KS-Net: Multi-band joint speech restoration and enhancement network for 2024 ICASSP SSI Challenge
Paper ā¢ 2402.01808 ā¢ Published ā¢ 1
š Speech Enhancement
Unlocking a new era in Speech Enhancement, powered by the latest AI technologies, for superior audio quality improvements! š
Note š Conference: ICASSP, 14-19 April 2024 | Seoul, Korea š°š· š Paper: https://huggingface.co/papers/2402.01808
Unsupervised speech enhancement with diffusion-based generative models
Paper ā¢ 2309.10450 ā¢ Published ā¢ 1Note š Conference: ICASSP, 14-19 April 2024 | Seoul, Korea š°š· š Paper: https://huggingface.co/papers/2309.10450 š Repository: https://github.com/joanne-b-nortier/UDiffSE
Diffusion-based speech enhancement with a weighted generative-supervised learning loss
Paper ā¢ 2309.10457 ā¢ Published ā¢ 1Note š Conference: ICASSP, 14-19 April 2024 | Seoul, Korea š°š· š Paper: https://huggingface.co/papers/2309.10457
Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain
Paper ā¢ 2203.17004 ā¢ PublishedNote š Conference: INTERSPEECH, 18-22 September 2022 | Incheon, Korea š°š· š Paper: https://huggingface.co/papers/2203.17004 š Web Page: https://www.inf.uni-hamburg.de/en/inst/ab/sp/publications/sgmse š Repository: https://github.com/sp-uhh/sgmse
Speech Enhancement and Dereverberation with Diffusion-based Generative Models
Paper ā¢ 2208.05830 ā¢ Published ā¢ 4Note š Journal: EEE/ACM Transactions on Audio, Speech, and Language Processing ā Vol. 31 ā pp. 2351-2364 ā 2023 š Paper: https://huggingface.co/papers/2208.05830 š Web Page: https://www.inf.uni-hamburg.de/en/inst/ab/sp/publications/sgmse š Repository: https://github.com/sp-uhh/sgmse
Attention is All You Need in Speech Separation
Paper ā¢ 2010.13154 ā¢ PublishedNote š Conference: ICASSP, 6-11 June 2021 | Toronto, Ontario, Canada šØš¦ š Paper: https://huggingface.co/papers/2010.13154 š„ Models š¤: - https://huggingface.co/speechbrain/sepformer-wham-enhancement - https://huggingface.co/speechbrain/sepformer-dns4-16k-enhancement
StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation
Paper ā¢ 2212.11851 ā¢ Published ā¢ 1Note š Journal: IEEE/ACM Transactions on Audio, Speech, and Language Processing ā Vol. 31 ā pp. 2351-2364 ā 2023 š Paper: https://huggingface.co/papers/2212.11851 š Web Page: https://www.inf.uni-hamburg.de/en/inst/ab/sp/publications/storm.html š Repository: https://github.com/sp-uhh/storm
AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement
Paper ā¢ 2309.08030 ā¢ Published ā¢ 1Note š® Post: https://huggingface.co/posts/DmitryRyumin/805387906293219 š Conference: ICASSP, 14-19 April 2024 | Seoul, Korea š°š· š Paper: https://huggingface.co/papers/2309.08030 š Web Page: https://home.ttic.edu/~jcchou/demo/avse/avse_demo.html