Speech Enhancement based on cascaded two flows
Information
- It is published at INTERSPEECH 2025 (poster)
-
Authors information
- Seonggyu Lee, Sein Cheong, Sangwook Han, Kihyuk Kim and Jong Won Shin (Speech and Audio Processing Lab, Gwangju Institute of Science and Technology, Korea)
- [Video (ENG)], [Video (KOR)]
-
[paper link]
- [paper download] (preprint)
-
[github code]
-
[First author’s google scholar]
-
[First author’s github]
-
[First author’s youtube channel]
-
[FlowSE (ICASSP2025, important previous work)]
Poster
References
[1] S. Lee, S. Cheong, S. Han, and J. W. Shin, “Flowse: Flow matching-based speech enhancement,” in ICASSP, 2025. (It is very important paper)
[2] J.-M. Lermercier, J. Richter, S. Welker, and T. Gerkmann, “Storm: A diffusion-based stochastic regeneration model for speech en hancement and dereverberation,” TASLP, 2023.