Publications

Publications by categories in reversed chronological order. Generated by jekyll-scholar.


2021

  1. Sound Event Detection with Adaptive Frequency Selection Wang, Zhepei, Casebeer, Jonah, Clemmitt, Adam, Tzinis, Efthymios, and Smaragdis, Paris In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2021 [PDF] [Video] [Poster] [Code]
  2. Separate But Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data Tzinis, Efthymios, Casebeer, Jonah, Wang, Zhepei, and Smaragdis, Paris IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2021 [PDF]
  3. Semi-Supervised Singing Voice Separation With Noisy Self-Training Wang, Zhepei, Giri, Ritwik, Isik, Umut, Valin, Jean-Marc, and Krishnaswamy, Arvindh In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2021 [PDF] [Video] [Poster]
  4. Compute and Memory Efficient Universal Sound Source Separation Tzinis, Efthymios, Wang, Zhepei, Jiang, Xilin, and Smaragdis, Paris ArXiv 2021 [PDF]

2020

  1. Sudo RM -RF: Efficient Networks for Universal Audio Source Separation Tzinis, Efthymios, Wang, Zhepei, and Smaragdis, Paris In IEEE International Workshop on Machine Learning for Signal Processing (MLSP) 2020 [PDF]
  2. Two-Step Sound Source Separation: Training On Learned Latent Targets Tzinis, Efthymios, Venkataramani, Shrikant, Wang, Zhepei, Sübakan, Yusuf Cem, and Smaragdis, Paris In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2020 [PDF]

2019

  1. Continual Learning of New Sound Classes Using Generative Replay Wang, Zhepei, Subakan, Yusuf Cem, Tzinis, Efthymios, Smaragdis, Paris, and Charlin, Laurent In IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA) 2019 [PDF]
  2. Multi-View Networks For Multi-Channel Audio Classification Casebeer, Jonah#, Wang, Zhepei#, and Smaragdis, Paris In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019 [PDF]

Remark: # indicates equal contribution