Showing 1–20 of 27 results
/ Date/ Name
Oct 13, 2021Independence-based Joint Dereverberation and Separation with Neural Source ModelNov 18, 2022Self-Remixing: Unsupervised Speech Separation via Separation and RemixingMay 29, 2025Interspeech 2025 URGENT Speech Enhancement ChallengeMay 12, 2025Is MixIT Really Unsuitable for Correlated Sources? Exploring MixIT for Unsupervised Pre-training in Music Source SeparationOct 12, 2023A Single Speech Enhancement Model Unifying Dereverberation, Denoising, Speaker Counting, Separation, and ExtractionApr 1, 2022Spatial Loss for Unsupervised Multi-channel Source SeparationSep 1, 2023Remixing-based Unsupervised Source Separation from ScratchApr 28, 2025A Comparative Study on Positional Encoding for Time-frequency Domain Dual-path Transformer-based Source Separation ModelsMar 26, 2022Remix-cycle-consistent Learning on Adversarially Learned Separator for Accurate and Stable Unsupervised Speech SeparationFeb 9, 2026Input-Adaptive Spectral Feature Compression by Sequence Modeling for Source SeparationAug 6, 2024TF-Locoformer: Transformer with Local Modeling by Convolution for Speech Separation and EnhancementJun 2, 2025Lessons Learned from the URGENT 2024 Speech Enhancement ChallengeOct 24, 2025FlexIO: Flexible Single- and Multi-Channel Speech Separation and EnhancementSep 27, 2023Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative StudyJun 30, 2025URGENT-PK: Perceptually-Aligned Ranking Model Designed for Speech Enhancement CompetitionSep 20, 2024Leveraging Audio-Only Data for Text-Queried Target Sound ExtractionJul 15, 2025P.808 Multilingual Speech Enhancement Testing: Approach and Results of URGENT 2025 ChallengeJan 26, 2026UrgentMOS: Unified Multi-Metric and Preference Learning for Robust Speech Quality AssessmentSep 19, 2023Exploring Speech Enhancement for Low-resource Speech SynthesisJun 7, 2024URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement