OpenCodePapers

speech-enhancement-on-easycom

Speech Enhancement
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodePESQSTOIViSQOLHASQIAudio Quality MOSSDRESTOIHASPISI-SDRSIIBSNRSegSNRModelNameReleaseDate
EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments✓ Link1.170.5441.680.249-12.90.3790.830-23.4139-10.1-12.2MaxDI (Baseline)2021-07-09
ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement4.19ReVISE (ch2)2022-12-21
ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement4.11ReVISE (bf)2022-12-21
ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement2.95Demucs (ch2)2022-12-21
ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement2.39Demucs (bf)2022-12-21
Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments-4.76DAJA (MVDR,HMA,1000) (Overlapped Speech)2022-07-15
Check out how to contribute new results.