Tzinis, Mirco Ravanelli, and Paris Smaragdis In IEEE Signal Processing Letters 2022 [PDF] [Poster] [Code]
5. Improved Singing Voice Separation with Chromagram-Based Pitch-Aware Remixing Siyuan Yuan, Zhepei Wang, Umut Isik, Ritwik Giri, Jean-Marc Valin, Michael M. Goodwin, and Arvindh Krishnaswamy In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2022 [PDF]
6. Separate But Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data Efthymios Tzinis, Jonah Casebeer, Zhepei Wang, and Paris Smaragdis In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2021 [PDF]
7. Sound Event Detection with Adaptive Frequency Selection Zhepei Wang, Jonah Casebeer, Adam Clemmitt, Efthymios Tzinis, and Paris Smaragdis In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2021 [PDF] [Video] [Poster] [Code]
8. Semi-Supervised Singing Voice Separation With Noisy Self-Training Zhepei Wang, Ritwik Giri, Umut Isik, Jean-Marc Valin, and Arvindh Krishnaswamy In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2021 [PDF] [Video] [Poster]
9. Sudo RM -RF: Efficient Networks for Universal Audio Source Separation Efthymios Tzinis, Zhepei Wang, and Paris Smaragdis In IEEE International Workshop on Machine Learning for Signal Processing (MLSP) 2020 [PDF] [Code]
10. Two-Step Sound Source Separation: Training On Learned Latent Targets Efthymios Tzinis, Shrikant Venkataramani, Zhepei Wang, Yusuf Cem Sübakan, and Paris Smaragdis In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2020 [PDF]
11. Continual Learning of New Sound Classes Using Generative Replay Zhepei Wang, Yusuf Cem Subakan, Efthymios Tzinis, Paris Smaragdis, and Laurent Charlin In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2019 [PDF]
12. Multi-View Networks For Multi-Channel Audio Classification Jonah Casebeer, Zhepei Wang, and Paris Smaragdis In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019 [PDF]

Preprints

1. Audio Editing with Non-Rigid Text Prompts Francesco Paissan, Zhepei Wang, Mirco Ravanelli, Paris Smaragdis, and Yusuf Cem Subakan preprint 2023 [PDF] [HTML]
2. Effects of Data Leakage in Zero-Shot Learning with Contrastive Audio-Text Pretraining Tiago Tavares, Fabio Ayres, Zhepei Wang, and Paris Smaragdis preprint 2023
3. Semi-supervised Time Domain Target Speaker Extraction with Attention Zhepei Wang, Ritwik Giri, Shrikant Venkataramani, Umut Isik, Jean-Marc Valin, Paris Smaragdis, Michael M. Goodwin, and Arvindh Krishnaswamy preprint 2022 [PDF] [Code]

Reports

1. Image-Text Classification to Correct the Amazon PrimeNow Search Experience Zhepei Wang, Alex Mitchell, Kofi Sekyi-Appiah, and Tina Zhu Clinic (Senior Capstone Project) Report in Computer Science, Harvey Mudd College 2018 [PDF] [Poster]